Water Resources Research最新文献

{"title":"Aperture Field Anisotropy Control on Immiscible Displacement Patterns in Rough Fractures","authors":"Kun Xing, Xiaoqing Shi, Zhibing Yang, Xueyuan Kang, Siyuan Qiang, Jichun Wu","doi":"10.1029/2024wr038099","DOIUrl":"https://doi.org/10.1029/2024wr038099","url":null,"abstract":"Two-phase flow displacement in rock fractures is crucial for various subsurface mass transfer processes and engineering applications. In fractures, the displacement of a less viscous fluid by a more viscous one (<i>i</i>.<i>e</i>., viscosity ratio <i>M</i> &gt; 1) involves viscous forces help stabilizing the displacement front in presence of capillary pressure fluctuations. Although previous studies have reported displacement patterns in isotropic fractures, the impact of anisotropic fractures on displacement patterns has not been systematically examined. In this study, we conducted flow-rate-controlled drainage experiments to examine how anisotropic aperture fields affect displacement patterns. We observed the transition of displacement patterns from capillary fingering (CF) to crossover zone (CZ) to compact displacement pattern (CD) based on variations in transverse pore-filling event (TPFE) frequency, which characterizes the competition between capillary and viscous forces. Increasing aperture correlation length in the transverse direction leads to increased TPFE frequency at a low flow rate, destabilizing displacement front. While the increasing aperture correlation length in longitudinal direction suppressed TPFE frequency, stabilizing displacement front. Therefore, the critical capillary number (<i>Ca</i>_CF-CZ), which indicates the onset of the CF-CZ transition, decreases as the aperture field varies from transversely to longitudinally correlated. At high flow rates, TPFEs almost disappeared, indicating that anisotropy did not affect CZ-CD transition (<i>Ca</i>_CZ-CD). Furthermore, we modified theoretical models of <i>Ca</i>_CF-CZ and <i>Ca</i>_CZ-CD by incorporating the aperture anisotropy factor, achieving a good fit with the experimental data. This study demonstrates the critical role of aperture field anisotropy in controlling two-phase displacement patterns and provides a theoretical framework for predicting multiphase flow behavior in natural fractures.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"125 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142490678","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}

{"title":"Coupled Hydrogeophysical Modeling to Constrain Unsaturated Soil Parameters for a Slow-Moving Landslide","authors":"J. P. Boyd, J. E. Chambers, P. B. Wilkinson, P. I. Meldrum, E. Bruce, A. Binley","doi":"10.1029/2023wr036319","DOIUrl":"https://doi.org/10.1029/2023wr036319","url":null,"abstract":"Geophysical methods have proven to be useful for investigating unstable slopes as they are both non-invasive and sensitive to the spatial distribution of physical properties in the subsurface. Of particular interest are the links between electrical resistivity and near-surface moisture content; recent work has demonstrated that it is possible to calibrate hydrological models using geophysical measurements. In this study we explore the use of in-field electrical resistivity data for calibrating unsaturated soil retention parameters and saturated hydraulic conductivity used for modeling unsaturated fluid flow. We study a synthetic case study, and a well-characterized site in the northeast of England and develop an approach to calibrate retention parameters for a mudstone and a sandstone formation, the former being an actively failing unit. Petrophysical relationships between electrical resistivity and moisture content (or saturation) are established for both formations. 2D hydrological models are driven by effective rainfall estimations; subsequently these models are coupled with a geophysical forward model via a Markov chain Monte Carlo approach. For the synthetic case, we show that our modeling approach is sensitive to the moisture retention parameters, while less so to saturated hydraulic conductivity. We observe the same characteristics and sensitivities for the field case, albeit with a greater data misfit. Further hydrological simulations suggest that the slope retained high moisture contents in the months preceding a rotational failure. Therefore, we propose that coupled hydrological and geophysical modeling approaches could aid in enhancing landslide monitoring, modeling, and early warning efforts.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"31 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142490675","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}

