Search Results (136)

Accurate crop yield prediction is essential for stabilizing food supply chains and reducing the uncertainties in financial risks related to agricultural production. Yet, it is even more essential to understand how crop yield models make predictions depending on their relationship to Earth Observation (EO) indicators. This study presents a state-of-the-art explainable artificial intelligence (XAI) method to estimate corn yield prediction over the Corn Belt in the continental United States (CONUS). We utilize the recently introduced Kolmogorov–Arnold Network (KAN) architecture, which offers an interpretable alternative to the traditional Multi-Layer Perceptron (MLP) approach by utilizing learnable spline-based activation functions instead of fixed ones. By including a KAN in our crop yield prediction framework, we are able to achieve high prediction accuracy and identify the temporal drivers behind crop yield variability. We create a multi-source dataset that includes biophysical parameters along the crop phenology, as well as meteorological, topographic, and soil parameters to perform end-of-season and in-season predictions of county-level corn yields between 2016–2023. The performance of the KAN model is compared with the commonly used traditional machine learning (ML) models and its architecture-wise equivalent MLP. The KAN-based crop yield model outperforms the other models, achieving an R² of 0.85, an RMSE of 0.84 t/ha, and an MAE of 0.62 t/ha (compared to MLP: R² = 0.81, RMSE = 0.95 t/ha, and MAE = 0.71 t/ha). In addition to end-of-season predictions, the KAN model also proves effective for in-season yield forecasting. Notably, even three months prior to harvest, the KAN model demonstrates strong performance in in-season yield forecasting, achieving an R² of 0.82, an MAE of 0.74 t/ha, and an RMSE of 0.98 t/ha. These results indicate that the model maintains a high level of explanatory power relative to its final performance. Overall, these findings highlight the potential of the KAN model as a reliable tool for early yield estimation, offering valuable insights for agricultural planning and decision-making. Full article

To address the challenge of insufficient spatial resolution in remote sensing precipitation data, this paper proposes a novel Multi-Scale Residual Generative Adversarial Network (MSRGAN) for reconstructing high-resolution precipitation images. The model integrates multi-source meteorological information and topographic priors, and it employs a Deep Multi-Scale Perception Module (DeepInception), a Multi-Scale Feature Modulation Module (MSFM), and a Spatial-Channel Attention Network (SCAN) to achieve high-fidelity restoration of complex precipitation structures. Experiments conducted using Weather Research and Forecasting (WRF) simulation data over the continental United States demonstrate that MSRGAN outperforms traditional interpolation methods and state-of-the-art deep learning models across various metrics, including Critical Success Index (CSI), Heidke Skill Score (HSS), False Alarm Rate (FAR), and Jensen–Shannon divergence. Notably, it exhibits significant advantages in detecting heavy precipitation events. Ablation studies further validate the effectiveness of each module. The results indicate that MSRGAN not only improves the accuracy of precipitation downscaling but also preserves spatial structural consistency and physical plausibility, offering a novel technological approach for urban flood warning, weather forecasting, and regional hydrological modeling. Full article

This study contributes new mineralogical, whole-rock geochemical, and magnetic susceptibility data to the well-established petrogenesis of the Miocene of Limnos volcanic rocks in the Aegean region. The combined examination of volcanic samples from the Katalakon, Romanou, and Myrina units demonstrates that they belong to a genetically related high-K calc-alkaline to shoshonitic suite that was formed by fractional crystallization in a continental arc setting and derived from a subduction-modified mantle source, contaminated by continental sediments. Different magmatic processes and crystallization conditions are reflected in modest compositional differences in magnetite (Ti, Al substitution) and ilmenite (Mg, Al, Fe–Ti ratios), as well as variations in trace elements between the units (e.g., elevated Nb–Zr in Romanou, high LREE in Myrina, and Ba in Katalakon). According to the magnetic data, bulk magnetic susceptibility is largely determined by magnetite abundance, whereas magnetic domain states are influenced by the grain size and shape, as euhedral grains are associated with stronger responses. The coupled geochemical and magnetic results indicate the diversified and transitional character of the Agios Ioannis Subunit in the Katalakon Unit. Full article

