Water Resources Research最新文献

Physics‐Informed Fusion Learning for Nowcasting Fault Detection of Hydrological Multi Sensor Network 水文多传感器网络近播故障检测的物理信息融合学习

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2026wr043436

Farid Mousavi,Ali Torabi Haghighi,Jari Silander,Mehdi Monemi,Mehdi Rasti

{"title":"Physics‐Informed Fusion Learning for Nowcasting Fault Detection of Hydrological Multi Sensor Network","authors":"Farid Mousavi,Ali Torabi Haghighi,Jari Silander,Mehdi Monemi,Mehdi Rasti","doi":"10.1029/2026wr043436","DOIUrl":"https://doi.org/10.1029/2026wr043436","url":null,"abstract":"Abstract Urban flood monitoring demands timely, reliable decisions under urgent and often unseen conditions. However, faults in sensor networks can undermine response, leading to human and economic losses. To address these issues, we propose a Nowcasting Physics‐Informed (NPI) model for fault detection in streamflow sensors, with a 100‐min memory window at 2‐min resolution. A Long Short‐Term Memory (LSTM) consumes fused features from measured signals and Storm Water Management Model simulator outputs to produce end‐of‐window fault probabilities. To ensure operational reliability, a lightweight per‐sensor eXtreme Gradient Boosting (XGBoost) stage calibrates the LSTM score using window‐local statistics of the measurement. In this study, we investigate whether and to what extent fusing a physical model with sensor data improves fault detection, and whether per‐sensor threshold calibration matters. Our results indicated yes. The Area under the precision–recall curve (AUC‐PR) was improved by 3.7%–12.5% over the physics‐informed model compared to baseline non‐physics‐informed learning. In addition, post‐hoc calibration improved AUC‐PR by an additional 0.2%–2.3%. Across five cross‐validation folds, F1‐score (F1) increased from 0.75 for the non‐physics LSTM baseline to 0.83 with calibration, and further to 0.88 for the physics informed model. Adding post‐hoc calibration to the physics informed model yielded the best result at 0.90. The NPI is causal and auditable, exporting calibrated probabilities and binary alerts for direct operator use without retraining the LSTM, and offers a practical template for warning systems and training strategies that remain robust to unseen conditions.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"198 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Constrained Estimation of Export and Import Inter‐Basin Groundwater Flows by Coupling Deep Learning With a Water‐Age Balance Approach 基于深度学习和水年龄平衡方法的流域间进出口地下水流量约束估计

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2026wr043625

Luyao Ren,Xiankui Zeng,Xiaodong Pan,Dong Wang,Jichun Wu

{"title":"Constrained Estimation of Export and Import Inter‐Basin Groundwater Flows by Coupling Deep Learning With a Water‐Age Balance Approach","authors":"Luyao Ren,Xiankui Zeng,Xiaodong Pan,Dong Wang,Jichun Wu","doi":"10.1029/2026wr043625","DOIUrl":"https://doi.org/10.1029/2026wr043625","url":null,"abstract":"Abstract Inter‐basin groundwater flow (IGF) is a critical process that links material and energy exchange between basins. Based on the source and flow direction of groundwater, IGF can be separated into export IGF and import IGF, which respectively denote the lateral outflow and inflow of groundwater from and into a basin. However, traditional hydrological modeling based on net IGF obscures the bidirectional exchange processes between basins. Furthermore, export and import IGF are difficult to measure directly, and existing methods to estimate them (e.g., hydrochemical tracing and groundwater modeling) are often costly and data‐demanding. Therefore, this study innovatively proposes a method that integrates the Long Short‐Term Memory (LSTM) with the ranked Storage Age Selection (rSAS) approach to partition export and import IGF. This method does not rely on detailed hydrogeological characterization and regional groundwater model. The feasibility of the proposed method was evaluated through a case study in the Lower Hafren basin, demonstrating its ability to quantify chloride transport processes within a unified water‐age balance framework, allowing a constrained estimation of unobserved inter‐basin groundwater flows. The results indicate that export and import IGF exhibit significantly different statistical characteristics compared to the net IGF. At the monthly timescale, the magnitudes of export IGF and import IGF are over two orders of magnitude greater than that of net IGF. And net IGF conceals the true seasonal fluctuation patterns inherent to export and import IGF. Furthermore, the uncertainties in the IGF partitioning were quantified and controlled through Bayesian uncertainty analysis and the LM‐CMA‐ES algorithm.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"20 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantifying Groundwater–Surface Water Exchange on a River Island: A Comparative Analysis of Direct and Indirect Methods 河岛地下水-地表水交换量化：直接法与间接法的比较分析

