Illegal, unreported, and unregulated (IUU) fishing activities seriously affect various aspects of human life. However, traditional methods for detecting and monitoring IUU fishing activities at sea have limitations. Although synthetic aperture radar (SAR) can complement existing vessel detection systems, extracting useful information from SAR images using traditional methods remains a challenge, especially in IUU fishing. This paper proposes a deep learning based fishing activity detection system, which is implemented on the xView3 dataset using six classical object detection models: SSD, RetinaNet, FSAF, FCOS, Faster R-CNN, and Cascade R-CNN. In addition, this work employs different enhancement techniques to improve the performance of the Faster R-CNN model. The experimental results demonstrate that training the Faster R-CNN model using the Online Hard Example Mining (OHEM) strategy increases the Avg-F1 value from 0.212 to 0.216.

While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.

Medical image analysis is a significant application of artificial intelligence for disease diagnosis. A crucial step in this process is the identification of regions of interest within the images. This task can be automated using object detection algorithms. YOLO and Faster R-CNN are renowned for such algorithms, each with its own strengths and weaknesses. This study aims to explore the advantages of both techniques to select more accurate bounding boxes for gallbladder detection from ultrasound images, thereby enhancing gallbladder cancer classification. A fusion method that leverages the benefits of both techniques is presented in this study. The proposed method demonstrated superior classification performance, with an accuracy of 92.62%, compared to the individual use of Faster R-CNN and YOLOv8, which yielded accuracies of 90.16% and 82.79%, respectively.

Explaining biodiversity is a central focus in theoretical ecology. A significant obstacle arises from the Competitive Exclusion Principle (CEP), which states that two species competing for the same type of resources cannot coexist at constant population densities, or more generally, the number of consumer species cannot exceed that of resource species at steady states. The conflict between CEP and biodiversity is exemplified by the paradox of the plankton, where a few types of limiting resources support a plethora of plankton species. In this review, we introduce mechanisms proposed over the years for promoting biodiversity in ecosystems, with a special focus on those that alleviate the constraints imposed by the CEP, including mechanisms that challenge the CEP in well-mixed systems at a steady state or those that circumvent its limitations through contextual differences.

The widespread adoption of electric vehicles (EVs) poses several challenges to power distribution networks and smart grid infrastructure due to the possibility of significantly increasing electricity demands, especially during peak hours. Furthermore, when EVs participate in demand-side management programs, charging expenses can be reduced by using optimal charging control policies that fully utilize real-time pricing schemes. However, devising optimal charging methods and control strategies for EVs is challenging due to various stochastic and uncertain environmental factors. Currently, most EV charging controllers operate based on a centralized model. In this paper, we introduce a novel approach for distributed and cooperative charging strategy using a Multi-Agent Reinforcement Learning (MARL) framework. Our method is built upon the Deep Deterministic Policy Gradient (DDPG) algorithm for a group of EVs in a residential community, where all EVs are connected to a shared transformer. This method, referred to as CTDE-DDPG, adopts a Centralized Training Decentralized Execution (CTDE) approach to establish cooperation between agents during the training phase, while ensuring a distributed and privacy-preserving operation during execution. We theoretically examine the performance of centralized and decentralized critics for the DDPG-based MARL implementation and demonstrate their trade-offs. Furthermore, we numerically explore the efficiency, scalability, and performance of centralized and decentralized critics. Our theoretical and numerical results indicate that, despite higher policy gradient variances and training complexity, the CTDE-DDPG framework significantly improves charging efficiency by reducing total variation by approximately %36 and charging cost by around %9.1 on average...

With the development of remote sensing technology in recent decades, spaceborne sensors with sub-meter and meter spatial resolution (Worldview and PlanetScope) have achieved a considerable image quality to generate 3D geospatial data via a stereo matching pipeline. These achievements have significantly increased the data accessibility in 3D, necessitating adapting these 3D geospatial data to analyze human and natural environments. This dissertation explores several novel approaches based on stereo and multi-view satellite image-derived 3D geospatial data, to deal with remote sensing application issues for built-up area modeling and natural environment monitoring, including building model 3D reconstruction, glacier dynamics tracking, and lake algae monitoring. Specifically, the dissertation introduces four parts of novel approaches that deal with the spatial and temporal challenges with satellite-derived 3D data. The first study advances LoD-2 building modeling from satellite-derived Orthophoto and DSMs with a novel approach employing a model-driven workflow that generates building rectangular 3D geometry models. Secondly, we further enhanced our building reconstruction framework for dense urban areas and non-rectangular purposes, we implemented deep learning for unit-level segmentation and introduced a gradient-based circle reconstruction for circular buildings to develop a polygon composition technique for advanced building LoD2 reconstruction. Our third study utilizes high-spatiotemporal resolution PlanetScope satellite imagery for glacier tracking at 3D level in mid-latitude regions. Finally, we proposed a term as "Algal Behavior Function" to refine the quantification of chlorophyll-a concentrations from satellite imagery in water quality monitoring, addressing algae fluctuations and timing discrepancies between satellite observations and field measurements, thus enhancing the precision of underwater algae volume estimates. Overall, this dissertation demonstrates the extensive potential of satellite photogrammetry applications in addressing urban and environmental challenges. It further showcases innovative analytical methodologies that enhance the applicability of adapting stereo and multi-view very high-resolution satellite-derived 3D data. (See full abstract in the document)

Self-supervised learning (SSL) provides a promising alternative for representation learning on hypergraphs without costly labels. However, existing hypergraph SSL models are mostly based on contrastive methods with the instance-level discrimination strategy, suffering from two significant limitations: (1) They select negative samples arbitrarily, which is unreliable in deciding similar and dissimilar pairs, causing training bias. (2) They often require a large number of negative samples, resulting in expensive computational costs. To address the above issues, we propose SE-HSSL, a hypergraph SSL framework with three sampling-efficient self-supervised signals. Specifically, we introduce two sampling-free objectives leveraging the canonical correlation analysis as the node-level and group-level self-supervised signals. Additionally, we develop a novel hierarchical membership-level contrast objective motivated by the cascading overlap relationship in hypergraphs, which can further reduce membership sampling bias and improve the efficiency of sample utilization. Through comprehensive experiments on 7 real-world hypergraphs, we demonstrate the superiority of our approach over the state-of-the-art method in terms of both effectiveness and efficiency.