This study introduces a novel framework with the use of extended reality (XR) systems in hydrology, particularly focusing on immersive visualization of hydrologic data for enhanced environmental planning and decision making. The study details the shift from traditional 2D data visualization methods in hydrology to more advanced XR technologies, including virtual and augmented reality. Unlike static 2D maps or charts that require cross-referencing disparate data sources, this system consolidates real-time, multivariate datasets, such as streamflow, precipitation, and terrain, into a single interactive, spatially contextualized 3D environment. Immersive information systems facilitate dynamic interaction with real-time hydrological and meteorological datasets for various stakeholders and use cases, and pave the way for metaverse and digital twin systems. This system, accessible via web browsers and XR devices, allows users to navigate a 3D representation of the continental United States. The paper addresses the current limitations in hydrological visualization, methodology, and system architecture while discussing the challenges, limitations, and future directions to extend its applicability to a wider range of environmental management and disaster response scenarios. Future application potential includes climate resilience planning, immersive disaster preparedness training, and public education, where stakeholders can explore scenario-based outcomes within a virtual space to support real-time or anticipatory decision making. Full article

Wildfires in the United States have increased in frequency and severity over recent decades, driven by climate change, altered weather patterns, and accumulated flammable materials. Accurately forecasting the Fire Weather Index (FWI) is crucial for mitigating wildfire risks and protecting ecosystems, human health, and infrastructure. This study analyzed FWI trends across the Continental United States (CONUS) from 2014 to 2023, using meteorological data from the gridMET dataset. Key variables, including temperature, relative humidity, wind speed, and precipitation, were utilized to calculate the FWI at a fine spatial resolution of 4 km, ensuring the precise identification of wildfire-prone areas. Based on this, our study developed a hybrid modeling framework to forecast FWI over a 14-day horizon, integrating Graph Neural Networks (GNNs) with Temporal Convolutional Neural Networks (TCNNs), Long Short-Term Memory (LSTM), and Deep Autoregressive Networks (DeepAR). The models were evaluated using the Index of Agreement (IOA) and root mean squared error (RMSE). The results revealed that the Southwest and West regions of CONUS consistently exhibited the highest mean FWI values, with the summer months demonstrating the greatest variability across all climatic zones. In terms of model performance on forecasting, Day 1 results highlighted the superior performance of the GNN-TCNN model, achieving an IOA of 0.95 and an RMSE of 1.21, compared to the GNN-LSTM (IOA: 0.93, RMSE: 1.25) and GNN-DeepAR (IOA: 0.92, RMSE: 1.30). On average, across all 14 days, the GNN-TCNN outperformed others with a mean IOA of 0.885 and an RMSE of 1.325, followed by the GNN-LSTM (IOA: 0.852, RMSE: 1.590) and GNN-DeepAR (IOA: 0.8225, RMSE: 1.755). The GNN-TCNN demonstrated robust accuracy across short-term (days 1–7) and long-term (days 8–14) forecasts. This study advances wildfire risk assessment by combining descriptive analysis with hybrid modeling, offering a scalable and robust framework for FWI forecasting and proactive wildfire management amidst a changing climate. Full article

Bottomland hardwood wetland forests along the Atlantic Coast of the United States have been changing over time; this change has been exceptionally apparent in the last two decades. Tree mortality is one of the most visually striking changes occurring in these coastal forests today. Using 2009–2019 tree mortality data from a bottomland hardwood forest monitored for long-term flux studies in North Carolina, we evaluated species composition and tree mortality trends and partitioned variance among hydrologic (e.g., sea level rise (SLR), groundwater table depth), biological (leaf area index (LAI)), and climatic (solar radiation and air temperature) variables affecting tree mortality. Results showed that the tree mortality rate rose from 1.64% in 2009 to 45.82% over 10 years. Tree mortality was primarily explained by a structural equation model (SEM) with R² estimates indicating the importance of hydrologic (R² = 0.65), biological (R² = 0.37), and climatic (R² = 0.10) variables. Prolonged inundation, SLR, and other stressors drove the early stages of ‘ghost forest’ formation in a formerly healthy forested wetland relatively far inland from the nearest coastline. This study contributes to a growing understanding of widespread coastal ecosystem transition as the continental margin adjusts to rising sea levels, which needs to be accounted for in ecosystem modeling frameworks. Full article

