Search Results (1,371)

Rift Valley fever (RVF) is a vector-borne zoonotic disease whose occurrence is strongly associated with climatic and environmental conditions, making data-driven approaches potentially valuable for epidemiological surveillance and risk assessment. Using a publicly available historical dataset comprising 180,288 monthly observations from geographically defined administrative units across Kenya between 1981 and 2010, this study investigates machine learning (ML) for the retrospective classification of reported RVF occurrence from contemporaneous climatic, environmental, topographic, and seasonal predictors under an extremely imbalanced classification setting. The dataset provides broad geographic coverage across Kenya over a 30-year historical period; however, because the outcome reflects reported events in historical surveillance records, it is not assumed to constitute a formally population-representative national sample or to capture all underlying RVF transmission. Each observation represents a geographic unit and observation month, and the response indicates whether an RVF event was reported during that corresponding period. Therefore, the present analysis should be interpreted as contemporaneous outbreak classification rather than as a fixed-horizon prospective forecast. Thirteen classifiers representing distinct learning paradigms were systematically evaluated: Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbors, Classification and Regression Tree, Naive Bayes, Support Vector Machine, Weighted Logistic Regression, XGBoost, LightGBM, CatBoost, Balanced Random Forest, EasyEnsemble, and RUSBoost. Model performance was assessed before and after SMOTENC-based rebalancing using overall and class-specific metrics, including accuracy, precision, sensitivity, specificity, F1-score, ROC–AUC, and precision–recall-based measures. Under the retrospective stratified hold-out benchmark, XGBoost, CatBoost, Balanced Random Forest, and LightGBM achieved ROC–AUC values of 0.9176, 0.9175, 0.9114, and 0.9062, respectively. Balanced Random Forest attained the highest outbreak sensitivity (0.8851), although at the cost of very low precision, illustrating that high rare-event detection can generate a substantial false-alert burden in surveillance settings. SMOTENC produced strongly model-dependent effects: it increased outbreak sensitivity for XGBoost, LightGBM, CatBoost, KNN, CART, and RUSBoost, but substantially reduced sensitivity for Balanced Random Forest and EasyEnsemble. SHAP-based interpretability analysis indicated that month, rainfall, and slope were among the most influential predictors and further showed that class rebalancing can alter the distribution of feature contributions. Overall, the findings demonstrate that modeling reported RVF occurrence under severe class imbalance requires joint evaluation of minority-class detection, false-positive behavior, discrimination, and model interpretability rather than overall accuracy alone. The present results establish a retrospective classification benchmark for climate-informed RVF risk assessment, but they should not be interpreted as an autonomous outbreak-warning system. Translation into prospective early-warning prediction will require an explicit forecasting horizon, predictors constructed exclusively from information available before the target period, temporally and geographically independent validation, and decision thresholds evaluated against an operationally acceptable false-alert burden. Full article

Shandong is a major agricultural and economic province in northern China, where precipitation critically affects agriculture, water resources, and disaster mitigation. Cyclone-induced rainfall is a key contributor to regional precipitation. This study investigates the climatological distribution of cyclones affecting Shandong from 1980 to 2025 using reanalysis data and an objective tracking scheme, with a focus on Yellow River cyclones and the moisture sources. Results show that Yellow River cyclones account for only 12.8% of all cyclones influencing Shandong, and merely 5.4% of Yellow River cyclones can migrate eastward into this region. A case study of the Yellow River cyclone in August 2024 reveals that its southeastward track is steered by the 500 hPa flow, while warm–moist advection ahead of the cold front, combined with frontal lifting, triggers heavy precipitation. Numerical modeling further quantifies that moisture originating south of 34° N contributes ~50% to the total integrated water vapor over Shandong, dominating the moisture supply, followed by local atmospheric moisture (~30%) and evaporation (~20%). Among southerly sources, the 30–34° N band contributes the most, while that south of 28° N contributes <10%. In addition, lower-latitude moisture is likely transported via atmospheric rivers and higher-latitude moisture through feeder airstreams. This study provides a quantitative basis for understanding Yellow River cyclone activities and their heavy rainfall forecasts over Shandong. Full article

