Search Results (609)

Accurate prediction of extreme rainfall events during the Indian Summer Monsoon (ISM, June to September) is critical for disaster preparedness and mitigation. This study evaluates the performance of two operational numerical weather prediction models, a high-resolution version of Global Forecast System (GFS T1534) and the control member of the Met Office Global and Regional Ensemble Prediction System-Global (MOGREPS-G), in forecasting such events during the ISM from 2020 to 2023. The results demonstrate that, with respect to observations, both models tend to underestimate the mean and variability of rainfall; GFS-T1534 represents the mean and correlation better while MOGREPS-G represents the variability better over the Indian landmass. To assess the models’ performance for extreme rainfall prediction, we fix a rainfall threshold of 50 mm day⁻¹, and the skill scores are computed including Probability of Detection, False Alarm Rate, Bias score and F1 score. Together, these scores indicate that both models show potential in short-range forecasting of extreme rainfall events, particularly within 24 h, but their skills remain limited at longer lead times. Specifically, the model biases vary over different geographical locations, often showing contrasting features. This underscores the need for model-specific post-processing and calibration techniques if these forecasts are to be used effectively for operational decision-making. Full article

Hydrologic assessment within the Southeast United States is challenging, particularly in upstream basins, necessitating improved approaches to drought forecasting and water management. Within the Tennessee Valley, dense populations intensify the need for robust hydrologic management and predictive capabilities. This study integrates dendrochronological proxy data, hindcast information, and future climate projections from the Oak Ridge National Laboratory (ORNL) to evaluate May–June–July drought regimes. Holistic hydrologic conditions were attained by integrating self-calibrating Palmer Drought Severity Index data from the North American Drought Atlas, basin-scale precipitation data from ORNL hindcasts and future predictions, and streamflow data from United States Geological Survey. Development of precipitation and streamflow reconstructions were completed using Stepwise Linear Regression, then bias-corrected and temporally smoothed using five- and ten-year moving windows. The reconstructions demonstrated strong statistical skill across all three basins (Little Tennessee River, Nantahala River, South Fork Holston River). When compared only to the hindcast, future drought is predicted to be the most severe on record, but within the context of the paleo record, while still severe, these future droughts remain inside the natural variability envelope. Findings highlight the importance of novel approaches to long-term drought monitoring, specifically integrating basins where instrumental periods are limited, and water management demands are high. Full article

Egypt generally experiences a hot and arid climate, with rainfall primarily confined to the northern coast during winter season. However, on 31 May 2025, Alexandria experienced an unusual late-spring convective storm that was associated with heavy rainfall, strong winds, intense lightning, and localized hail. This rare event caused temporary disruptions to urban life and underscored the growing vulnerability of coastal cities to short-duration, high-intensity precipitation events occurring outside the climatological rainy season. This study investigates the atmospheric mechanisms underlying this event through a comprehensive synoptic and dynamic analysis of pressure systems, wind fields, and temperature structures extending from the surface to the 200 hPa level. Particular emphasis is placed on the role of moisture convergence and upper-level dynamical forcing in triggering the rapid development of deep convection. Furthermore, the influence of anomalous large-scale circulation patterns on storm initiation and intensification is systematically examined. Improved understanding of these processes provides valuable insight into off-season convective activity over the southeastern Mediterranean and enhances forecasting capability, risk assessment, and early warning strategies for similar extreme events in the region. Furthermore, the influence of anomalous large-scale circulation patterns on storm initiation and intensification is quantitatively assessed to clarify their contribution to the event’s development. A deeper understanding of these processes offers critical insight into the mechanisms governing off-season convective activity over the southeastern Mediterranean and strengthens forecasting skill, risk assessment frameworks, and early warning systems for comparable extreme events in the region. Full article