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2026wr043579

Nayeon Ki,Kyungwon Kwak,Jonghoon Park,Gyeongseo Jeong,Yongmoon Lee,Hanjin Choe,Chung‐Mo Lee

{"title":"Quantifying Groundwater–Surface Water Exchange on a River Island: A Comparative Analysis of Direct and Indirect Methods","authors":"Nayeon Ki,Kyungwon Kwak,Jonghoon Park,Gyeongseo Jeong,Yongmoon Lee,Hanjin Choe,Chung‐Mo Lee","doi":"10.1029/2026wr043579","DOIUrl":"https://doi.org/10.1029/2026wr043579","url":null,"abstract":"Abstract Groundwater–surface water exchange is a key hydrological process that governs river water quality and aquatic ecosystems. However, the quantification of such exchange remains uncertain, especially within river island aquifers where exchange processes are highly heterogeneous. In this study, direct seepage meter measurements and indirect Darcy‐based estimates of exchange fluxes were compared under consistent spatiotemporal conditions within the aquifer of Jungsa Island, a river island in the lower West Nakdong River, South Korea. At the downstream low‐permeability site (SP‐3), Darcy‐based exchange fluxes ranged from −2.14 × 10 −5 to 1.15 × 10 −5 m/hr. Owing to these small magnitudes, net intrusion and discharge were not distinguishable. However, seepage meter measurements consistently indicated intrusion of surface water into the island aquifer, with fluxes ranging from −8.46 × 10 −4 to −1.94 × 10 −4 m/hr. At the upstream high‐permeability site (SP‐6), seepage meter measurements captured both transient groundwater discharge during short measurement periods and sustained surface water intrusion during longer measurements. Darcy‐based estimates at this site consistently indicated intrusion, indicating that both methods showed the same flow direction during longer measurements. Consequently, Darcy‐based approaches may underestimate exchange fluxes under low‐permeability conditions. These findings suggest that short‐term monitoring is favorable for capturing immediate, transient flow dynamics, whereas extended continuous measurements help buffer short‐term fluctuations to provide a more representative estimate of daily integrated exchange. Ultimately, by establishing a methodological framework that accounts for localized riverbed heterogeneity, this study provides practical guidelines for optimizing field investigation strategies in complex riparian environments.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"5 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Generalized Unit Hydrograph Theory for Dynamic River Networks 动态河网的广义单位线理论

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2026wr043477

Gianluca Botter,Alice Andreanelli,Elena Bachini,Alessandro Cenzon,Nicola Durighetto