Highway soft rock slope deformation monitoring produces nonlinear, non-stationary, and multi-scale time series that are strongly affected by rainfall and field noise. This study proposes an adaptive hybrid framework that combines optimal variational mode decomposition (OVMD), the sparrow search algorithm (SSA), and gated recurrent unit (GRU) networks. High-precision BeiDou Global Navigation Satellite System (GNSS) observations collected hourly over a 120-day K55 monitoring campaign (late 2022 to early 2023) are cleaned using a cumulative-sum (CUSUM) change-point detector and cubic-spline reconstruction, while rainfall-related hydro-mechanical variables derived from seepage and slope-stability analyses are incorporated as external inputs. To prevent future-information leakage during blind testing, OVMD is recomputed causally at each one-day-ahead forecast origin using only observations available up to that origin; it then separates the deformation signal into physically interpreted trend, periodic, and high-frequency components, and SSA adaptively optimizes component-specific GRU hyperparameters for parallel prediction and reconstruction. On the K55 strongly weathered shale slope, across five independent runs the proposed model achieved a mean root-mean-square error (RMSE) of 0.04 ± 0.01 mm and a mean absolute percentage error (MAPE) of 0.18 ± 0.05%, outperforming standard GRU, long short-term memory (LSTM), and back-propagation neural network (BPNN) baselines that received an equivalent validation-based hyperparameter search. Cross-scenario evaluation on a geologically distinct K14 marl slope, independently retrained on its own record, yielded a mean RMSE of 0.14 ± 0.02 mm and a mean MAPE of 0.42 ± 0.08%. The results indicate that the proposed framework improves prediction accuracy while retaining useful cross-scenario robustness, supporting intelligent monitoring and early warning of rainfall-sensitive highway slopes. Full article

Accurate runoff forecasting serves as a fundamental basis for the scientific management of water resources and flood and drought risk mitigation. Owing to the nonlinearity, non-stationarity, and multi-scale temporal characteristics of runoff series, existing deep learning models still exhibit notable limitations in capturing long-term trends, responding to abrupt hydrological events, and ensuring model interpretability. The original Transformer relies on global self-attention, whose computational complexity increases quadratically with sequence length; it also has limited capacity to capture short-term local temporal dependencies such as rainfall–runoff relationships, and lacks prior constraints tailored to hydrological processes. To address these challenges, this study proposes a collaborative forecasting framework that integrates a gated convolutional Transformer (GCTrans) with an improved black kite algorithm (IBKA), enabling accurate, stable, and interpretable daily-scale runoff prediction. The GCTrans model consists of three customized modules: convolution-enhanced positional encoding (CEPE), which combines learnable positional encoding with local causal convolution to strengthen the temporal association of adjacent rainfall–runoff events, thereby providing a hydrologically meaningful positional reference for the attention mechanism; gated convolutional attention (GCA), which adopts a dual-path parallel architecture comprising global self-attention and local causal convolution to adaptively fuse long-term seasonal patterns with short-term storm-induced variations, thus capturing both baseflow evolution and flood peak responses; and a temporal gated output layer (TGOL), which performs adaptive feature weighting along the temporal dimension to selectively enhance the contribution of critical driving periods associated with extreme flood events, thereby improving the flood peak prediction accuracy. In addition, an improved black kite algorithm (IBKA) was developed by incorporating Tent chaotic initialization to enhance initial population diversity and introducing cosine adaptive inertia weights to dynamically balance global exploration and local exploitation, effectively alleviating premature convergence in high-dimensional hyperparameter spaces. Validation using data from the ME-Inland snowmelt-dominated watershed and the OR-Coastal storm-driven coastal watershed in the United States demonstrated that the GCTrans model consistently outperformed benchmark models including TCN, LSTM, Transformer, and Informer. After synergistic optimization with IBKA, both prediction accuracy and stability were further improved. SHAP-based interpretability analysis revealed that the model’s feature response patterns are statistically consistent with the rainfall–runoff generation mechanisms of the study basins: temperature-related drivers dominate in the inland watershed, while precipitation plays a dominant role in the coastal watershed, confirming the hydrological plausibility of the model’s decision-making logic. The integrated framework—encompassing model architecture, optimization algorithm, and interpretability—offers a valuable methodological reference for deep learning-based runoff forecasting in complex hydrological settings. Full article