Existing validation of mean wind speed estimates via reflectometry from global navigation systems of satellites (GNSS-R)—has been largely limited in spatial coverage to equatorial buoys or tropical cyclone events near continental United States. Two alternative validation techniques are presented for the Cyclone GNSS (CYGNSS) mission using surface-based observations along coasts and coral reefs instead of buoys, and triple collocation analysis (TCA) instead of a 1:1 gridded comparison for tropical cyclone (TC) events. For the surface-based analysis, Fully Developed Seas (FDS) v3.2 and NOAA v1.2 were compared to anemometer data provided by the Australian Bureau of Meteorology across the Australia and Pacific regions. Overall, the products performed similarly to previous studies with NOAA having higher correlations and lower errors than FDS, though FDS performed better than NOAA over the Australian dataset for high wind speed events. TCA was used to validate NOAA v1.2 and Merged v3.2 datasets with other satellite remotely sensed products from the Soil Moisture Active Passive (SMAP) mission and Synthetic Aperture Radar (SAR). Both additive and multiplicative error models for TCA were applied. The performance overall was similar between the two products, with NOAA producing higher errors. NOAA performed better than Merged for mean winds above 17 m/s as the large temporal averaging reduced sensitivity to high winds. For SMAP winds above 17 m/s, NOAA’s average bias (−2.1 m/s) was significantly smaller than the average bias in Merged (−4.4 m/s). Future ideas for rapid intensification detection and constellation design are discussed. Full article

Performance plays a critical role in the practical use of global streamflow reanalysis. This paper presents the combined use of random forest and the Shapley additive explanation to examine the mechanism by which catchment attributes influence the accuracy of streamflow estimates in reanalysis products. In particular, the reanalysis generated by the Global Flood Awareness System streamflow is validated by streamflow observations provided by the Catchment Attributes and MEteorology for Large-sample Studies dataset. Results highlight that with regard to the Kling–Gupta efficiency, the reanalysis surpasses mean flow benchmarks in 93% of catchments across the continental United States. In addition, twelve catchment attributes are identified as major controlling factors with spatial patterns categorized into five clusters. Topographic characteristics and climatic indices are also observed to exhibit pronounced influences. Streamflow reanalysis performs better in catchments with low precipitation seasonality and steep slopes or in wet catchments with a low frequency of precipitation events. The partial dependence plot slopes of most key attributes are consistent across the four seasons but the slopes’ magnitudes vary. Seasonal snow exhibits positive effects during snow melting from March to August and negative effects associated with snowpack accumulation from September to February. Catchments with very low precipitation seasonality (values less than −1) show strong seasonal variation in streamflow estimations, with negative effects from June to November and positive effects from December to May. Overall, this paper provides useful information for applications of global streamflow reanalysis and lays the groundwork for further research into understanding the seasonal effects of catchment attributes. Full article

Antibiotic resistance is a silent global crisis intensified by the recent pandemic of coronavirus disease 2019 (COVID-19). To address this growing threat, wastewater-based surveillance (WBS) is emerging as a promising public health tool for monitoring antibiotic resistance within communities. Our meta-analysis aims to reveal the landscape of antibiotic-resistance genes (ARGs) in global wastewater during and after the COVID-19 pandemic. The analysis included wastewater samples collected between 2020 and 2024 from five countries across three continents: Asia (China), Europe (United Kingdom and Russia), and North America (United States and Canada). Our findings showed higher observed ARGs in Russia and China despite their small sample size, while the USA showed more diverse ARGs. Distinct patterns of ARGs were observed in European and North American wastewater samples (p-value < 0.001). We identified 2483 ARGs, with multidrug-resistant (MDR) genes dominating most regions and accounting for almost 45% of all ARGs detected in Europe. Country-specific indicator ARGs showed 22 unique ARGs for Russia, 3 for each of the UK and Canada, and 2 were specific for China. Continentally, 100 indicator ARGs were specific to Asia, 38 to Europe, and 18 to North America. These findings highlight the regional variations in ARG profiles, emphasizing the urgent need for region-specific strategies to combat antibiotic-resistance threat. Additionally, our study further supports the value of WBS as a valuable public health tool for monitoring antibiotic resistance. Full article