Timely up-to-date land use/land cover (LULC) maps play a pivotal role in supporting agricultural territory management, environmental monitoring and facilitating well-informed and sustainable decision-making. Typically, when creating a land cover (LC) map, precise ground truth data is collected through time-consuming and expensive field campaigns. This data is then utilized in conjunction with satellite image time series (SITS) through advanced machine learning algorithms to get the final map. Unfortunately, each time this process is repeated (e.g., annually over a region to estimate agricultural production or potential biodiversity loss), new ground truth data must be collected, leading to the complete disregard of previously gathered reference data despite the substantial financial and time investment they have required. How to make value of historical data, from the same or similar study sites, to enhance the current LULC mapping process constitutes a significant challenge that could enable the financial and human-resource efforts invested in previous data campaigns to be valued again. Aiming to tackle this important challenge, we here propose a deep learning framework based on recent advances in domain adaptation and generalization to combine remote sensing and reference data coming from two different domains (e.g. historical data and fresh ones) to ameliorate the current LC mapping process. Our approach, namely REFeD (data Reuse with Effective Feature Disentanglement for land cover mapping), leverages a disentanglement strategy, based on contrastive learning, where invariant and specific per-domain features are derived to recover the intrinsic information related to the downstream LC mapping task and alleviate possible distribution shifts between domains. Additionally, REFeD is equipped with an effective supervision scheme where feature disentanglement is further enforced via multiple levels of supervision at different granularities. The experimental assessment over two study areas covering extremely diverse and contrasted landscapes, namely Koumbia (located in the West-Africa region, in Burkina Faso) and Centre Val de Loire (located in centre Europe, France), underlines the quality of our framework and the obtained findings demonstrate that out-of-year information coming from the same (or similar) study site, at different periods of time, can constitute a valuable additional source of information to enhance the LC mapping process.

Detecting the Earth's inner core motions relative to the mantle presents a considerable challenge due to their indirect accessibility. Seismological observations initially provided evidence for differential/super-rotation of the inner core, but recently demonstrated a possibly about 70-year periodic oscillation. The contrasting results underscore the ongoing enigma surrounding inner core motion, leaving debates unresolved, including the precise oscillate period. In parallel to seismic observations, satellite geodesy has accumulated decades of global high-precision records, providing a novel avenue to probe inner core motions. Here, we detect an about 6-year oscillation from the gravitational field degree-2 order-2 Stokes coefficients derived from satellite observations, and find it has a unique phase correlation with the about 6-year signal in the Earth's length-of-day variations. This correlation is attributed to an inner core oscillation which is controlled by the gravitational coupling between the inner core and lower mantle (mainly due to the density heterogeneity of the two large low-velocity provinces; LLVPs). That is, we independently corroborate the inner core periodic oscillation, albeit with a significantly shorter period than previously suggested. Our findings demonstrate the dense layer of the LLVPs (mean density anomalies of about +0.9 percent at the bottom), consistent with inversions from tidal tomography and Stoneley modes. Furthermore, our research reveals equatorial topographic undulations of about 187 m at the inner core boundary.

A probabilistic framework to study the dependence structure induced by deterministic discrete-time state-space systems between input and output processes is introduced. General sufficient conditions are formulated under which output processes exist and are unique once an input process has been fixed, a property that in the deterministic state-space literature is known as the echo state property. When those conditions are satisfied, the given state-space system becomes a generative model for probabilistic dependences between two sequence spaces. Moreover, those conditions guarantee that the output depends continuously on the input when using the Wasserstein metric. The output processes whose existence is proved are shown to be causal in a specific sense and to generalize those studied in purely deterministic situations. The results in this paper constitute a significant stochastic generalization of sufficient conditions for the deterministic echo state property to hold, in the sense that the stochastic echo state property can be satisfied under contractivity conditions that are strictly weaker than those in deterministic situations. This means that state-space systems can induce a purely probabilistic dependence structure between input and output sequence spaces even when there is no functional relation between those two spaces.

Despite extensive research into ship detection via remote sensing, no studies identify ship-to-ship transfers in satellite imagery. Given the importance of transshipment in illicit shipping practices, this is a significant gap. In what follows, I train a convolutional neural network to accurately detect 4 different types of cargo vessel and two different types of Ship-to-Ship transfer in PlanetScope satellite imagery. I then elaborate a pipeline for the automatic detection of suspected illicit ship-to-ship transfers by cross-referencing satellite detections with vessel borne GPS data. Finally, I apply this method to the Kerch Strait between Ukraine and Russia to identify over 400 dark transshipment events since 2022.

Ocean eddies play a significant role both on the sea surface and beneath it, contributing to the sustainability of marine life dependent on oceanic behaviors. Therefore, it is crucial to investigate ocean eddies to monitor changes in the Earth, particularly in the oceans, and their impact on climate. This study aims to pinpoint ocean eddies using AWS cloud services, specifically SageMaker. The primary objective is to detect small-scale (<20km) ocean eddies from satellite remote images and assess the feasibility of utilizing SageMaker, which offers tools for deploying AI applications. Moreover, this research not only explores the deployment of cloud-based services for remote sensing of Earth data but also evaluates several YOLO (You Only Look Once) models using single and multi-GPU-based services in the cloud. Furthermore, this study underscores the potential of these services, their limitations, challenges related to deployment and resource management, and their user-riendliness for Earth science projects.

Earth observation (EO) satellite missions have been providing detailed images about the state of the Earth and its land cover for over 50 years. Long term missions, such as NASA's Landsat, Terra, and Aqua satellites, and more recently, the ESA's Sentinel missions, record images of the entire world every few days. Although single images provide point-in-time data, repeated images of the same area, or satellite image time series (SITS) provide information about the changing state of vegetation and land use. These SITS are useful for modeling dynamic processes and seasonal changes such as plant phenology. They have potential benefits for many aspects of land and natural resource management, including applications in agricultural, forest, water, and disaster management, urban planning, and mining. However, the resulting satellite image time series (SITS) are complex, incorporating information from the temporal, spatial, and spectral dimensions. Therefore, deep learning methods are often deployed as they can analyze these complex relationships. This review presents a summary of the state-of-the-art methods of modelling environmental, agricultural, and other Earth observation variables from SITS data using deep learning methods. We aim to provide a resource for remote sensing experts interested in using deep learning techniques to enhance Earth observation models with temporal information.

Tidal flow of seawater across the Earth's magnetic field induces electric currents and magnetic fields within the ocean and solid Earth. The amplitude and phase of the induced fields depends on electrical properties of both the seawater and the solid Earth, thus can be used as a proxy to study seabed properties or potentially for monitoring long-term trends in the global ocean climatology. This paper presents new global oceanic tidal magnetic field models and their uncertainties for four tidal constituents, including $M_2, N_2, O_1$ and $Q_1$, which was not reliably retrieved previously. Models are obtained through a robust least-squares analysis of magnetic field observations from the \textit{Swarm} and CHAMP satellites using a specially designed data selection scheme. We compare the retrieved magnetic signals with several alternative models reported in the literature. Additionally, we validate them using a series of high-resolution global 3-D electromagnetic simulations and place constraints on the conductivity of sub-oceanic mantle for all tidal constituents, revealing an excellent agreement between all tidal constituents and the oceanic upper mantle structure.