{"title":"A Generalized Unit Hydrograph Theory for Dynamic River Networks","authors":"Gianluca Botter,Alice Andreanelli,Elena Bachini,Alessandro Cenzon,Nicola Durighetto","doi":"10.1029/2026wr043477","DOIUrl":"https://doi.org/10.1029/2026wr043477","url":null,"abstract":"Abstract The instantaneous unit hydrograph (IUH) synthetically describes how effective rainfall is transformed into discharge at the catchment outlet. According to classical geomorphological theories, the IUH is regarded as a time‐invariant probability density function of watershed response times, an interpretation that implicitly postulates a fixed configuration of the channel network. However, river networks dynamically expand and contract, leading to systematic temporal variations in response times that challenge the foundations of standard IUH approaches. Here, we develop a generalized unit hydrograph theory that explicitly accounts for time‐varying river networks. The proposed framework introduces a dynamic formulation of the convolution relationship linking effective rainfall and streamflow, applicable when active network length varies during and across events. In this case, the rainfall–runoff kernel can be decomposed into two components: the classical IUH contribution evaluated on the instantaneous network configuration and an additional dynamic term capturing the effects of temporal changes in flowing stream length. Numerical applications show that, across the explored configurations, network dynamics reshape the hydrological response of catchments and the associated flow‐duration curves, in particular by increasing flood peaks and slowing down recessions. This pattern is confirmed by a proof‐of‐concept application to a monitored rainfall–runoff event in the Valfredda catchment (northeastern Italy), which achieved reasonably good performance and illustrates the potential of the proposed framework in real‐world settings. The proposed framework bridges classical unit hydrograph theory and empirical evidence on channel network dynamics, providing a new pathway for representing catchment functioning in hydrological models.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"87 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149210475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Big Data for Small Streams: Leveraging a Coarse National Model to Enhance Fine‐Resolution Stream Temperature Predictions 小溪的大数据：利用粗糙的国家模型来增强精细分辨率的河流温度预测

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2025wr041874

J. R. Barclay,L. E. Koenig,Y. Fan,X. Jia,A. Appling

{"title":"Big Data for Small Streams: Leveraging a Coarse National Model to Enhance Fine‐Resolution Stream Temperature Predictions","authors":"J. R. Barclay,L. E. Koenig,Y. Fan,X. Jia,A. Appling","doi":"10.1029/2025wr041874","DOIUrl":"https://doi.org/10.1029/2025wr041874","url":null,"abstract":"Abstract Predictive stream temperature models are commonly used to address spatial and temporal gaps in observational data because stream temperature information is essential for environmental management decisions. National models capture broad patterns driven by climate, topography, and seasonality, but often lack the spatial resolution to simulate fine‐scale variation in groundwater discharge, riparian shading, or tributary inflows. In contrast, watershed models may simulate finer‐resolution patterns but miss regional drivers or be limited by scarcity of observations. To generate watershed‐extent, fine‐resolution stream temperature predictions, we developed 18 multiscale machine‐learning models that leverage (a) a broad‐extent, coarse‐resolution stream temperature model and (b) finer‐resolution observations and predictor data. The coarse‐resolution model simulates daily stream temperature across the conterminous United States on the National Hydrologic Geospatial Fabric (13.7 km median reach length; 865,364 km total). The fine‐resolution models simulate daily stream temperature on the National Hydrography Dataset Plus version 2 (1.5 km median; 5,192,808 km total). We compared multiscale models to seven purely broad‐ (national) or watershed‐extent models, testing them in eight watersheds (436–985 km 2 ) with differing hydrologic settings and under realistic data availability scenarios. Especially when observations within a watershed were scarce, multiscale models generated more accurate predictions than national or watershed‐specific models. A recurrent graph convolution neural network pretrained on coarse predictions and fine‐tuned on watershed‐specific observations was most accurate across watersheds and data scenarios. These results highlight that leveraging both coarse, national results and watershed‐specific data can increase model accuracies, particularly when observations within a watershed are spatially or temporally limited.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"22 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149209167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Shear‐Thinning Rheology Reshapes Hydrodynamic Dispersion in Heterogeneous Fractures 剪切-减薄流变学重塑非均质裂缝的水动力分散