Accurate runoff forecasting is essential for effective water resource management, hydropower operation, and flood risk mitigation. In this study, daily inflow runoff in the Xin’an River Basin, eastern China, was simulated using four ensemble learning models: Gradient Boosting Decision Tree (GBDT), XGBoost, CatBoost, and Stacking. Among them, the CatBoost model achieved the best performance, with a correlation coefficient (CC) exceeding 0.97, Nash–Sutcliffe efficiency (NSE) above 0.95, and reduced RMSE and MAE compared with the currently operational hydrological model. To extend the forecast lead times, two hydro–meteorological coupled models were developed by integrating the CatBoost model with a single numerical weather prediction model (EC) and a dynamically weighted multi-model ensemble precipitation forecast system (OCF). The coupled models were evaluated for lead times up to 240 h. The forecast skill value was highest within 96 h, with CC values above 0.80 and NSE around 0.50. The OCF-coupled model demonstrated improved reliability for lead times of 48–96 h, whereas the EC-driven forecasts performed better within the first 48 h. Case studies during the 2021–2022 flood seasons confirmed that the coupled framework accurately reproduced flood evolution and peak discharge dynamics, demonstrating its practical value for medium-range runoff forecasting in humid river basins. Full article

In 2024, an abrupt drought-to-flood transition (ADFT) event occurred in Henan Province, China, causing severe losses to agriculture and the economy. Predicting the spatiotemporal evolution of such compound extremes remains challenging at the subseasonal scale. This study employs soil moisture percentiles to identify local droughts and floods, connects them into coherent patches, and detects an ADFT event spatiotemporally. The proposed three-dimensional identification method is further applied to evaluate the ECMWF S2S reforecasts of the 2024 ADFT event. At a 1-week lead, the ECMWF ensemble mean successfully captures the transition. However, the spatial extent is underpredicted substantially at a 2-week lead. In terms of probabilistic forecast, the Brier skill scores for drought, transition, and flood stages are 0.38, 0.57, and 0.38 at a 1-week lead, respectively. However, these scores drop sharply at a 2-week lead, particularly for the transition and flood stages. The decreased forecast skill is jointly influenced by internal dynamical errors in the model and biases in the positions of the subtropical high- and low-pressure systems at long lead. This study assesses the capability of a numerical model to predict a compound extreme from both deterministic and probabilistic perspectives, and highlights the critical role of atmospheric circulation in achieving skillful prediction. Full article

Short-term river water-level forecasting is essential for operational hydrology, supporting flood warning and water management. Although deep learning models such as Long Short-Term Memory (LSTM) networks have gained attention, classical statistical approaches including Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) remain attractive due to their interpretability and efficiency. This study presents a controlled comparison between ARIMA/SARIMA and stacked LSTM models for 7-day-ahead water-depth forecasting using synthetic daily hydrographs representing normal, drought, and flood regimes. Model performance is assessed using a rolling-origin forecasting strategy that generates multiple overlapping predictions, reducing bias from short validation windows. Forecast skill is evaluated through standard error metrics and hydrology-oriented indicators, including the Global Forecast Skill Index (GFSI). Results show comparable median performance between SARIMA and LSTM across regimes, with no statistically significant differences detected by nonparametric tests. Apparent differences in flood conditions should be interpreted cautiously due to limited sample representation. Overall, increased model complexity does not inherently guarantee superior predictive skill in this univariate short-term setting, highlighting the importance of rigorous evaluation design in comparative forecasting studies. Full article

Ku-band scatterometers lose extensive Sea Surface Vector Wind (SSVW) observations under extreme winds, heavy precipitation, or instrument anomalies, degrading forecast and assimilation skill. Traditional interpolation fails to reconstruct non-linear wind structures, whereas existing deep learning inpainting is hampered by scarce public datasets, high computational cost and insufficient continuity modeling. We propose WMamba, an Attention-Structured State Space Duality (ASSD)-based framework that exploits wind continuity to encode global dependencies with O(N) complexity for accurate SSVW inpainting. A Grouped Multiscale Attention Block (GMAB) ensures accurate fine-scale wind detail reconstruction by mitigating local pixel degradation. We also introduce L-WMamba, a lightweight 0.36 M-parameter variant suitable for resource-limited devices. Moreover, we release the SSVW Inpainting Dataset (WID), comprising 123,841 high-wind HY-2B HSCAT samples (2018–2022), as an open benchmark. Experiments demonstrate that WMamba outperforms GRL (state-of-the-art) decreasing the RMSE for wind speed and direction by 11.4% and 6.3%, respectively, while achieving a 94.7% reduction in parameters. In particular, WMamba effectively inpaints wind details, as evidenced by the highest MS-SSIM and RAPSD scores. This framework and dataset establish a robust baseline for extreme-weather SSVW recovery. Full article