Time series anomaly detection (TSAD) finds many applications such as monitoring environmental sensors, industry KPIs, patient biomarkers, etc. A two-fold challenge for TSAD is a versatile and unsupervised model that can detect various different types of time series anomalies (spikes, discontinuities, trend shifts, etc.) without any labeled data. Modern neural networks have outstanding ability in modeling complex time series. Self-supervised models in particular tackle unsupervised TSAD by transforming the input via various augmentations to create pseudo anomalies for training. However, their performance is sensitive to the choice of augmentation, which is hard to choose in practice, while there exists no effort in the literature on data augmentation tuning for TSAD without labels. Our work aims to fill this gap. We introduce TSAP for TSA "on autoPilot", which can (self-)tune augmentation hyperparameters end-to-end. It stands on two key components: a differentiable augmentation architecture and an unsupervised validation loss to effectively assess the alignment between augmentation type and anomaly type. Case studies show TSAP's ability to effectively select the (discrete) augmentation type and associated (continuous) hyperparameters. In turn, it outperforms established baselines, including SOTA self-supervised models, on diverse TSAD tasks exhibiting different anomaly types.

This comprehensive review explores electrical and seismic refraction methods, including their emerging techniques, namely electrical resistivity tomography (ERT) and seismic refraction tomography (SRT). It discusses their crucial roles in understanding surface-subsurface crustal dynamics, outlining their principles, strengths, and limitations. Additionally, it provides insights into the induced polarization method and briefly discusses the self-potential method. The review thoroughly examines the mapping of surface-subsurface resistivity and velocity structures, crucial for comprehending Earth's surface, deep crustal, and hazard processes. Despite the numerous benefits of these techniques, challenges persist, necessitating multidisciplinary approaches due to lithology heterogeneities, geological process nuances, and geophysical data uncertainties. Hence, the emergence of machine learning and deep learning in ERT and SRT significantly enhances their accuracy in inversion modeling and geological feature identification. This integration of domain-specific knowledge with data- and image-driven approaches effectively addresses subsurface characterization challenges. Case studies utilizing real-time field electrical and seismic P-wave velocity datasets illustrate concepts, accompanied by the development of new methodological frameworks and analytical modeling. These frameworks provide systematic data modeling, facilitating velocity-resistivity relationships for enhanced geological characterization. This evidence underscores the importance of leveraging state-of-the-art techniques to obtain a broader range of parameters for subsurface structure delineation, environmental risk assessment, and informed decision-making. Ongoing research innovation is anticipated to continue improving capabilities in subsurface geophysical exploration.

Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective representation learning. Recent advances in generative self-supervised learning (SSL) suggest that hypergraph neural networks learned from generative self supervision have the potential to effectively encode the complex hypergraph topology. Designing a generative SSL strategy for hypergraphs, however, is not straightforward. Questions remain with regard to its generative SSL task, connection to downstream tasks, and empirical properties of learned representations. In light of the promises and challenges, we propose a novel generative SSL strategy for hypergraphs. We first formulate a generative SSL task on hypergraphs, hyperedge filling, and highlight its theoretical connection to node classification. Based on the generative SSL task, we propose a hypergraph SSL method, HypeBoy. HypeBoy learns effective general-purpose hypergraph representations, outperforming 16 baseline methods across 11 benchmark datasets.

In the domain of Space Situational Awareness (SSA), the challenges pertaining to orbit determination and catalog correlation are notably pronounced, partly attributable to the escalating presence of non-cooperative satellites engaging in unspecified maneuvers at irregular intervals. This study introduces an initial orbit determination methodology reliant upon data obtained from a single surveillance radar, such as the Spanish Space Surveillance and Tracking Surveillance Radar (S3TSR). The need for fast algorithms within an operational context is considered here as the main design driver. The result is a least-squares fitting procedure that incorporates an analytically formulated approximation of the dynamics under the J2 perturbation, valid for short-term propagation. The algorithm makes use of all available observables, including range-rate, which makes it distinct from other similar methods. The method is compared in a battery of synthetic tests against a classical range and angles fitting method (GTDS) to study the effect of the track length and density of measurements on the full state estimation. The presented methodology is quite versatile, and it is leveraged to improve the estimation quality by adding information of the object's orbital plane obtained from predictions. The resulting method has been named OPOD.

Most studies on machine learning in sensing systems focus on low-level perception tasks that process raw sensory data within a short time window. However, many practical applications, such as human routine modeling and occupancy tracking, require high-level reasoning abilities to comprehend concepts and make inferences based on long-term sensor traces. Existing machine learning-based approaches for handling such complex tasks struggle to generalize due to the limited training samples and the high dimensionality of sensor traces, necessitating the integration of human knowledge for designing first-principle models or logic reasoning methods. We pose a fundamental question: Can we harness the reasoning capabilities and world knowledge of Large Language Models (LLMs) to recognize complex events from long-term spatiotemporal sensor traces? To answer this question, we design an effective prompting framework for LLMs on high-level reasoning tasks, which can handle traces from the raw sensor data as well as the low-level perception results. We also design two strategies to enhance performance with long sensor traces, including summarization before reasoning and selective inclusion of historical traces. Our framework can be implemented in an edge-cloud setup, running small LLMs on the edge for data summarization and performing high-level reasoning on the cloud for privacy preservation. The results show that LLMSense can achieve over 80\% accuracy on two high-level reasoning tasks such as dementia diagnosis with behavior traces and occupancy tracking with environmental sensor traces. This paper provides a few insights and guidelines for leveraging LLM for high-level reasoning on sensor traces and highlights several directions for future work.