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2026wr044432

Chengkai Wang,Qiuheng Xie,Heping Xie,Senyou An

{"title":"Shear‐Thinning Rheology Reshapes Hydrodynamic Dispersion in Heterogeneous Fractures","authors":"Chengkai Wang,Qiuheng Xie,Heping Xie,Senyou An","doi":"10.1029/2026wr044432","DOIUrl":"https://doi.org/10.1029/2026wr044432","url":null,"abstract":"Abstract Hydrodynamic dispersion of shear‐thinning fluid in fractured rocks is jointly governed by fracture heterogeneity and fluid rheology, yet the way aperture correlation length alters dispersion mechanisms remains unclear. Here, we carry out pore‐scale lattice Boltzmann simulations to investigate fluid flow and solute transport in heterogeneous fractures with systematically varied aperture correlation lengths and injection velocities. The results show that aperture correlation length controls the basic transport pattern, with short correlation length leading to diffusive front spreading and long correlation length promoting channelized transport through persistent preferential pathways. Increasing injection velocity drives the transition from molecular diffusion to advective transport, in which the overall solute spreading reflects the competition between fracture‐plane geometrical dispersion and aperture‐scale shear dispersion. Shear‐thinning rheology reshapes this progression by enhancing fracture plane velocity heterogeneity while reducing aperture‐wise velocity gradients, thereby extending the role of geometrical dispersion and delaying the development of shear‐dispersion. Pore‐scale analysis further suggests that shear‐induced viscosity reduction promotes earlier eddy formation in stagnant zones and alters local mixing processes beyond purely diffusion‐controlled exchange. These findings provide a pore‐scale mechanistic explanation for the transition and reorganization of dispersion regimes in heterogeneous fractures.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"294 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Can Competition‐Based Programs Promote Conservation in Agriculture? Evidence From the “Most Crop per Drop” Contest 基于竞争的项目能促进农业保护吗？来自“每滴最多收成”竞赛的证据

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2025wr042868

Shahin Bahrami,Qiuqiong Huang,Christopher Henry,Rodolfo M. Nayga,Eva Stephani Caroline

引用次数: 0

Quantifying Vegetation Dependence on Groundwater: Evidence From Northern China's Drylands 植被对地下水依赖的量化：来自中国北方旱地的证据

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2025wr042844

Xing Li,Yong Wang,Yong Zhao,Jiaqi Zhai,Fan He,Yuan Liu,Jiaxin Li,Kuan Liu,Tao Wang,Minjian Chen

{"title":"Quantifying Vegetation Dependence on Groundwater: Evidence From Northern China's Drylands","authors":"Xing Li,Yong Wang,Yong Zhao,Jiaqi Zhai,Fan He,Yuan Liu,Jiaxin Li,Kuan Liu,Tao Wang,Minjian Chen","doi":"10.1029/2025wr042844","DOIUrl":"https://doi.org/10.1029/2025wr042844","url":null,"abstract":"Abstract Groundwater is a critical source for vegetation in drylands, yet the quantification of vegetation dependence on groundwater (VDG) remains underexplored. Understanding this dependence is essential for unraveling vegetation‐groundwater interactions and informing sustainable water resources management in drylands. This study constructed a vegetation response curve to depth to groundwater (DTG) by analyzing the relationship between DTG and the Normalized Difference Vegetation Index (NDVI) at the pixel scale. A new method was developed to quantify VDG from the fitted NDVI–DTG response curve, where VDG was defined as the rate of NDVI change per unit change in normalized DTG at the inflection point of the NDVI–DTG response curve. VDG values were obtained for nine representative arid, semi‐arid, and semi‐humid regions in northern China (with an annual precipitation gradient of 200–800 mm). VDG shows pronounced spatial variation across the nine regions, with mean values decreasing from approximately 1.28 in the driest region to approximately 0.24 in the wettest region along the precipitation gradient. A strong negative correlation between annual precipitation (P) and VDG was identified (VDG = 2.08e −0.0037P ), highlighting precipitation as a dominant regulator of VDG across regions. The research provides new empirical evidence for a deeper understanding of the effects of groundwater on vegetation, and also provides strong scientific support for groundwater management and ecological restoration with various annual precipitation amounts.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"26 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149150588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Structure–Function Coherent Coarsening for Cross‐Resolution Ecohydrological Modeling 交叉分辨率生态水文模型的结构-功能相干粗化

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2025wr042963

Long Jiang,Yang Yang,Morgan Thornwell,Robert McKane,Sonali Chokshi,Huanfeng Duan,Tiantian Yang,Hoshin Vijai Gupta

