ABSTRACT The Hindu Kush Himalaya (HKH), known as the “Water Tower of Asia”, faces mounting challenges from climate change, accelerated glacial retreat, intensified land-use changes, and transboundary water management complexities, leading to significant hydrological transformations that threaten regional water sustainability. To address the urgent need for precise water monitoring, we produced the comprehensive 10-meter resolution surface water dataset (HKH-SWD10m) for the HKH region spanning from 2016 to 2022. The dataset is produced by developing a Vision Transformer-based deep learning network optimized for rapid, automated water extraction. The resulting network achieved exceptional performance metrics on our test dataset, with an Overall Accuracy (OA) of 0.9981, an Intersection over Union (IoU) of 0.9734, and a Kappa of 0.9855. Extensive validation using 15,000 stratified random sampling points demonstrated high accuracy with an OA of 0.9787, a Producer’s Accuracy (PA) of 0.9638, a User’s Accuracy (UA) of 0.9856, and a Kappa of 0.9476. Comparative analysis with the 30-meter resolution Global Surface Water (GSW) dataset revealed that HKH-SWD10m is generally consistent with the GSW product but captures more small water bodies while providing superior boundary delineation precision. Based on the HKH-SWD10m dataset, we analyzed changes of surface water in the HKH over the years 2016–2022. Our interannual analysis (2016–2022) not only corroborates previous hydrological findings but reveals novel sub-regional divergence in surface water trends when analyzed through national and basin-level frameworks, suggesting localized climate impacts. This dataset advances hydrological monitoring capabilities by offering unprecedented spatial-temporal resolution for the HKH, serving as a critical resource for water security assessments, ecosystem management, and climate adaptation strategies. The HKH-SWD10m dataset is publicly available through Zenodo (https://doi.org/10.5281/zenodo.15067176) and National Earth System Science Data Center of China (https://doi.org/10.12041/geodata.551748804486886.ver1.db).

ABSTRACT Climate hazards can escalate into humanitarian disasters. Understanding their trajectories—considering hazard intensity, human exposure, and societal vulnerability—is essential for effective anticipatory action. The International Disaster Database (EM-DAT) is the only freely available global resource of humanitarian disaster records. However, it has imprecise geocoded information, which severely constrains its integration with spatial climate and socioeconomic data, limiting its use for climate impact research and policy planning. Here, we present Geo-Disasters (https://doi.org/10.5281/zenodo.15487667), a database that provides geocoded locations of 9,217 climate-related disasters reported by EM-DAT from 1990 to 2023, along with an open, reproducible framework for updating (https://doi.org/10.6084/m9.figshare.29125907.v1). Our method remains accurate even when only region names are available and includes matching quality flags to assess reliability. The augmented EM-DAT enables integration with other geocoded data, supporting machine learning applications and cross-domain analyses of climate risks, vulnerabilities, and adaptation deficits. By making more extreme events available, Geo-Disasters aims to bridge critical data gaps in global climate-hazard risk assessment and to inform more equitable adaptation planning.

ABSTRACT The Southwest China Vortex (SWCV) is a powerful mesoscale synoptic system that can lead to severe hazards to the east of the Tibetan Plateau. However, SWCV data have increasingly become a problem, impeding studies on SWCV evolution. In this study, we established a new SWCV event (SWCVE) dataset using a well-trained CNN model, a nearest-neighbor search method, and hourly ERA5 reanalysis data. The new dataset, containing genesis locations, moving paths, and lysis locations of 9,379 SWCVEs from 1940 to 2023, was validated by independent-sample test, case study, and cross-check analysis of the SWCVE genesis frequency. The results show that the new SWCVE dataset is characterized by efficiency, reliability, and robustness. Additionally, it can be updated following ERA5 reanalysis data in real time. Therefore, the new SWCVE dataset lays the foundation for a better understanding of SWCV evolution on time scales no less than one hour. The new SWCVE dataset is openly available at https://doi.org/10.5281/zenodo.15073815 or https://www.scidb.cn/doi/10.5281/zenodo.15073815.

ABSTRACT Harmful algal blooms (HABs) pose serious threats to aquatic environments, ecosystems, and local economies. In response, recent research has explored the deployment of autonomous boats to monitor, measure, and mitigate these blooms. This study presents a novel approach utilizing Watabot-Pro, an autonomous boat specifically designed for the management of HABs. Despite technological advancements in such systems, uncertainties remain regarding their operational efficiency and effectiveness—particularly in comparison to conventional mitigation strategies and under varying environmental conditions and parameter settings. Leveraging remote sensing imagery and algal concentration data provided by the Environmental Protection Agency (EPA), we develop a computational framework to simulate and assess the potential of autonomous boats in managing HABs. Our simulations model the removal of cyanobacteria (commonly known as blue-green algae) using both traditional and autonomous methods across multiple scenarios informed by real-world environmental variables. This work offers valuable insights for environmental scientists, researchers, and policymakers by introducing emerging technologies for ecological intervention and evaluating their associated uncertainties.