Precipitation forecasts from numerical weather prediction systems can contain systematic errors in both occurrence and magnitude, limiting their usefulness for hydrological applications. This study evaluated two operational precipitation forecasting systems against two observational reference datasets across three basins in São Paulo State, Brazil, and assessed statistical post-processing for dry/wet occurrence and precipitation magnitude. Four logistic-regression-based methods were evaluated for occurrence correction, while Quantile Delta Mapping (QDM) was applied to precipitation amounts. Occurrence correction was assessed using POD, FAR, CSI, and ACC, with dry days defined as the event. Changes in individual classifications were evaluated using the exact McNemar test, while changes in categorical metrics across seven lead times were assessed using exact paired permutation tests and bootstrap 95% confidence intervals. A descriptive multi-metric ranking was used to compare correction methods. QDM was evaluated using RMSE skill score and KGE. Occurrence correction modified categorical performance, with effects depending on forecast–observation pairing, basin, and lead time. The McNemar test identified significant classification changes after Holm adjustment in some configurations, whereas the permutation tests did not provide evidence of systematic metric improvement. HBLR-AR1 showed the most balanced overall performance, whereas LR-Seasonal was the least consistent method. QDM improved RMSE skill, particularly at longer lead times, but did not consistently improve KGE. Overall, correction effectiveness depended on forecast–observation discrepancies. Full article

Agricultural drought is a natural hazard which has disastrous impacts on populations, economies and the environment in drought-vulnerable countries. This study develops an agricultural drought prediction framework for Timor-Leste—a least developed country in Southeast Asia. Currently, long-range forecasting capabilities and proactive agricultural drought management practices in Timor-Leste remain limited, constraining the country’s ability to prepare for and respond to periodic drought events. This research evaluated the effectiveness of drought prediction in Timor-Leste using seasonal rainfall outlooks from a dynamical Global Climate Model (GCM): the European Centre for Medium-Range Weather Forecasts’ (ECMWF) Seasonal Forecast System 5 (SEAS5), across different drought and non-drought events. SEAS5 effectively predicted an increased probability of below-average median rainfall over Timor-Leste for the case study of the 2015–2016 El Niño-induced drought and was assessed as having higher probabilistic skill across the wider study area compared with the Australian Bureau of Meteorology’s (BoM) Australian Community Climate and Earth-System Simulator (ACCESS-S2). While some limitations exist in raw forecast skill at times of year when predictability is lower, outlooks from both GCMs could, with sound communication, be applied to predict drought’s onset, peak and end. This research serves as a foundational step toward the development of an agricultural drought early warning system in Timor-Leste. Full article

Conventional evaluations of rainfall prediction models rely on average accuracy, often masking the conditions, locations and causes of model failure and reduced reliability. This study proposes a paradigm shift from conventional average-accuracy benchmarking toward failure-aware forecast-error diagnosis in the Bengawan Solo River Basin, a tropical monsoon river basin in Indonesia with moderate topographic gradients (grid elevations span ≈ 300–650 m). Methodologically, forecasts from previously published models are treated as fixed inputs and their errors are modelled as the response variable, so the analysis diagnoses when and where models fail rather than retraining them. By treating forecast errors as response variables, rather than as random residuals, this study analyses 345,180 model–grid records–month records from ten individual models (RF, XGB, LGBM, SVR, MLP, LSTM, GRU, TCN, CNN, Transformer) and one best ensemble model (Ensemble_Q, a stacking of RF, XGB, SVR, MLP, LGBM, LSTM, GRU, TCN, CNN, Transformer) against observed CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data) precipitation, seasonal phase, ENSO and IOD regimes (El Niño–Southern Oscillation and Indian Ocean Dipole, respectively), the MJO index (Madden–Julian Oscillation) as an additional analysis, and elevation as a topographic control, using log-error models, high-error logistic regression, interaction tests, and block bootstrap validation (N = 1000), false discovery rate, and spatial statistics. Results indicate that prediction errors are not random but are systematically controlled: the Transition II phase increases log-error by 245% (pooled log-error model) and raises the odds of a high-error event roughly 40-fold relative to the dry season; La Niña conditions amplify errors by 41% and the odds of a high-error event by 3.3 times (though this ENSO signal is largely entangled with co-occurring Negative-IOD months), and every 100 m increase in elevation increases errors by 26%, with errors forming distinct spatial clusters (Moran’s I = 0.78; p = 0.001). Ensemble_Q outperforms the baseline on an aggregate basis (mean absolute error, MAE = 54.10 mm) but still experiences error amplification under these conditions, while spatial deep-learning architectures (TCN, CNN, Transformer) prove most vulnerable to elevation gradients. All major patterns persisted across variations in thresholds, model subsets, ENSO definitions, multiplicity corrections, and bootstrapping. These findings confirm that superior mean accuracy does not guarantee operational reliability, and that conditional failure diagnosis is an essential complement to benchmarking rainfall predictions in tropical monsoon regions. Full article