{"title":"Structure–Function Coherent Coarsening for Cross‐Resolution Ecohydrological Modeling","authors":"Long Jiang,Yang Yang,Morgan Thornwell,Robert McKane,Sonali Chokshi,Huanfeng Duan,Tiantian Yang,Hoshin Vijai Gupta","doi":"10.1029/2025wr042963","DOIUrl":"https://doi.org/10.1029/2025wr042963","url":null,"abstract":"Abstract Ecohydrological models are increasingly applied in regional scenario‐based studies, yet their cross‐resolution application remains constrained by high computational costs of fine‐resolution simulations and by structural inconsistencies introduced during scale transfer. We propose a Structure–Function Coherent Coarsening (SFCC) framework that improves the preservation of hydrological structure and functional heterogeneity during model input coarsening. Using the VELMA model in 24 subbasins of the Salish Sea Basin, USA, we evaluate coarsening strategies for three input types: (a) DEMs coarsened with a Hydro‐Aware approach that better preserves drainage topology; (b) land cover and soil type data sets coarsened with function‐preserving methods ( Auto‐Weight and Auto‐Reassign ) that retain small but process‐dominant classes; and (c) initial conditions coarsened with Hydro‐Aware , Landcover‐Aware , and Soil‐Aware strategies to improve temporal stability. Results show that the Hydro‐Aware method better preserves watershed morphology and yields more consistent runoff and nitrate loss predictions across resolutions than mean‐based coarsening. For categorical inputs, the function‐preserving methods can reduce the dominant‐class bias of majority aggregation, particularly in basins where small, high‐impact patches drive nitrogen export. Long‐term simulations show that hydrological variables stabilize quickly, whereas biogeochemical variables stabilize more slowly. In both cases, differences caused by coarsening decrease over time and eventually level off. This suggests that preserving both structural consistency and functional heterogeneity can help maintain stable model behavior over time. By operating directly at the data‐input level, SFCC improves integration of multi‐source data sets while retaining high‐resolution information. It supports cross‐scale simulation, calibration, and model integration, and provides a scalable foundation for regional scenario analysis.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"403 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

In the Age of AI—Are National Models and Data Sets Still Important for Stream Flow Prediction? 在人工智能时代，国家模型和数据集对河流流量预测仍然重要吗？

IF 5.4 1区地球科学

Water Resources Research Pub Date : 2026-10-01 DOI: 10.1029/2025wr042530

Brett Snider,Ehsan Roshani

{"title":"In the Age of AI—Are National Models and Data Sets Still Important for Stream Flow Prediction?","authors":"Brett Snider,Ehsan Roshani","doi":"10.1029/2025wr042530","DOIUrl":"https://doi.org/10.1029/2025wr042530","url":null,"abstract":"Abstract Accurate streamflow prediction is critical for effective water resource management, and recent advances in deep learning and multi‐basin data sets have significantly improved model skill. Global deep‐learning models, trained on thousands of catchments have demonstrated strong generalization across diverse climates and continents. However, these models rely solely on globally available meteorological inputs, potentially overlooking the value of nationally developed data sets with enhanced regional accuracy. In this study, we assess the benefit of using Canada's high‐resolution national reanalysis data set (CaSR) in long short‐term memory (LSTM) models for streamflow prediction. We compare model performance using different meteorological forcings, global (ERA5‐Land), continental (Daymet), national (CaSR), and a combined “Complete” model, across over 1,000 Canadian stream gauges. Model performance is evaluated using the Nash–Sutcliffe Efficiency (NSE), Kling‐Gupta Efficiency (KGE) and related metrics. We also benchmark our best‐performing model against Google's global LSTM streamflow model at 412 Canadian gauges. Results show that national‐scale deep‐learning models using CaSR outperforms deep‐learning models using only global or continental inputs. The Complete model achieved the highest performance, with a median KGE 0.886−exceeding the 0.839 achieved by Google's global model within Canada. These findings suggest that nationally trained models using a wide array of inputs, including national meteorological data sets, can outperform state‐of‐the‐art global deep‐learning models that do not use such data when applied within their region of origin. For countries with dense observational networks and distinct hydrological regimes, investing in national data sets and models can enhance deep‐learning model prediction accuracy, leading to improved resilience to climate extremes and local water management decisions.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"9 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149090717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0