Machine Learning Classification Strategy to Improve Streamflow Estimates in Diverse River Basins in the Colorado River Basin DOI Creative Commons

Sarah Maebius,

Katrina Bennett, Jon Schwenk

et al.

Earth and Space Science, Journal Year: 2024, Volume and Issue: 11(12)

Published: Dec. 1, 2024

Abstract Streamflow in the Colorado River Basin (CRB) is significantly altered by human activities including land use/cover alterations, reservoir operation, irrigation, and water exports. Climate also highly varied across CRB which contains snowpack‐dominated watersheds arid, precipitation‐dominated basins. Recently, machine learning methods have improved generalizability accuracy of streamflow models. Previous successes with LSTM modeling primarily focused on unimpacted basins, few studies included impacted systems either regional or single‐basin modeling. We demonstrate that diverse hydrological behavior river basins are too difficult to model a single, model. propose method delineate catchments into categories based level predictability, characteristics, influence. Lastly, we each category climate anthropogenic proxy data sets use feature importance assess whether performance improves additional relevant data. Overall, cover at low temporal resolution was not sufficient capture irregular patterns releases, demonstrating having high‐resolution release global scale. On other hand, classification approach reduced complexity has potential improve forecasts human‐altered regions.

Language: Английский

Hybrid deep learning downscaling of GCMs for climate impact assessment and future projections in Oman DOI
Erfan Zarei, Mohammad Reza Nikoo, Ghazi Al-Rawas

et al.

Journal of Environmental Management, Journal Year: 2025, Volume and Issue: 376, P. 124522 - 124522

Published: Feb. 15, 2025

Language: Английский

Citations

1
Coupling SWAT and Transformer Models for Enhanced Monthly Streamflow Prediction DOI Open Access

Jiahui Tao,

Yicheng Gu,

Xin Yin

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(19), P. 8699 - 8699

Published: Oct. 9, 2024

The establishment of an accurate and reliable predictive model is essential for water resources planning management. Standalone models, such as physics-based hydrological models or data-driven have their specific applications, strengths, limitations. In this study, a hybrid (namely SWAT-Transformer) was developed by coupling the Soil Water Assessment Tool (SWAT) with Transformer to enhance monthly streamflow prediction accuracy. SWAT first constructed calibrated, then its outputs are used part inputs Transformer. By correcting errors using Transformer, two effectively coupled. Monthly runoff data at Yan’an Ganguyi stations on Yan River, first-order tributary Yellow River Basin, were evaluate proposed model’s performance. results indicated that performed well in predicting high flows but poorly low flows. contrast, able capture low-flow period information more accurately outperformed overall. SWAT-Transformer could correct predictions overcome limitations single model. integrating SWAT’s detailed physical process portrayal Transformer’s powerful time-series analysis, coupled significantly improved offer optimal resource management, which crucial sustainable economic societal development.

Language: Английский

Citations

4
Cascaded neural network surrogate modeling for real-time decision-making in long-distance water supply distribution DOI Creative Commons
Lin Shi, Jian Zhang, Sheng Chen

et al.

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 16, 2025

Effective water distribution in long-distance supply systems requires precise control over pump station operations and flow-regulating elements, such as speeds valve openings, typically achieved through hydraulic models. However, traditional models are time-intensive to develop require frequent calibration, limiting their practicality for real-time applications. This paper presents a cascaded neural network (CNN) model that integrates classification regression components serve an efficient surrogate decision-making. In the proposed CNN model, component identifies number of pumps needed meet system flow demands, while predicts target values openings. Considering nonlinear relationship between rate regulating error was introduced evaluation metric via Orthogonal-Triangular (QR) decomposition. The model's performance robustness were validated using data from actual system, including analyses its sensitivity uncertainties reservoir level measurements. Results demonstrate achieves more accurate predictions compared pure networks. Furthermore, uncertainty analysis reveals is less affected by measurement errors, it sensitive underscoring importance monitoring practical

Language: Английский

Citations

0
Enhancing Long-Term Flood Forecasting with SageFormer: A Cascaded Dimensionality Reduction Approach Based on Satellite-Derived Data DOI Creative Commons
Fatemeh Ghobadi, Amir Saman Tayerani Charmchi,