Accurate areal rainfall estimation is essential for hydrological modeling and flood forecasting, yet method selection remains uncertain in small catchments with extremely sparse gauge networks. This event-scale study compared arithmetic mean (AM), Thiessen polygon (TP), inverse distance weighting (IDW), precipitation–elevation linear regression (ELR), multiple linear regression (MLR), and a multi-layer perceptron (MLP) in a 0.719 km² catchment monitored by three gauges. Two complementary evaluations were conducted. Station-wise leave-one-out cross-validation (LOOCV) assessed prediction at an omitted gauge, whereas a radar-referenced comparison assessed catchment-average estimates obtained from the complete gauge network. MLR produced the lowest LOOCV error (RMSE = 0.433 mm; CC = 0.777). In the radar comparison, MLP and MLR produced nearly identical RMSE values of 0.668 and 0.669 mm, respectively, and are therefore interpreted as practically similar rather than meaningfully different. All method rankings are conditional on the selected 60 h event, the three-gauge arrangement, and uncertainty in the radar reference. The findings demonstrate that station-omission performance and full-network areal estimation address different operational questions and should be considered together when selecting an interpolation method for extremely sparse networks. Full article

This study investigates the relationship between key circulation factors and ensemble forecast uncertainty during an atypical extreme heavy-rainfall event under weak synoptic forcing that affected the Guangzhou–Foshan megacity cluster in the Pearl River Delta (PRD) on 8 September 2022. Here, “atypical” refers to a localized extreme event occurring over the low-elevation urban river network without strong synoptic-scale drivers. Framed as an event-specific retrospective diagnostic analysis, the study used the China Land Multi-source Precipitation Analysis System version 2.1 (CMPAS-V2.1), ERA5 reanalysis, and 3-km (R3) and 9-km (R9) ensemble forecasts from the CMA Tropical Regional Atmospheric Model Ensemble Prediction System (CMA-TRAMS EPS). Spearman rank correlation and Monte Carlo field-significance tests were first applied to identify environmental variables closely associated with hourly precipitation variations, pinpointing the 700-hPa U-wind, 500-hPa V-wind, and 850-hPa V-wind as the most significant circulation predictors. Spatial anomaly fields of these key predictors were then subjected to hierarchical clustering, with clustering robustness evaluated using the cophenetic correlation coefficient (CCC) and bootstrap resampling. Because the clustering structure of the 925-hPa V-wind was comparatively weak, it was excluded from the final member-selection procedure. Finally, circulation-consistent ensemble members were selected using a multi-predictor consensus criterion (retaining 13 R3 members and 7 R9 members), and their 24 h accumulated precipitation was averaged to obtain a circulation-conditioned subset mean. The results show that persistent high temperatures, abundant moisture in the middle and lower troposphere, and a favorable multilayer circulation configuration provided suitable conditions for convective instability accumulation and localized heavy rainfall development. The precipitation forecasts exhibited substantial member-to-member variability. Under a consistent evaluation threshold, the 9-km configuration demonstrated superior overall ensemble-mean spatial skill compared to the 3-km configuration, indicating that increasing horizontal resolution does not necessarily improve forecast skill for weakly forced extreme rainfall. The resulting circulation-conditioned subset means successfully shifted the predicted heavy-rainfall center toward the observed Guangzhou–Foshan region and reduced the overestimated heavy-rainfall magnitudes over northern Guangzhou. Rather than serving as a purely objective score-maximizing post-processing algorithm, this approach extracts physically indicative spatial scenarios from ensemble spread. These findings provide a practical diagnostic framework for conditional forecast correction of localized heavy rainfall under weak synoptic forcing, though validation across multiple independent cases and consistent quantitative verification are necessary to assess its operational generalizability. Full article

