The decontaminant mechanism of polyamide membranes for sulfamethoxazole: The insights from combined machine learning and molecular modelling

Chemical Engineering Science, Journal Year: 2025, Volume and Issue: unknown, P. 121293 - 121293

Published: Jan. 1, 2025

Language: Английский

---

Mixture of experts leveraging informer and LSTM variants for enhanced daily streamflow forecasting

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132737 - 132737

Published: Jan. 1, 2025

Language: Английский

---

Machine learning-based prediction for airflow velocity in unpressured water-conveyance tunnels

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(2)

Published: Feb. 1, 2025

Spillway and drainage tunnels have an open-channel flow pattern when operating under unpressured condition, above which air is driven resisted by water flow, wall friction, pressure difference. Unpressured present many airflow-related safety environmental issues, including fluctuation, gate vibration, shaft cover blow-off, odor emission; therefore, it valuable to study predict their airflow velocity. Given the difficulty in accurate prediction of velocity complicated influences hydraulic, structural, boundary parameters, this focuses on establishing high-performance models understanding importance independent coupled each parameter using machine learning. It found that Froude number, ratio free-surface width unwetted perimeter, relative ventilation area, tunnel length are four key parameters. By these parameters input combination, learning can well tunnels, achieving significantly higher performance than existing empirical theoretical models. Among models, built Random Forest XGBoost demonstrate best with R2 ≥ 0.911. The interpretability analysis reveals highest number increases generally result enhancement plays a dominant role ≤11.5, continuous increase exhibits marginal effect. area close importances, either promoting To help researchers engineers unfamiliar easily accurately GPlearn algorithm employed establish explicit expressions, validated good 0.900.

Language: Английский

---

Spatial heterogeneity of groundwater depths in coastal cities and their responses to multiple factors interactions by interpretable machine learning models

Geoscience Frontiers, Journal Year: 2025, Volume and Issue: unknown, P. 102033 - 102033

Published: Feb. 1, 2025

Language: Английский

---

Blending daily satellite precipitation product and rain gauges using stacking ensemble machine learning with the consideration of spatial heterogeneity

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133223 - 133223

Published: March 1, 2025

Language: Английский

---

Performance enhancement of deep learning model with attention mechanism and FCN model in flood forecasting

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133221 - 133221

Published: April 1, 2025

Language: Английский

---

Machine-Learning-Based Ensemble Prediction of the Snow Water Equivalent in the Upper Yalong River Basin

Sustainability, Journal Year: 2025, Volume and Issue: 17(9), P. 3779 - 3779

Published: April 22, 2025

The snow water equivalent (SWE) in high-altitude regions is crucial for resource management and disaster risk reduction, yet accurate predictions remain challenging due to complex snowmelt processes, nonlinear meteorological factors, time-lag effects. This study used remote sensing products from the Advanced Microwave Scanning Radiometer (AMSR) as predictand evaluating SWE predictions. It applied nine machine learning models—linear regression (LR), decision trees (DT), support vector (SVR), random forest (RF), artificial neural networks (ANNs), AdaBoost, XGBoost, gradient boosting (GBDT), CatBoost. For each model, submodels were constructed predict next 1 30 days. of model formed prediction over Through an accuracy evaluation ensemble forecasting, days Yalong River above Ganzi Basin was finally achieved. results showed that all models, average Nash–Sutcliffe Efficiency (NSE) rate greater than 0.8, root mean square error (RMSE) under 8 mm, relative (RE) below 7% across three lead time periods (1–10, 11–20, 21–30 days). combining ANNs, GBDT, CatBoost, demonstrated superior accuracy, with NSE values exceeding 0.85 RMSE 6 mm. A sensitivity analysis using Shapley Additive Explanations (SHAP) revealed temperature variables (average, minimum, maximum temperatures) most influential while humidity (Rhu) significantly affected by reducing evaporation. These findings provide insights improving regions.

Language: Английский

---

Driving Forces behind the Reduction in Cropland Area on Hainan Island, China: Implications for Sustainable Agricultural Development

Land, Journal Year: 2024, Volume and Issue: 13(8), P. 1274 - 1274

Published: Aug. 13, 2024

Food security is a major challenge for China at present and will be in the future. Revealing spatiotemporal changes cropland identifying their driving forces would helpful decision-making to maintain grain supply sustainable development. Hainan Island endowed with rich agricultural resources due its unique climatic conditions facing tremendous pressure protection huge variation natural human activities over past few decades. The purpose of this study assess on predict future under different scenarios. Key findings are as follows: (1) From 2000 2020, area decreased by 956.22 km2, causing center shift southwestward 8.20 km. This reduction mainly transformed into construction land woodland, particularly evident coastal areas. (2) Among anthropogenic factors, increase footprint primary reason decrease cropland. Land use driven population growth, especially economically active densely populated areas, key factors decrease. Natural such topography climate change also significantly impact changes. (3) Future scenarios show significant differences In development scenario, expected continue decreasing 597 while ecological conversion restricted 269.11 km2; however, trend reversed, increasing 448.75 km2. Our provide deep understanding behind and, through scenario analysis, demonstrate potential policy choices. These insights crucial formulating sound management policies protect resources, food security, promote balance.

Language: Английский

---

Bridging the gap: An interpretable coupled model (SWAT-ELM-SHAP) for blue-green water simulation in data-scarce basins

Agricultural Water Management, Journal Year: 2024, Volume and Issue: 306, P. 109157 - 109157

Published: Nov. 8, 2024

Language: Английский

---

Stream salinity prediction in data-scarce regions: Application of transfer learning and uncertainty quantification

Journal of Contaminant Hydrology, Journal Year: 2024, Volume and Issue: 266, P. 104418 - 104418

Published: Aug. 26, 2024

Language: Английский

---