We present an uncertainty-aware Digital Twin (DT) for geologic carbon storage (GCS), capable of handling multimodal time-lapse data and controlling CO2 injectivity to mitigate reservoir fracturing risks. In GCS, DT represents virtual replicas of subsurface systems that incorporate real-time data and advanced generative Artificial Intelligence (genAI) techniques, including neural posterior density estimation via simulation-based inference and sequential Bayesian inference. These methods enable the effective monitoring and control of CO2 storage projects, addressing challenges such as subsurface complexity, operational optimization, and risk mitigation. By integrating diverse monitoring data, e.g., geophysical well observations and imaged seismic, DT can bridge the gaps between seemingly distinct fields like geophysics and reservoir engineering. In addition, the recent advancements in genAI also facilitate DT with principled uncertainty quantification. Through recursive training and inference, DT utilizes simulated current state samples, e.g., CO2 saturation, paired with corresponding geophysical field observations to train its neural networks and enable posterior sampling upon receiving new field data. However, it lacks decision-making and control capabilities, which is necessary for full DT functionality. This study aims to demonstrate how DT can inform decision-making processes to prevent risks such as cap rock fracturing during CO2 storage operations.

Monitoring changes in the Earth's surface is crucial for understanding natural processes and human impacts, necessitating precise and comprehensive interpretation methodologies. Remote sensing satellite imagery offers a unique perspective for monitoring these changes, leading to the emergence of remote sensing image change interpretation (RSICI) as a significant research focus. Current RSICI technology encompasses change detection and change captioning, each with its limitations in providing comprehensive interpretation. To address this, we propose an interactive Change-Agent, which can follow user instructions to achieve comprehensive change interpretation and insightful analysis, such as change detection and change captioning, change object counting, change cause analysis, etc. The Change-Agent integrates a multi-level change interpretation (MCI) model as the eyes and a large language model (LLM) as the brain. The MCI model contains two branches of pixel-level change detection and semantic-level change captioning, in which the BI-temporal Iterative Interaction (BI3) layer is proposed to enhance the model's discriminative feature representation capabilities. To support the training of the MCI model, we build the LEVIR-MCI dataset with a large number of change masks and captions of changes. Experiments demonstrate the SOTA performance of the MCI model in achieving both change detection and change description simultaneously, and highlight the promising application value of our Change-Agent in facilitating comprehensive interpretation of surface changes, which opens up a new avenue for intelligent remote sensing applications. To facilitate future research, we will make our dataset and codebase of the MCI model and Change-Agent publicly available at https://github.com/Chen-Yang-Liu/Change-Agent

Deep learning has shown remarkable success in remote sensing change detection (CD), aiming to identify semantic change regions between co-registered satellite image pairs acquired at distinct time stamps. However, existing convolutional neural network and transformer-based frameworks often struggle to accurately segment semantic change regions. Moreover, transformers-based methods with standard self-attention suffer from quadratic computational complexity with respect to the image resolution, making them less practical for CD tasks with limited training data. To address these issues, we propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions while reducing the model size. Our ELGC-Net comprises a Siamese encoder, fusion modules, and a decoder. The focus of our design is the introduction of an Efficient Local-Global Context Aggregator module within the encoder, capturing enhanced global context and local spatial information through a novel pooled-transpose (PT) attention and depthwise convolution, respectively. The PT attention employs pooling operations for robust feature extraction and minimizes computational cost with transposed attention. Extensive experiments on three challenging CD datasets demonstrate that ELGC-Net outperforms existing methods. Compared to the recent transformer-based CD approach (ChangeFormer), ELGC-Net achieves a 1.4% gain in intersection over union metric on the LEVIR-CD dataset, while significantly reducing trainable parameters. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. Finally, we also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings, while achieving comparable performance. Project url https://github.com/techmn/elgcnet.

Accessions are prospective sources of genetic variability, as well as valuable genetic resources to deal with present and future crop breeding difficulties. The assessment of population structure and genetic diversity of tomatoes (Solanum lycopersicum L.) that have been distributed in Iraqi Kurdistan region critical in breeding programs for the production of high-yielding cultivars as well as widening the genetic base of tomato. Using fruit quality indices and molecular markers, a panel of 64 tomato accessions taken from six provinces of Iraqi Kurdistan Region, were analyzed for genetic diversity and population structure. In the analysis of variance, the fruit phenotypic data revealed a high level of significant variability among tomato accessions. The most important characteristics for explaining fruit morphological variability, according to principal component analysis (PCA), were fruit weight, fruit size, fruit diameter, total soluble solids, and moisture content. Seven clades with different fruit characteristics were revealed in the cluster analysis. Genetic diversity and relationships among accessions were analyzed using thirteen inter simple sequence repeat (ISSR), twenty-six start codon-targeted (SCoT) polymorphisms, and fifteen conserved DNA-derived polymorphisms (CDDP). The ISSR, SCoT, and CDDP markers generated 121, 294, and 170 polymorphic bands, respectively, showing a high prevalence of polymorphism. The average polymorphism information content (PIC) values for ISSR, SCoT, and CDDP were 0.81, 0.84, and 0.84, respectively. The accessions were divided into two groups based on the cluster and STRUCTURE analysis results. The Mantel test revealed that three sets of markers had positive and significant relationships.

Means to increase water resources are essential in regions grappling with water scarcity and growing populations. Soil aquifer treatment (SAT) is a cheap, low maintenance, low-energy method to supply water for irrigation of crops consumed raw or even for drinking purposes. However, the most expensive cost-component of SATs is the land use, the infiltration basins the area of which is inversely proportional to the infiltration rate, the most important characteristic of SAT basins design and operation, which until now was believed to be time-dependent and, therefore, difficult to predict. Focusing on the Shafdan SAT in Israel as a showcase and using a decade's worth of data from 50 recharge basins, we study the time dependence of the infiltration rates. The study reveals a noteworthy consistency in the decline of effluent levels during the drainage phase across various flooding events, signifying a constant, head-independent infiltration rate. 97% of over 40,000 flooding events showed this behavior. Furthermore, the infiltration rate calculated in this manner provides good predictions of the average infiltration rate during the entire wetting phase. The water-level-independent infiltration rate is a general feature. It was found in all the 50 studied basins, regardless of the soil sand content, commissioning year, operation conditions and season. The constant infiltration rate law revealed in this study simplifies the prediction of the flooding cycle duration and will facilitate simplified predictive modeling of multiple basins SAT systems. Our research may extend beyond SAT systems, offering insights applicable to other managed aquifer recharge methods, crucial for effective water resource management, ensuring environmental compatibility.