Doosun Kang

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 365 - 365

Published: Jan. 22, 2025

Floods, increasingly exacerbated by climate change, are among the most destructive natural disasters globally, necessitating advancements in long-term forecasting to improve risk management. Traditional models struggle with complex dependencies of hydroclimatic variables and environmental conditions, thus limiting their reliability. This study introduces a novel framework for enhancing flood accuracy integrating geo-spatiotemporal analyses, cascading dimensionality reduction, SageFormer-based multi-step-ahead predictions. The efficiently processes satellite-derived data, addressing curse focusing on critical long-range spatiotemporal dependencies. SageFormer captures inter- intra-dependencies within compressed feature space, making it particularly effective forecasting. Performance evaluations against LSTM, Transformer, Informer across three data fusion scenarios reveal substantial improvements accuracy, especially data-scarce basins. integration hydroclimate attention-based networks reduction demonstrates significant over traditional approaches. proposed combines advanced deep learning, both interpretability precision capturing By offering straightforward reliable approach, this advances remote sensing applications hydrological modeling, providing robust tool mitigating impacts extremes.

Language: Английский

Citations

0
Middle‐ and Long‐Term Runoff Forecast Model for Water Resource and Climate Security Based on Self‐Attention Mechanism DOI
Juan Chen,

M.Y. Liu,

Weifeng Liu

et al.

Land Degradation and Development, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 28, 2025

ABSTRACT Reliable middle‐ and long‐term streamflow forecasts are critical for ensuring water resources management climate security. This study establishes a novel runoff forecasting model based on the self‐attention (SA) mechanism variational mode decomposition‐gated recurrent unit (VMD‐GRU) framework to improve monthly prediction accuracy. The maximal information coefficient (MIC) method is adopted screen key drivers of variability. proposed integrates VMD decompose sequence into intrinsic components applies GRU coupled with SA predict each component. whale optimization algorithm (WOA) VMD‐SA‐GRU hyperparameters, then forecast results obtained by superimposing Using 40 years data from South‐to‐North Water Diversion Project in China, evaluated against VMD‐GRU benchmarks. Results demonstrate that leverages strengths its constituent algorithms, significantly improving Compared model, enhances Nash‐Sutcliff efficiency (NSE) 6%–35%, reduces root mean square error (RMSE) 15%–30%, decreases absolute (MAE) 15%–33%. robust provides reliable tool sustainable resource addressing climate‐related challenges.

Language: Английский

Citations

0
Long Short-Term Memory (LSTM) Networks for Accurate River Flow Forecasting: A Case Study on the Morava River Basin (Serbia) DOI Open Access
Igor Leščešen, Mitra Tanhapour, Pavla Pekárová

et al.

Water, Journal Year: 2025, Volume and Issue: 17(6), P. 907 - 907

Published: March 20, 2025

Accurate forecasting of river flows is essential for effective water resource management, flood risk reduction and environmental protection. The ongoing effects climate change, in particular the shift precipitation patterns increasing frequency extreme weather events, necessitate development advanced models. This study investigates application long short-term memory (LSTM) neural networks predicting runoff Velika Morava catchment Serbia, representing a pioneering LSTM this region. uses daily runoff, temperature data from 1961 to 2020, interpolated using inverse distance weighting method. model, which was optimized trial-and-error approach, showed high prediction accuracy. For station, model mean square error (MSE) 2936.55 an R2 0.85 test phase. findings highlight effectiveness capturing nonlinear hydrological dynamics, temporal dependencies regional variations. underlines potential models improve management strategies Western Balkans.

Language: Английский

Citations

0
A Bibliometric Analysis of Trends in Rainfall-Runoff Modeling Techniques for Urban Flood Mitigation (2005-2024) DOI Creative Commons

Abd. Rakhim Nanda,

Nurnawaty Nurnawaty,

Amrullah Mansida

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104927 - 104927

Published: April 1, 2025

Language: Английский

Citations

0
The enhanced integration of proven techniques to quantify the uncertainty of forecasting extreme flood events based on numerical weather prediction models DOI Creative Commons
Mitra Tanhapour, Jaber Soltani, Hadi Shakibian

et al.

Weather and Climate Extremes, Journal Year: 2025, Volume and Issue: unknown, P. 100767 - 100767

Published: April 1, 2025

Language: Английский

Citations

0
A spatiotemporal watershed-scale machine-learning model for hourly and daily flood-water level prediction: the case of the tidal Beigang River, Taiwan DOI Creative Commons

Wen‐Dar Guo,

Wei‐Bo Chen,

Chih-Hsin Chang

et al.

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: March 3, 2025

Language: Английский

Citations

0
Analysis and Prediction of Flood Disasters Based on BP Neural Network and Convolutional Neural Network DOI

Yanbing Lin

Published: Jan. 10, 2025

Language: Английский

Citations

0