ABSTRACT Geo-referenced social media data supports disaster management by offering real-time insights through user-generated content. To identify critical information amid high volumes of noise, classifying the relevance of posts is essential. Most existing methods primarily use textual features, neglecting spatial and temporal context despite its importance in determining relevance. This study proposes a multimodal approach that integrates text with spatiotemporal features for relevance classification of geo-referenced social media posts. We evaluate our method on 4,574 manually labelled posts from five disasters: the 2020 California wildfires, 2021 Ahr Valley floods, 2023 Chile wildfires, 2023 Turkey earthquake and 2023 Emilia-Romagna floods. Labels were assigned based on text, geographic location and time. Our spatiotemporal features include proximity to disaster impact sites, local co-occurrences with disaster-related posts, event type and geographic context. When utilised on their own, they achieved a macro F1 score of 0.713 with a random forest classifier. A fine-tuned TwHIN-BERT-base model using only text scored 0.779. For multimodal classification, we tested feature concatenation, in-context learning, stacking and partial stacking. Partial stacking produced the highest macro F1 score (0.814). Our multilingual, context-aware classification approach lays the groundwork for more integrated GeoAI applications in disaster management, the social sciences and beyond.

ABSTRACT Under strong wind conditions, floatable plastics (i.e., plastic mulching films, plastic greenhouses, plastic dust-proof nets, etc.) are prone to be blown up to hang on the power transmission lines of high-speed railways, leading to the misfunction or even train service suspension. Therefore, timely and accurate mapping of these floatable plastics is of great significance to both railway administrations and the safety of passengers onboard. However, the potential of remote sensing has not been well justified in this study field. To tackle this issue, we take Beijing-Shanghai high-speed railway as an example, which is the busiest railway in China, and propose a novel deep learning based semantic segmentation model to map floatable plastics from very high-resolution optical satellite imagery. Specifically, a well-annotated sample dataset of floatable plastics is prepared, consisting of three typical categories of plastic mulching films, plastic greenhouses and plastic dust-proof nets. Afterwards, a hybrid Convolutional Neural Network-Mamba (CNN-Mamba) network is proposed, which integrates multi-scale convolutions with various local receptive fields and Mamba with global receptive fields into an end-to-end model. Specifically, the Multi-Perspective Fusion Block leverages multi-kernel convolutions to capture multi-scale local features, while the Feature Refinement Module integrates encoder-decoder multi-level features, thereby improving semantic consistency and boundary precision. Experimental results showed that the proposed model has achieved a high performance in floatable plastics mapping with an mIoU of 0.8641 and an average F1-score of 0.9261. Ablation studies have been done to justify the rationality of each module in the proposed hybrid model. Besides, the proposed model also outperformed several CNN-based and Mamba-based networks, not only in floatable plastics mapping but also in two other popular land use land cover datasets. Overall, this study provides an effective pipeline for monitoring the floatable plastics along high-speed railways.

ABSTRACT Remotely sensed air temperature data from NASA POWER are widely used in regions with scarce climatic observations, particularly for agricultural applications such as calculating crop water requirements. This study employed a suite of machine learning (ML) algorithms to correct biases in NASA POWER air temperature outputs, including multiple support vector regression (SVR) variants—Linear SVR, Quadratic SVR, Cubic SVR, Fine Gaussian SVR, Medium Gaussian SVR, Coarse Gaussian SVR—and ensemble decision tree models: bagged trees (BGT) and boosted trees (BT). The objective of this study was to assess the ability of different ML algorithms to reduce biases in NASA POWER air temperature data, with the broader goal of identifying the most suitable ML method for air temperature bias correction in Nigeria. For this analysis, we used daily air temperature records from seven meteorological stations across diverse regions of Nigeria. The performance of NASA POWER minimum and maximum air temperature datasets was evaluated using standard error metrics. Subsequent application of ML algorithms significantly improved data accuracy: the normalized root mean square error (NRMSE) of the corrected outputs was mostly below 10%, indicating excellent predictive performance when ML was integrated. Among the SVR variants tested, Fine Gaussian SVR consistently yielded the best prediction results. This finding suggests that Fine Gaussian SVR is a robust tool for enhancing the reliability of air temperature data—critical for improving the accuracy of crop water requirement calculations in regions where in-situ air temperature observations are limited.

ABSTRACT Accurately predicting ocean eddy lifetimes is challenging due to their nonlinear energy dynamics and complex environmental interactions. This study utilizes a global ocean eddy trajectory dataset to analyse spatio-temporal dynamics, from energy accumulation to dissipation, identifying key lifetime factors: self energy, spatial distribution, and seasonal variability. We propose the first deep learning framework (ELPNet) designed to model the complete lifetimes of mesoscale eddies. It employs an adaptive time-series dimensionality reduction technique to present the dynamic evolution of eddies in a real-time and normalized manner. Furthermore, it integrates Long Short-Term Memory (LSTM) networks and Transformer models within a U-shaped encoder-decoder architecture to capture multi-scale spatio-temporal patterns, thereby enhancing the representation capability of eddies’ complete lifecycles. To address limitations of conventional metrics for nonlinear dissipation, we introduce the Eddy Lifetime Prediction Accuracy (ELPA) metric. With ELPA at a 30% tolerance, ELPNet achieves 71.2% prediction accuracy, doubling the performance of traditional methods. Error analysis highlights seafloor topography, energy dissipation rates, and eddy survival stages as primary accuracy constraints. This scalable approach extends to forecasting other oceanic phenomena like ocean fronts and internal waves, thereby enhancing intelligent ocean science forecasting systems.