In this work, radioactivity investigations of soil samples from neutral and agricultural sites in Punjab/India have been carried out to study the impact of land use patterns. The analysis of radiological, mineralogical, physicochemical, and morphological attributes of soil samples has been performed employing state-of-the-art techniques. The mean activity concentration of 238U, 232Th, 40K, 235U, and 137Cs, measured using a carbon-loaded p-type HPGe detector, in neutral land was observed as 58.03, 83.95, 445.18, 2.83, and 1.16Bq kg-1, respectively. However, in vegetation land, it was found to be 40.07, 64.68, 596.74, 2.26 and 2.11Bq kg-1, respectively. In the detailed activity analysis, radium equivalent (Raeq) radioactivity is found to be in the safe prescribed limit of 370Bq kg-1 for all investigated soil samples. However, the dosimetric investigations revealed that the outdoor absorbed gamma dose rate (96.08nGy h-1) and consequent annual effective dose rate (0.12mSv y-1) for neutral land, and the gamma dose rate (82.46nGy h-1) and subsequent annual effective dose rate (0.10mSv y-1) for vegetation land marginally exceeded the global average. The surface morphology of neutral land favored more compactness, while agricultural land favored high porosity. Various heavy metals of health concern, namely As, Cd, Co, Cr, Cu, Hg, Pb, Se, and Zn, were also evaluated in all soil samples using Inductively Coupled Plasma-Mass Spectroscopy (ICP-MS). Pollution Load Index (PLI) and Ecological Risk Index (RI) revealed that vegetation land was more anthropogenically contaminated than neutral land, with maximum contamination from Hg and As.

Data mining, particularly the analysis of multivariate time series data, plays a crucial role in extracting insights from complex systems and supporting informed decision-making across diverse domains. However, assessing the similarity of multivariate time series data presents several challenges, including dealing with large datasets, addressing temporal misalignments, and the need for efficient and comprehensive analytical frameworks. To address all these challenges, we propose a novel integrated computational approach known as Multivariate Time series Alignment and Similarity Assessment (MTASA). MTASA is built upon a hybrid methodology designed to optimize time series alignment, complemented by a multiprocessing engine that enhances the utilization of computational resources. This integrated approach comprises four key components, each addressing essential aspects of time series similarity assessment, thereby offering a comprehensive framework for analysis. MTASA is implemented as an open-source Python library with a user-friendly interface, making it accessible to researchers and practitioners. To evaluate the effectiveness of MTASA, we conducted an empirical study focused on assessing agroecosystem similarity using real-world environmental data. The results from this study highlight MTASA's superiority, achieving approximately 1.5 times greater accuracy and twice the speed compared to existing state-of-the-art integrated frameworks for multivariate time series similarity assessment. It is hoped that MTASA will significantly enhance the efficiency and accessibility of multivariate time series analysis, benefitting researchers and practitioners across various domains. Its capabilities in handling large datasets, addressing temporal misalignments, and delivering accurate results make MTASA a valuable tool for deriving insights and aiding decision-making processes in complex systems.

Cytology image segmentation is quite challenging due to its complex cellular structure and multiple overlapping regions. On the other hand, for supervised machine learning techniques, we need a large amount of annotated data, which is costly. In recent years, late fusion techniques have given some promising performances in the field of image classification. In this paper, we have explored a fuzzy-based late fusion techniques for cytology image segmentation. This fusion rule integrates three traditional semantic segmentation models UNet, SegNet, and PSPNet. The technique is applied on two cytology image datasets, i.e., cervical cytology(HErlev) and breast cytology(JUCYT-v1) image datasets. We have achieved maximum MeanIoU score 84.27% and 83.79% on the HErlev dataset and JUCYT-v1 dataset after the proposed late fusion technique, respectively which are better than that of the traditional fusion rules such as average probability, geometric mean, Borda Count, etc. The codes of the proposed model are available on GitHub.

Recent advancements in remote sensing (RS) technologies have shown their potential in accurately classifying local climate zones (LCZs). However, traditional scene-level methods using convolutional neural networks (CNNs) often struggle to integrate prior knowledge of ground objects effectively. Moreover, commonly utilized data sources like Sentinel-2 encounter difficulties in capturing detailed ground object information. To tackle these challenges, we propose a data fusion method that integrates ground object priors extracted from high-resolution Google imagery with Sentinel-2 multispectral imagery. The proposed method introduces a novel Dual-stream Fusion framework for LCZ classification (DF4LCZ), integrating instance-based location features from Google imagery with the scene-level spatial-spectral features extracted from Sentinel-2 imagery. The framework incorporates a Graph Convolutional Network (GCN) module empowered by the Segment Anything Model (SAM) to enhance feature extraction from Google imagery. Simultaneously, the framework employs a 3D-CNN architecture to learn the spectral-spatial features of Sentinel-2 imagery. Experiments are conducted on a multi-source remote sensing image dataset specifically designed for LCZ classification, validating the effectiveness of the proposed DF4LCZ. The related code and dataset are available at https://github.com/ctrlovefly/DF4LCZ.

Time series analysis is a vital task with broad applications in various domains. However, effectively capturing cross-dimension and cross-time dependencies in non-stationary time series poses significant challenges, particularly in the context of environmental factors. The spurious correlation induced by the environment confounds the causal relationships between cross-dimension and cross-time dependencies. In this paper, we introduce a novel framework called Caformer (\underline{\textbf{Ca}}usal Trans\underline{\textbf{former}}) for time series analysis from a causal perspective. Specifically, our framework comprises three components: Dynamic Learner, Environment Learner, and Dependency Learner. The Dynamic Learner unveils dynamic interactions among dimensions, the Environment Learner mitigates spurious correlations caused by environment with a back-door adjustment, and the Dependency Learner aims to infer robust interactions across both time and dimensions. Our Caformer demonstrates consistent state-of-the-art performance across five mainstream time series analysis tasks, including long- and short-term forecasting, imputation, classification, and anomaly detection, with proper interpretability.

This study introduces Pedophysics, an open-source Python package designed to facilitate solutions for users who work in the field of soil assessment using near-surface geophysical electromagnetic techniques. At the core of this software is the ability to translate geophysical data into specific soil properties (and vice-versa) using pedophysical models (PM). Pedophysical modelling techniques offer valuable insights into various realms including precision agriculture, soil health, resource prospecting, nutrient and land management, hydrogeology, and heritage conservation. In developing a tool for pedophysical modelling, some challenges emerged: selecting suitable PMs from the extensive literature, adapting these to specific conditions, and ensuring adequate data availability. While addressing these, we designed an automated workflow that implements robust PMs (selected after a throughout review), apply different modelling approaches based on soil characteristics and targeted properties, and employs pedotransfer functions and assumptions to integrate missing soil data into PMs. The capabilities of Pedophysics extend to handling complex scenarios such as fusing data from different instruments, incorporating continuous monitoring measurements, and soil calibration data. With these solutions, Pedophysics automates the process of deriving targeted soil and geophysical properties with state-of-art accuracy. Hereby, users can rely on Pedophysics to implement specific knowledge about pedophysical modeling. The software promotes global access to advanced soil geophysical solutions by being open-source and encouraging community contributions. Pedophysics is written in pure Python and has minimal dependencies. It can be easily installed from the Python Package Index (PyPI).