Atmospheric river (AR)-driven flooding is a natural hazard that causes severe damage in many regions, and the damage escalates sharply once an AR persists beyond a certain duration. Existing studies and numerical weather prediction models, however, have focused mainly on AR occurrence and on the intensity of integrated vapor transport (IVT) at individual time steps, paying little attention to duration. California and Chile are both exposed to severe AR-related hazards, yet for the period since 2000, the Global Ensemble Forecast System (GEFS) forecast at a two-day lead, compared against the regional IVT threshold, correctly predicts persistence for only about 30% of the ARs that actually persisted for 24 h or longer. This study retains the predictive capability of the physics-based GEFS forecast while correcting its weak performance on persistence using TabPFN, a pre-trained transformer for tabular data. Using single-control-member forecasts from the GEFS v12 reforecast (2000 to 2019), the model predicts the minimum IVT over the target window and compares it with the regional threshold. In the performance evaluation, the F1 score, which combines the precision and recall of AR persistence prediction into a single measure, rose from 0.414 to 0.502 and 0.601 in the two regions, and TabPFN outperformed machine learning models such as 1D-CNN and LGBM. Moreover, on the California coast, the proposed model, through its persistence decisions, captured 66.3% of the rainfall that fell during persistent atmospheric river events, up from 30.7% for the raw forecast. The proposed model offers a forecast post-processing method for predicting AR persistence and can contribute meaningfully to flood disaster prevention. Full article

Surface subsidence in mining areas is a widespread, long-term, and slow-onset geological hazard that can induce cascading failures, including slope instability and ground collapse, thereby threatening infrastructure and human safety. Accurate characterization of its spatiotemporal evolution and reliable prediction of future trends are therefore essential for effective mine safety management and hazard assessment. This study investigates an open-pit mine by integrating time-series Interferometric Synthetic Aperture Radar (InSAR) monitoring with a deep learning–based prediction framework. A total of 70 Sentinel-1A synthetic aperture radar (SAR) images acquired between January 2023 and May 2025 were processed to quantify surface deformation. The results reveal a large-scale subsidence funnel, with a maximum subsidence rate of 143.00 mm/yr and a cumulative displacement of −337.89 mm. The observed deformation is controlled by combined effects of rainfall, seismic activity, and local geological conditions. To predict the temporal evolution of subsidence, a hybrid convolutional neural network–long short-term memory (CNN–LSTM) time-series forecasting model (CL-TSF) is proposed. By integrating convolutional feature extraction with long short-term memory–based sequence modeling, the model effectively captures spatial patterns and long-term temporal dependencies. Compared with conventional CNN and LSTM models, the proposed approach achieves superior performance, with a Mean Absolute Percentage Error (MAPE) of 2.24% and a Root Mean Square Error (RMSE) of 5.260. Its robustness is validated through accurate multi-step prediction of the final five deformation periods. These findings provide insights into mining-induced subsidence mechanisms and demonstrate the potential of the proposed framework for dynamic early warning and risk assessment in mining areas. Full article

Accurate assimilation of satellite-derived precipitation data remains a critical challenge in regional numerical weather prediction (NWP), particularly for convective-scale rainfall. Conventional observation operators rely on radiative transfer models or simplified moist physics, introducing substantial uncertainty at convective scales. This study develops a machine learning-based observation operator and implements a “one-dimensional variational (1D-Var) + three-dimensional variational (3D-Var)” framework to assimilate FY-3G/PMR precipitation data into the CMA-MESO. Results show the machine learning-based operator demonstrates high accuracy for light, moderate, and heavy rain (BIAS < 0.5 mm/h, RMSE < 2.5 mm/h) and exhibits good generalization capability across different weather systems. Through the two-step assimilation, the retrieved humidity profiles improve initial moisture fields. Both the single case study and the one-month continuous cycling experiment consistently show that the assimilation yields measurable improvements in short-term precipitation forecasts, particularly for extreme precipitation events, with a maximum TS improvement of 19.9% for severe torrential rain. This work demonstrates that the machine learning-based observation operator exhibits potential in precipitation data assimilation, offering a viable pathway to enhance NWP. Full article