The continental United States is a global hotspot of severe thunderstorms and therefore is particularly vulnerable to social and economic damages from high-impact severe convective weather (SCW), such as tornadoes, thunderstorm winds, and large hail. However, our knowledge of the spatiotemporal climatology and variability of SCW occurrence is still lacking, and the potential change in SCW frequency and intensity in response to anthropogenic climate warming is highly uncertain due to deficient and sparse historical records and the global and regional climate model’s inability to resolve thunderstorms. This study investigates SCW in the Central and Eastern United States in spring and early summer for the current and future warmed climate using two multi-year continental-scale convection-permitting Weather Research and Forecasting (WRF) model simulations. The pair of simulations consist of a retrospective simulation, which downscales the ERA-Interim reanalysis during October 2000–September 2013, and a future climate sensitivity simulation based on the perturbed reanalysis-derived boundary conditions with the CMIP5 ensemble-mean high-end emission scenario climate change. A proxy based on composite reflectivity and updraft helicity threshold is applied to infer the simulated SCW occurrence. Results indicate that the retrospective simulation captures reasonably well the spatial distributions and seasonal variations of the observed SCW events, with an exception of an overestimate along the Atlantic and Gulf coast. In a warmer-moister future, most regions experience intensified SCW activity, most notably in the early-middle spring, with the largest percentage increase in the foothills and higher latitudes. In addition, a shift of simulated radar reflectivity toward higher values, in association with the significant thermodynamic environmental response to climatic warming, potentially increases the SCW severity and resultant damage. Full article

Recurring polarimetric radar signatures in supercells include deep and persistent differential reflectivity (Z_DR) columns, hail inferred in low-level scans, and the Z_DR arc signature. Prior investigations of supercell polarimetric signatures reveal positive correlations between the Z_DR column depth and cross-sectional area and quantitative characteristics of the radar reflectivity field. This study expands upon prior work by examining temporal associations between supercell polarimetric radar signatures, incorporating a dataset of relatively discrete, right-moving supercells from the continental United States observed by the Weather Surveillance Radar 1988-Doppler (WSR-88D) network. Cross-correlation coefficients were calculated between the Z_DR column area and depth and the base-scan hail area, Z_DR arc area, and mean Z_DR arc value. These correlation values were computed with a positive and negative lag time of up to 45 min. Results of the lag correlation analysis are consistent with prior observations indicative of storm cycling, including temporal associations between Z_DR columns and inferred hail signatures/Z_DR arcs in both tornadic and nontornadic supercells, but were most pronounced in tornadic storms. Full article

State-owned agricultural land is an asset that the state must manage in a responsible and transparent manner. Agricultural land is extremely important for farmers as it enables them to carry out agricultural activities. Due to its importance to farmers, it is often the subject of debate as stakeholders are often dissatisfied with the allocation and management of state-owned agricultural land. Qualitative research of the process of state agricultural land lease and the associated legislation in the Republic of Croatia enabled the analysis of the existing business model, with the results pointing to shortcomings in the Initial and Evaluation phases of the process. A steady rise in the number of tenders published in 2015–2022 was recorded. Local administrative units in the Continental region scored higher than those in the Adriatic region (both cities and municipalities) in terms of transparency. Unfortunately, the response rate from the local authorities was below 50% across both region and unit, further indicating low transparency. Based on the findings, a proposal of changes in the tendering process was made utilizing a digital platform as an environment for all stakeholders, which provides functionalities essential for the transparent implementation of tenders for the agricultural land lease in Croatia. Full article

The model error is a direct reflection of the accuracy of the model simulation. However, it is challenging to estimate the model error due to the presence of numerous uncertainties inherent to the atmospheric and soil data, as well as the structure and parameters of the model itself. This paper addresses the fundamental issue of error estimation in the simulation of soil moisture by the Variable Infiltration Capacity (VIC) model, with a particular focus on the continental United States from 2010 to 2020. The paper develops a model error estimation method based on the Triple Collocation (TC) error estimation and in situ data validation of the VIC model at different temporal and spatial scales. Furthermore, it addresses the issue of failing to consider the variability of temporal and spatial scales in model error estimations. Furthermore, it generates the standard product data on soil moisture simulation errors for the VIC model in the continental United States. The mean of the simulation error variance of the VIC model, estimated using the TC method for spatially scaled soil moisture in the continental United States, is found to be 0.0045 (m³/m³)², with a median value of 0.0042 (m³/m³)². The mean time-scale error variance of the VIC model, validated using ground station data, is 0.0096 (m³/m³)², with a median value of 0.0078 (m³/m³)². Concurrently, the paper employs Köppen climate classification and land cover data as supplementary data, conducting a comprehensive investigation and analysis of the characteristics and alterations of the VIC model error in the study area from both temporal and spatial perspectives. The findings indicate a proclivity for reduced error rates during the summer months and elevated rates during the winter, with lower rates observed in the western region and higher rates in the eastern region. The objective of this study is twofold: firstly, to conduct a quantitative assessment and analysis of the VIC model’s simulation capabilities; secondly, to validate the accuracy and quality of the soil moisture products simulated by the model. The accurate estimation of model errors is a fundamental prerequisite for the numerical simulation and data assimilation of models, which has a vast range of applications in numerical meteorological and hydrological forecasting, natural environment monitoring, and other fields. Full article