In the context of an increasing popularity of data-driven models to represent dynamical systems, many machine learning-based implementations of the Koopman operator have recently been proposed. However, the vast majority of those works are limited to deterministic predictions, while the knowledge of uncertainty is critical in fields like meteorology and climatology. In this work, we investigate the training of ensembles of models to produce stochastic outputs. We show through experiments on real remote sensing image time series that ensembles of independently trained models are highly overconfident and that using a training criterion that explicitly encourages the members to produce predictions with high inter-model variances greatly improves the uncertainty quantification of the ensembles.

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multi-scale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. SatMAE++ achieves mean average precision (mAP) gain of 2.5\% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at \url{https://github.com/techmn/satmae_pp}.

The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from open-vocabulary detection for the remote sensing domain. We develop a few-shot object detector based on a traditional two-stage architecture, where the classification block is replaced by a prototype-based classifier. A large-scale pre-trained model is used to build class-reference embeddings or prototypes, which are compared to region proposal contents for label prediction. In addition, we propose to fine-tune prototypes on available training images to boost performance and learn differences between similar classes, such as aircraft types. We perform extensive evaluations on two remote sensing datasets containing challenging and rare objects. Moreover, we study the performance of both visual and image-text features, namely DINOv2 and CLIP, including two CLIP models specifically tailored for remote sensing applications. Results indicate that visual features are largely superior to vision-language models, as the latter lack the necessary domain-specific vocabulary. Lastly, the developed detector outperforms fully supervised and few-shot methods evaluated on the SIMD and DIOR datasets, despite minimal training parameters.

Distributed Acoustic Sensing (DAS) is promising for traffic monitoring, but its extensive data and sensitivity to vibrations, causing noise, pose computational challenges. To address this, we propose a two-step deep-learning workflow with high efficiency and noise immunity for DAS-based traffic monitoring, focusing on instance vehicle trajectory segmentation and velocity estimation. Our approach begins by generating a diverse synthetic DAS dataset with labeled vehicle signals, tackling the issue of missing training labels in this field. This dataset is used to train a Convolutional Neural Network (CNN) to detect linear vehicle trajectories from the noisy DAS data in the time-space domain. However, due to significant noise, these trajectories are often fragmented and incomplete. To enhance accuracy, we introduce a second step involving the Hough transform. This converts detected linear features into point-like energy clusters in the Hough domain. Another CNN is then employed to focus on these energies, identifying the most significant points. The inverse Hough transform is applied to these points to reconstruct complete, distinct, and noise-free linear vehicle trajectories in the time-space domain. The Hough transform plays a crucial role by enforcing a local linearity constraint on the trajectories, enhancing continuity and noise immunity, and facilitating the separation of individual trajectories and estimation of vehicle velocities (indicated by trajectory slopes in the Hough domain). Our method has shown effectiveness in real-world datasets, proving its value in real-time processing of DAS data and applicability in similar traffic monitoring scenarios. All related codes and data are available at https://github.com/TTMuTian/itm/.

Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high spatial resolution. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We address these shortcomings by learning a consistency model (CM) that efficiently and accurately downscales arbitrary ESM simulations without retraining in a zero-shot manner. Our approach yields probabilistic downscaled fields at a resolution only limited by the observational reference data. We show that the CM outperforms state-of-the-art diffusion models at a fraction of computational cost while maintaining high controllability on the downscaling task. Further, our method generalizes to climate states unseen during training without explicitly formulated physical constraints.

This paper focuses on the hypothesis of optimizing time series predictions using fractal interpolation techniques. In general, the accuracy of machine learning model predictions is closely related to the quality and quantitative aspects of the data used, following the principle of \textit{garbage-in, garbage-out}. In order to quantitatively and qualitatively augment datasets, one of the most prevalent concerns of data scientists is to generate synthetic data, which should follow as closely as possible the actual pattern of the original data. This study proposes three different data augmentation strategies based on fractal interpolation, namely the \textit{Closest Hurst Strategy}, \textit{Closest Values Strategy} and \textit{Formula Strategy}. To validate the strategies, we used four public datasets from the literature, as well as a private dataset obtained from meteorological records in the city of Brasov, Romania. The prediction results obtained with the LSTM model using the presented interpolation strategies showed a significant accuracy improvement compared to the raw datasets, thus providing a possible answer to practical problems in the field of remote sensing and sensor sensitivity. Moreover, our methodologies answer some optimization-related open questions for the fractal interpolation step using \textit{Optuna} framework.

Detecting objects across varying scales is still a challenge in computer vision, particularly in agricultural applications like Rice Leaf Disease (RLD) detection, where objects exhibit significant scale variations (SV). Conventional object detection (OD) like Faster R-CNN, SSD, and YOLO methods often fail to effectively address SV, leading to reduced accuracy and missed detections. To tackle this, we propose SaRPFF (Self-Attention with Register-based Pyramid Feature Fusion), a novel module designed to enhance multi-scale object detection. SaRPFF integrates 2D-Multi-Head Self-Attention (MHSA) with Register tokens, improving feature interpretability by mitigating artifacts within MHSA. Additionally, it integrates efficient attention atrous convolutions into the pyramid feature fusion and introduce a deconvolutional layer for refined up-sampling. We evaluate SaRPFF on YOLOv7 using the MRLD and COCO datasets. Our approach demonstrates a +2.61% improvement in Average Precision (AP) on the MRLD dataset compared to the baseline FPN method in YOLOv7. Furthermore, SaRPFF outperforms other FPN variants, including BiFPN, NAS-FPN, and PANET, showcasing its versatility and potential to advance OD techniques. This study highlights SaRPFF effectiveness in addressing SV challenges and its adaptability across FPN-based OD models.

In the present-day context, small satellites and their constellations consisting of varying sizes (nano, micro, pico satellites) are being favored for remote sensing and in situ probing of the heliosphere and terrestrial magnetosphere-ionosphere system. We introduce a mission concept aimed at concurrently observing Earth's northern and southern auroral ovals while conducting in situ measurements of particles, fields, and temperature. The mission concept consists of two small satellites, each having an identical auroral X-ray imager, an in situ particle detector, a magnetometer pair, and an electron temperature analyzer onboard in an elliptical polar orbit (400X1000 km ). This mission would assist the space weather community in primarily answering important questions about the formation, morphology, and hemispherical asymmetries that we observe in the X-ray aurora, the fluxes of precipitating particles, Solar Energetic Particles, currents, and cusp dynamics. Once realized, this would be the first dedicated twin spacecraft mission of such kind to simultaneously study hemispheric asymmetries of solar-wind magnetosphere coupling. This study reveals the intricacies of the mission concept, encompassing orbital details, potential payloads, and its underlying scientific objectives. By leveraging the capabilities of small satellites, this mission concept is poised to make significant contributions to space weather monitoring and research.