The diurnal sea surface temperature variation (DSV) influences atmospheric convection and precipitation through air–sea interactions in the equatorial Pacific. Deep learning-based DSV forecasting has been less explored compared to traditional methods, presenting the potential for a substantial leap in forecast accuracy. In this study, a forecast model is developed for 24 h DSV in the equatorial Pacific using an improved coupled Transformer-CNN (CoTCN-DSV) by incorporating a new loss function including maximal and minimal values. The CoTCN-DSV forecasts diurnal variation in SST at the interval of 3 h based on 3 h SST from the WHOI dataset. The CoTCN-DSV captures DSV well with root mean square error (RMSE) of DSA below 0.03 °C/0.13 °C at 3 h/12 h lead times and maintains high forecast skill with the temporal correlation coefficient (R) of 0.78 at the lead times of 12 h in the equatorial Pacific. The CoTCN-DSV reduces RMSE for daily max/min SST by 10.9% and 12.8% due to replacing the new loss function, then significantly improving DSV forecast. There are systematic SST biases in the WHOI dataset and this leads to relatively large RMSEs when DSV forecasts trained using WHOI are evaluated against TAO observations. Replaced WHOI SST by TAO SST, the forecasted DSA RMSE by CoTCN-DSV is reduced by an average of 43%. This confirms that the CoTCN-DSV has good generalization ability and high-quality data are important to advance the forecast accuracy. These finding show that CoTCN-DSV has the potential to forecast extreme values for different scenarios. Full article

Agent-based models of financial markets often rely on a small set of hand-crafted trading rules, making it difficult to relate model heterogeneity to information that is observable in market data. We take a different standpoint and treat the design of heterogeneity as a representation problem under limited observations. In our framework, each agent’s decision rule is implemented as a neural-network mapping from recent price histories to order decisions, trained on historical index or stock price series. To describe and manipulate heterogeneity without pre-assigning mechanism labels, we introduce Fit Quality (FQ), an ex post effect-defined index summarizing how strongly each learned rule fits the price patterns it was trained on, and we use FQ solely as a coordinate for organizing agent populations and constructing controlled changes in agent composition, rather than as a measure of forecasting skill or economic performance. Using this representation, we examine whether simulations can reproduce several stylized features of return series. We also perform simple ablation experiments to assess how far the observed properties depend on the data-trained decision rules rather than on the market mechanism alone. Taken together, the framework is intended as a step toward more data-linked, representation-conscious agent-based models, in which alternative ways of organizing heterogeneity can be compared within a common market environment. Full article

To advance marine thunderstorm forecasting and enhance the operational utility of lightning data, this study developed a novel very low-frequency (VLF) lightning data assimilation scheme for the South China Sea region. The three-dimensional graupel mixing ratio field was successfully inverted from VLF lightning detection data through the application of an empirical formula linking lightning frequency to graupel mass, a database of graupel mixing ratio profiles, and a distance-weighted diffusion scheme. This reconstructed field was then subjected to horizontal diffusion and assimilated into the Weather Research and Forecasting (WRF) model using the Grid Nudging module within the WRF–Four-Dimensional Data Assimilation (WRF-FDDA) system. A quantitative evaluation of 37 nocturnal marine convective cases was conducted using Fengyun-4A(FY-4A) satellite observations. The results demonstrate that the proposed assimilation method significantly enhances short-term (0–6 h) forecast performance. Specifically, the Fractions Skill Score (FSS) derived from the Advanced Geosynchronous Radiation Imager (AGRI) data increased rapidly during the early forecast stage, exceeding a value of 0.9. Meanwhile, the Lightning Mapping Imager Event (LMIE) product evaluation showed a high probability of detection (POD) of 85% for lightning forecasts, with a false alarm ratio (FAR) of only 9%. These findings indicate that the assimilation approach improves the accuracy of capturing the spatial structure and evolution of convective systems. Although the degree of improvement diminished with longer lead times, the results confirm the value of VLF lightning data in initializing convective-scale processes and underscore its practical value in marine nowcasting applications. Full article