This study investigates the influence of rainfall variability on runoff generation in the Upper Ing River Basin and inflow to the Mae Tum Reservoir in northern Thailand using the physically based Soil and Water Assessment Tool (SWAT) version 2012. In small mountainous watersheds, water supply reliability for irrigation and domestic use—particularly for unmonitored royal initiated projects like the Mae Tum Reservoir—has become a critical concern due to shifting climatic extremes. A SWAT model was developed using detailed spatial data on topography, land use, and soil characteristics together with long-term daily climate and streamflow records. The model performance at Station I.17 was evaluated through calibration and validation using the R², Nash–Sutcliffe Efficiency (NSE), and percent bias indices. Rainfall regimes were classified into dry, normal, and wet years based on the mean and standard deviation of 25-year gauge records to drive scenario simulations. The calibrated model reproduced seasonal runoff patterns satisfactorily (monthly NSE up to 0.685 and R² up to 0.712). The simulations demonstrated the strong sensitivity of both the runoff at Station I.17 and reservoir inflow to interannual rainfall differences, with the annual runoff ranging from 71.5 to 379.7 million m³ and the annual inflow to Mae Tum Reservoir ranging from 28.84 to 48.33 million m³. These findings demonstrate that physically based spatial modeling can effectively replace traditional empirical operating rules, providing a highly transferable framework for runoff forecasting, reservoir inflow assessment, and climate responsive water resources planning in data-scarce tropical mountainous basins. Full article

This study proposes an innovative framework that combines hydroclimatic and agro-environmental predictors, including nitrate concentration and NDVI, with climatic factors such as Rainfall, temperature, and evapotranspiration to forecast piezometric level variations in the Saïss Basin, Morocco. Eight Machine Learning (ML) models were benchmarked, and feature importance was assessed using Shapley Additive exPlanations (SHAP) to ensure model transparency and interpretability. In parallel, the PELT algorithm was applied to detect structural change points, while Sen’s slope estimator and the Mann–Kendall test were used to quantify long-term trends. The Extra Trees (ET) model achieved the best performance (R² = 0.92), with Rainfall emerging as the most influential predictor, followed by nitrate concentration, confirming the added value of hydrochemical indicators for groundwater forecasting. Change-point analysis revealed significant declines during the 1980s and 1990s, followed by lower-amplitude fluctuations since the late 2000s. Projections toward 2050 suggest partial stabilization in the central part of the basin under favorable recharge conditions, whereas persistent declines are expected to continue in peripheral areas subjected to sustained groundwater abstraction pressure. These findings provide a robust and transferable decision-support tool for the sustainable management of groundwater resources in semi-arid agricultural area. Full article

Climate change is expected to alter the climatic suitability of crops. This study evaluated the climatic suitability of maize cultivation in the TR21 Thrace Region of Türkiye using the EcoCrop model. Climatic suitability was assessed for a reference period (1950–2000) and projected for the 2050s using three CMIP5 global climate models (MPI_ESM_LR, HADGEM2_ES, and CNRM_CM5) under the RCP4.5 and RCP8.5 scenarios. The EcoCrop model implemented in DIVA-GIS was used to evaluate climatic suitability. All climate models projected increases in average annual temperature of 1.7–3.8 °C, whereas projected changes in average annual precipitation ranged from −92 to +46 mm. Despite variations in temperature and rainfall forecasts, the projections indicate that the area suitable for maize cultivation will increase; the HADGEM2_ES model produced the highest proportion of suitable areas. The suitability rate across all projections ranged from 54.7% to 96.8%. Projected climate change is likely to improve maize climatic suitability in TR21 by the 2050s. Because EcoCrop evaluates climatic suitability based solely on temperature and precipitation thresholds, the projected changes should be interpreted as a climatic envelope for maize rather than as a direct increase in future yield or productivity. These findings inform agricultural adaptation strategies and regional land-use planning under climate change. Full article