Low-cost particulate matter sensors (LCS) are an important source of air quality data, improving the spatial and temporal resolution of data gathered by sparsely placed official monitoring stations. Their readings, however, are subject to bias due to unaccounted for effects pertaining to both the physical properties of the aerosol particles and design limitations of the devices. A calibration model is paramount in order to valorize the output of LCS devices. In this paper, a calibration model is developed for the LCS network of the municipality of Timisoara, Romania. A regression approach is used for calibrating PM10. Several models are tested, considering as independent variables the LCS PM10, relative humidity, and temperature. Models with physics-based corrections for relative humidity are found to work best. The calibrated data is tested against data from collocated stations from the National Air Quality Monitoring Network (NAQMN), showing an average performance of nRMSE=7.5{\mu}g/m3, R2=0.31. The calibration model is applied to the city-wide LCS network of the municipality. The yearly average PM10 of the network is shown to be similar to that of NAQMN, both being well within the EU yearly PM10 standard. For daily PM10 values, however, several stations are found that regularly exceed the daily threshold set by the European Union. These violations are not witnessed at the NAQMN stations. This is interpreted as due to the small number of reference stations located in the administrative boundaries of the city, which miss particular localized emission sources that are not collocated with these stations.

An in-depth comprehension of global land cover is essential in Earth observation, forming the foundation for a multitude of applications. Although remote sensing technology has advanced rapidly, leading to a proliferation of satellite imagery, the inherent complexity of these images often makes them difficult for non-expert users to understand. Natural language, as a carrier of human knowledge, can be a bridge between common users and complicated satellite imagery. In this context, we introduce a global-scale, high-quality image-text dataset for remote sensing, providing natural language descriptions for Sentinel-2 data to facilitate the understanding of satellite imagery for common users. Specifically, we utilize Sentinel-2 data for its global coverage as the foundational image source, employing semantic segmentation labels from the European Space Agency's (ESA) WorldCover project to enrich the descriptions of land covers. By conducting in-depth semantic analysis, we formulate detailed prompts to elicit rich descriptions from ChatGPT. To enhance the dataset's quality, we introduce the manual verification process. This step involves manual inspection and correction to refine the dataset, thus significantly improving its accuracy and quality. Finally, we offer the community ChatEarthNet, a large-scale image-text dataset characterized by global coverage, high quality, wide-ranging diversity, and detailed descriptions. ChatEarthNet consists of 163,488 image-text pairs with captions generated by ChatGPT-3.5 and an additional 10,000 image-text pairs with captions generated by ChatGPT-4V(ision). This dataset has significant potential for training vision-language geo-foundation models and evaluating large vision-language models for remote sensing. The dataset will be made publicly available.

Numerous countries have built urban stations for monitoring the amount of PM2.5 in the atmosphere. In Iraq, there aren't enough stations to monitor PM2.5 pollution levels across all governorates. As a result, satellite remote sensing data is used in the majority of studies aimed at monitoring PM2.5 and the impact of other factors on it. The current study aimed to analyze the spatial and temporal distribution of (PM2.5) and its relationship with the meteorological parameters.(Air temperature, Relative humidity, Precipitation and wind speed) in Iraq during two periods (2001 and 2022). The dataset adopted in the study were downloaded from the Giovanni user interface which is based on satellite remote sensing data and reanalysis by MERRA-2model which produce by NASA. The output results shows that, the seasonal and annual PM2.5 concentration values increased from 2001 to 2022 due especially in the center and south of Iraq with the highest values of PM2.5 concentration recorded in the summers of 2001 and 2022 being 172.41 micro.g/m3 and 190.06 micro.g/m3 (increased 10.24%), respectively. Because of the low average temperature and the influence of northeasterly winds bringing continental air from Central Asia, PM2.5 values in northern and northeastern Iraq are lower than those in the center and southern regions. in 2001, they ranged from 8.41 to 12.6 micro.g/m3, whereas in 2022, they ranged from 9.02 to 15.98 micro.g/m3 throughout the year. Rainfall during the cold months in the north and northeast is an essential factor in cleaning the air of PM2.5. Also, study results indicate that the max. of PM 2.5 values have consistently exceeded the upper limits of PM2.5 quarterly standards set by both the US and Iraqi regulations, for the years 2001 and 2022, but the min. PM2.5 values are within both standards.

A common phenomena confining the representation quality in Self-Supervised Learning (SSL) is dimensional collapse (also known as rank degeneration), where the learned representations are mapped to a low dimensional subspace of the representation space. The State-of-the-Art SSL methods have shown to suffer from dimensional collapse and fall behind maintaining full rank. Recent approaches to prevent this problem have proposed using contrastive losses, regularization techniques, or architectural tricks. We propose WERank, a new regularizer on the weight parameters of the network to prevent rank degeneration at different layers of the network. We provide empirical evidence and mathematical justification to demonstrate the effectiveness of the proposed regularization method in preventing dimensional collapse. We verify the impact of WERank on graph SSL where dimensional collapse is more pronounced due to the lack of proper data augmentation. We empirically demonstrate that WERank is effective in helping BYOL to achieve higher rank during SSL pre-training and consequently downstream accuracy during evaluation probing. Ablation studies and experimental analysis shed lights on the underlying factors behind the performance gains of the proposed approach.

One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore the compositionality of complex tasks, and present a novel skill-based imitation learning framework enabling one-shot imitation and zero-shot adaptation; from a single demonstration for a complex unseen task, a semantic skill sequence is inferred and then each skill in the sequence is converted into an action sequence optimized for environmental hidden dynamics that can vary over time. Specifically, we leverage a vision-language model to learn a semantic skill set from offline video datasets, where each skill is represented on the vision-language embedding space, and adapt meta-learning with dynamics inference to enable zero-shot skill adaptation. We evaluate our framework with various one-shot imitation scenarios for extended multi-stage Meta-world tasks, showing its superiority in learning complex tasks, generalizing to dynamics changes, and extending to different demonstration conditions and modalities, compared to other baselines.