Precise characterization of the thermospheric neutral wind is essential for comprehending the dynamic interactions within the ionosphere-thermosphere system, as evidenced by the development of models like HWM and the need for localized data. However, numerical models often suffer from biases due to uncertainties in external forcing and the scarcity of direct wind observations. This study examines the influence of incorporating actual neutral wind profiles from the Michelson Interferometer for Global High-resolution Thermospheric Imaging (MIGHTI) on the Ionospheric Connection Explorer (ICON) satellite into the Thermosphere Ionosphere Electrodynamics General Circulation Model (TIE-GCM) via an ensemble-based data assimilation framework. To address the challenges of assimilating real observational data, a robust background check Quality Control (QC) scheme with dynamic thresholds based on ensemble spread was implemented. The assimilation performance was evaluated by comparing the analysis results against independent, unassimilated observations and a free-running model Control Run. The findings demonstrate a substantial improvement in the precision of the thermospheric wind field. This enhancement is reflected in a 45–50% reduction in Root Mean Square Error (RMSE) for both zonal and meridional components. For zonal winds, the system demonstrated effective bias removal and sustained forecast skill, indicating a strong model memory of the large-scale mean flow. In contrast, while the assimilation exceptionally corrected the meridional circulation by refining the spatial structures and reshaping cross-equatorial flows, the forecast skill for this component dissipated rapidly. This characteristic of “short memory” underscores the highly dynamic nature of thermospheric winds and emphasizes the need for high-frequency assimilation cycles. The system required a spin-up period of approximately 8 h to achieve statistical stability. These findings demonstrate that the assimilation of data from ICON/MIGHTI satellites not only diminishes numerical inaccuracies but also improves the representation of instantaneous thermospheric wind distributions. Providing a high-fidelity dataset is crucial for advancing the modeling and understanding of the complex interactions within the Earth’s ionosphere-thermosphere system. Full article

Flood events driven by climate variability and change pose significant risks for socio-economic activities in the Awash Basin, necessitating advanced forecasting tools. This study benchmarks five deep learning (DL) architectures, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (BiLSTM), and a Hybrid CNN–LSTM, for daily discharge forecasting for the Hombole catchment in the Upper Awash Basin (UAB) using 40 years of hydrometeorological observations (1981–2020). Rainfall, lagged discharge, and seasonal indicators were used as predictors. Model performance was evaluated against two baseline approaches, a conceptual HBV rainfall–runoff model as well as a climatology, using standard and hydrological metrics. Of the two baselines (climatology and HBV), the climatology showed limited skill with large bias and negative NSE, whereas the HBV model achieved moderate skill (NSE = 0.64 and KGE = 0.82). In contrast, all DL models substantially improved predictive performance, achieving test NSE values above 0.83 and low overall bias. Among them, the Hybrid CNN–LSTM provided the most balanced performance, combining local temporal feature extraction with long-term memory and yielding stable efficiency (NSE ≈ 0.84, KGE ≈ 0.90, and PBIAS ≈ −2%) across flow regimes. The LSTM and GRU models performed comparably, offering strong temporal learning and robust daily predictions, while BiLSTM improved flood timing through bidirectional sequence modeling. The CNN captured short-term variability effectively but showed weaker representation of extreme peaks. Analysis of peak-flow metrics revealed systematic underestimation of extreme discharge magnitudes across all models. However, a post-processing flow-regime classification based on discharge quantiles demonstrated high extreme-event detection skill, with deep learning models exceeding 89% accuracy in identifying extreme-flow occurrences on the test set. These findings indicate that, while magnitude errors remain for rare floods, DL models reliably discriminate flood regimes relevant for early warning. Overall, the results show that deep learning models provide clear improvements over climatology and conceptual baselines for daily streamflow forecasting in the UAB, while highlighting remaining challenges in peak-flow magnitude prediction. The study indicates promising results for the integration of deep learning methods into flood early-warning workflows; however, these results could be further improved by adopting a probabilistic forecasting framework that accounts for model uncertainty. Full article