To facilitate a direct comparison of the differences in network resources among countries worldwide, this paper proposes a method for quantifying the relationship between autonomous systems and territorial networks from the perspective of network topology. Using global router-level network topology data as the foundational data for the network resources of various countries, we abstract the dual mapping information of router geographic distribution and operational ownership into a matrix-form mathematical model. By employing relevant indicators from both network scale and border connectivity, we compare matrix model data from different periods to quantitatively assess changes in the network structures of countries globally. The study results show that internet resources are concentrated in the United States, which owns 38.04% of the global routers, distributed across 87.88% of the countries, significantly impacting the global network. Compared to the average quantitative indicators of each country, 67.00% of the countries exhibit higher deployment consistency, 37.30% show higher border connection consistency, 23.81% perform prominently in terms of impact, and 46.20% have outstanding border node degrees. From a continental perspective, the analysis indicates that Asian and African countries have a closer relationship between AS and territorial networks, while Europe’s connections are relatively sparse. Over time, we observe a slight decline in deployment consistency in Asia, Africa, and Europe, a slight increase in border connection consistency in Asia, Africa, and North America, and enhanced impact in Asia, Africa, Europe, and South America. These trends suggest that the integration between AS and territorial networks is intensifying in most countries. Full article

Background: Mental health in Puerto Rico is a complex and multifaceted issue that has been shaped by the island’s unique history, culture, and political status. Recent challenges, including disasters, economic hardships, and political turmoil, have significantly affected the mental well-being of the population, coupled with the limitations in the accessibility of mental health services. Thus, Puerto Rico has fewer mental health professionals per capita than any other state or territory in the United States. Objective: This comprehensive review examines the impact of disasters on mental health and mental health services in Puerto Rico. Given the exodus of Puerto Ricans from the island, this review also provides an overview of mental health resources available on the island, as well as in the continental United States. This review identifies efforts to address mental health issues, with the intent of gaining a proper understanding of the available mental health services, key trends, as well as observable challenges and achievements within the mental health landscape of the Puerto Rican population. Design: A comprehensive search using the PRIMO database of the University of Central Florida (UCF) library database was conducted, focusing on key terms related to disasters and mental healthcare and services in Puerto Rico. The inclusion criteria encompassed studies on Puerto Rican individuals, both those who remained on the island and those who migrated post-disaster, addressing the mental health outcomes and services for adults and children. We included peer-reviewed articles published from 2005 onwards in English and/or Spanish, examining the impact of disasters on mental health, accessibility of services, and/or trauma-related consequences. Results: In this scoping review, we identified 39 studies addressing the mental health profile of Puerto Ricans, identifying significant gaps in service availability and accessibility and the impact of environmental disasters on mental health. The findings indicate a severe shortage of mental health services in Puerto Rico, exacerbated by disasters such as Hurricanes Irma and Maria, the earthquakes of late 2019 and early 2020 that followed, and the COVID-19 pandemic, resulting in substantial delays in accessing care, and limited insurance coverage, particularly in rural regions. Despite these challenges, efforts to improve mental health services have included substantial federal funding and community initiative aimed at enhancing care availability and infrastructure. Limitations include the use of a single database, language restrictions, and potential variability in data extraction and synthesis. Conclusions: This scoping review highlights the significant impact of disasters on mental health in Puerto Rico and the challenges in accessing mental health services exacerbated by disasters. Despite efforts, significant gaps in mental healthcare and services persist, emphasizing the need for more rigorous research and improvements in infrastructure and workforce to enhance mental health outcomes for Puerto Ricans both on the island and in the continental United States. Full article