This paper introduces an approach for building a Named Entity Recognition (NER) model built upon a Bidirectional Encoder Representations from Transformers (BERT) architecture, specifically utilizing the SlovakBERT model. This NER model extracts address parts from data acquired from speech-to-text transcriptions. Due to scarcity of real data, a synthetic dataset using GPT API was generated. The importance of mimicking spoken language variability in this artificial data is emphasized. The performance of our NER model, trained solely on synthetic data, is evaluated using small real test dataset.

This paper introduces SudokuSens, a generative framework for automated generation of training data in machine-learning-based Internet-of-Things (IoT) applications, such that the generated synthetic data mimic experimental configurations not encountered during actual sensor data collection. The framework improves the robustness of resulting deep learning models, and is intended for IoT applications where data collection is expensive. The work is motivated by the fact that IoT time-series data entangle the signatures of observed objects with the confounding intrinsic properties of the surrounding environment and the dynamic environmental disturbances experienced. To incorporate sufficient diversity into the IoT training data, one therefore needs to consider a combinatorial explosion of training cases that are multiplicative in the number of objects considered and the possible environmental conditions in which such objects may be encountered. Our framework substantially reduces these multiplicative training needs. To decouple object signatures from environmental conditions, we employ a Conditional Variational Autoencoder (CVAE) that allows us to reduce data collection needs from multiplicative to (nearly) linear, while synthetically generating (data for) the missing conditions. To obtain robustness with respect to dynamic disturbances, a session-aware temporal contrastive learning approach is taken. Integrating the aforementioned two approaches, SudokuSens significantly improves the robustness of deep learning for IoT applications. We explore the degree to which SudokuSens benefits downstream inference tasks in different data sets and discuss conditions under which the approach is particularly effective.

Satellite observations of the geomagnetic field contain signals generated in Earth's interior by electrical currents in the core and by magnetized rocks in the lithosphere. At short wavelengths the lithospheric signal dominates, obscuring the signal from the core. Here we present details of a method to co-estimate separate models for the core and lithospheric fields, which are allowed to overlap in spherical harmonic degree, that makes use of prior information to aid the separation. Using a maximum entropy method we estimate probabilistic models for the time-dependent core field and the static lithospheric field that satisfy constraints provided by satellite observations while being consistent with prior knowledge of the spatial covariance and expected magnitude of each field at its source surface.

Probabilistic seismic hazard and risk models are essential to improving our awareness of seismic risk, to its management, and to increasing our resilience against earthquake disasters. These models consist of a series of components, which may be tested and validated individually, however testing and validating these types of models as a whole is challenging due to the lack of recognised procedures. Estimations made with other models, as well as observations of ground shaking and damages in past earthquakes lend themselves to testing the components for ground motion modelling and for the severity of damage to buildings. Here, we are using observations of damages caused by the Le Teil 2019 earthquake, third-party estimations of macroseismic intensity for this seismic event, and ShakeMap analyses in order to make comparisons with estimations made with scenario simulations using model components developed in the context of the 2020 Euro-Mediterranean Seismic Hazard Model and the European Seismic Risk Model. The comparisons concern the estimated ground motion intensity measures, the macroseismic intensity, the number of damaged buildings, and the probabilities of the damage grade. The divergences of the estimations from the observations, which are observed in some of comparisons, are attributed to factors external to the models, such as the location of the hypocentre.

Wireless Sensor Networks (WSNs) play a pivotal role in enabling Internet of Things (IoT) devices with sensing and actuation capabilities. Operating in remote and resource-constrained environments, these IoT devices face challenges related to energy consumption, crucial for network longevity. Existing clustering protocols often suffer from high control overhead, inefficient cluster formation, and poor adaptability to dynamic network conditions, leading to suboptimal data transmission and reduced network lifetime. This paper introduces Low-Energy Adaptive Clustering Hierarchy with Reinforcement Learning-based Controller (LEACH-RLC), a novel clustering protocol designed to address these limitations by employing a Mixed Integer Linear Programming (MILP) approach for strategic selection of Cluster Heads (CHs) and node-to-cluster assignments. Additionally, it integrates a Reinforcement Learning (RL) agent to minimize control overhead by learning optimal timings for generating new clusters. LEACH-RLC aims to balance control overhead reduction without compromising overall network performance. Through extensive simulations, this paper investigates the frequency and opportune moments for generating new clustering solutions. Results demonstrate the superior performance of LEACH-RLC over state-of-the-art protocols, showcasing enhanced network lifetime, reduced average energy consumption, and minimized control overhead. The proposed protocol contributes to advancing the efficiency and adaptability of WSNs, addressing critical challenges in IoT deployments.

In the universe of Natural Language Processing, Transformer-based language models like BERT and (Chat)GPT have emerged as lexical superheroes with great power to solve open research problems. In this paper, we specifically focus on the temporal problem of semantic change, and evaluate their ability to solve two diachronic extensions of the Word-in-Context (WiC) task: TempoWiC and HistoWiC. In particular, we investigate the potential of a novel, off-the-shelf technology like ChatGPT (and GPT) 3.5 compared to BERT, which represents a family of models that currently stand as the state-of-the-art for modeling semantic change. Our experiments represent the first attempt to assess the use of (Chat)GPT for studying semantic change. Our results indicate that ChatGPT performs significantly worse than the foundational GPT version. Furthermore, our results demonstrate that (Chat)GPT achieves slightly lower performance than BERT in detecting long-term changes but performs significantly worse in detecting short-term changes.

Visible (VIS) imagery is important for monitoring Tropical Cyclones (TCs) but is unavailable at night. This study presents a Conditional Generative Adversarial Networks (CGAN) model to generate nighttime VIS imagery with significantly enhanced accuracy and spatial resolution. Our method offers three key improvements compared to existing models. First, we replaced the L1 loss in the pix2pix framework with the Structural Similarity Index Measure (SSIM) loss, which significantly reduced image blurriness. Second, we selected multispectral infrared (IR) bands as input based on a thorough examination of their spectral properties, providing essential physical information for accurate simulation. Third, we incorporated the direction parameters of the sun and the satellite, which addressed the dependence of VIS images on sunlight directions and enabled a much larger training set from continuous daytime data. The model was trained and validated using data from the Advanced Himawari Imager (AHI) in the daytime, achieving statistical results of SSIM = 0.923 and Root Mean Square Error (RMSE) = 0.0299, which significantly surpasses existing models. We also performed a cross-satellite nighttime model validation using the Day/Night Band (DNB) of the Visible/Infrared Imager Radiometer Suite (VIIRS), which yields outstanding results compared to existing models. Our model is operationally applied to generate accurate VIS imagery with arbitrary virtual sunlight directions, significantly contributing to the nighttime monitoring of various meteorological phenomena.