Accurate solar forecasting is critical for photovoltaic integration, particularly in regions with complex terrain and limited observations. This study benchmarks five deep learning architectures—MLP, RNN, LSTM, CNN, and a Grey Wolf Optimizer–enhanced MLP (MLP–GWO)—to evaluate the accuracy–computational efficiency trade-off for generating daily solar potential maps from ERA5 reanalysis over Mexico. Models were trained using a strict temporal split on a high-dimensional grid (85 × 129 points, flattened to 10,965 outputs) and evaluated in terms of predictive skill and hardware cost. The RNN achieved the best overall performance (RMSE ≈ 32.3, MAE ≈ 27.8, R² ≈ 0.96), while the MLP provided a competitive lower-complexity alternative (RMSE ≈ 54.8, MAE ≈ 46.0, R² ≈ 0.88). In contrast, the LSTM and CNN showed poorer generalization, and the MLP–GWO failed to converge. For the CNN, this underperformance is linked to the intentionally flattened spatial representation. Overall, the results indicate that within a specific ERA5-based, daily-resolution, and resource-constrained experimental framework, lightweight architectures such as RNNs and MLPs offer the most favorable balance between accuracy and computational efficiency. These findings position them as efficient surrogates of ERA5-derived daily solar potential suitable for large-scale, preliminary energy planning applications. Full article

Photovoltaic (PV) power forecasting has become a key tool for the intelligent management of electrical grids. Since the largest source of error in PV power forecasting originates from uncertainties in solar irradiance prediction, improving the accuracy of solar irradiance forecasts has emerged as an active research topic. This study evaluates multiple random tree-based model versions using a challenging dataset collected at globally distributed stations, spanning elevations from sea level to nearly 4000 m and covering a wide range of climate classes. The originality of the study lies in the synergistic contribution of two elements: the innovative inclusion of diffuse irradiance among the predictors and a comparative analysis of forecast quality across lowland and mountainous locations. In such environments, accurate solar resource forecasting is particularly important for the intelligent management of stand-alone PV systems deployed at high altitudes and in remote, off-grid areas. Overall, the results identify Extremely Randomized Trees (XTRc) as the best-performing model. XTRc achieves Skill Scores ranging from 0.087 to 0.298 across individual stations. The model accuracy remains high even at mountain stations, provided that sky-condition variability is low. Full article

Hydrological drought poses a significant threat to water security and ecosystems globally. While remote sensing offers vast spatial data, advanced analytical methods are required to translate this data into actionable insights. This review addresses this need by systematically synthesizing the state-of-the-art in using convolutional neural networks (CNNs) and satellite-derived vegetation indices for hydrological drought detection. Following PRISMA guidelines, a systematic search of studies published between 1 January 2018 and August 2025 was conducted, resulting in 138 studies for inclusion. A narrative synthesis approach was adopted. Among the 138 studies included, 58% focused on hybrid CNN-LSTM models, with a marked increase in publications observed after 2020. The analysis reveals that hybrid spatiotemporal models are the most effective, demonstrating superior forecasting skill and in some cases achieving 10–20% higher accuracy than standalone CNNs. The most robust models employ multi-modal data fusion, integrating vegetation indices (VIs) with complementary data like Land Surface Temperature (LST). Future research should focus on enhancing model transferability and incorporating explainable AI (XAI) to strengthen the operational utility of drought early warning systems. Full article