{"title":"Seiche-Induced Fish Kills in the Sea of Galilee—A Possible Explanation for Biblical Miracles?","authors":"Yael Amitai, Ehud Strobach, David P. Hamilton, Shmuel Assouline, Ami Nishri, Tamar Zohary","doi":"10.1029/2024wr037894","DOIUrl":"https://doi.org/10.1029/2024wr037894","url":null,"abstract":"In Lake Kinneret (the biblical Sea of Galilee), Israel, internal waves of significant amplitude are induced by westerly winds. These waves give rise to upwelling into the surface mixed layer of colder, oxygen-depleted water from the hypolimnetic and metalimnetic layers. If upwelling occurs soon after the onset of annual thermal stratification, when surface mixed layer extends over a narrow depth range, but the hypolimnion is already anoxic, there is a potential for massive fish kills as fish cannot escape the anoxic water that intrudes into the surface mixed layer along the western shore. This study uses a coupled three-dimensional atmosphere-lake model to elucidate the mechanisms behind these infrequent major fish kills in Lake Kinneret. Remarkably, nowadays fish-kill events happen at the same location in the lake where the biblical <i>Miracle of Loaves and Fishes</i> and presumably the <i>Miraculous Catch of Fish</i> occurred two millennia before the present and may explain the appearance of large numbers of easy-to-collect fish close to the shore described in the biblical narratives.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"59 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142490089","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}

{"title":"The Cooling Effect of Oasis Reservoir-Riparian Forest Systems in Arid Regions","authors":"Yinying Jiao, Guofeng Zhu, Siyu Lu, Linlin Ye, Dongdong Qiu, Gaojia Meng, Qinqin Wang, Rui Li, Longhu Chen, Yuhao Wang, Dehong Si, Wentong Li","doi":"10.1029/2024wr038301","DOIUrl":"https://doi.org/10.1029/2024wr038301","url":null,"abstract":"In arid regions with limited water resources, numerous reservoirs have been built to support economic and social development. However, how the construction of reservoirs interacts with the surrounding ecosystem to affect temperature remains unclear. Spanning 2018 to 2022 in the Shiyang River Basin, we collected surface water and precipitation, as well as stem and soil samples. Using isotopic methods, we quantified how evaporation in the oasis reservoir-riparian forest system affects the local climate. Our findings show that the latent heat released by evapotranspiration from the reservoir and riparian forest system reduces the daily maximum temperature and daily temperature range by 7°C and 6°C respectively, compared to downstream areas with sparse vegetation around artificial lakes. Additionally, it enhances local moisture recycling, increasing precipitation. This study reveals regional cooling effect due to interactions between water bodies, the atmosphere, and vegetation. We propose that establishing reservoir-riparian forest systems can positively impact local climate regulation and serve as an effective strategy for adapting to global climate warming.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"109 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142488827","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}

{"title":"The Geometry of Flow: Advancing Predictions of River Geometry With Multi-Model Machine Learning","authors":"Shuyu Y. Chang, Zahra Ghahremani, Laura Manuel, Seyed Mohammad Hassan Erfani, Chaopeng Shen, Sagy Cohen, Kimberly J. Van Meter, Jennifer L. Pierce, Ehab A. Meselhe, Erfan Goharian","doi":"10.1029/2023wr036733","DOIUrl":"https://doi.org/10.1029/2023wr036733","url":null,"abstract":"Hydraulic geometry parameters describing river hydrogeomorphic relationships are critical for determining a channel's capacity to convey water and sediment which is important for flood forecasting. Although well-established, power-law hydraulic geometry curves have been widely used to understand riverine systems and mapping flooding inundation worldwide for the past 70 years, we have become increasingly aware of their limitations. In the present study, we have moved beyond these traditional power-law relationships, testing the ability of machine-learning models to provide improved predictions of river width and depth. For this work, we have used an unprecedentedly large river measurement data set (HYDRoSWOT) as well as a suite of watershed predictor data to develop novel data-driven approaches to better estimate river geometries over the contiguous United States (CONUS). Our Random Forest, XGBoost, and neural network models out-performed the traditional, regionalized power law-based hydraulic geometry equations for both width and depth, providing R-squared values of as high as 0.75 for width and as high as 0.67 for depth, compared with R-squared values of 0.45 for width and 0.18 for depth from the regional hydraulic geometry equations. Our results also show diverse performance outcomes across stream orders and geographical regions for the different machine-learning models, demonstrating the value of using multi-model approaches to maximize the predictability of river geometry. The developed models have been used to create the newly publicly available STREAM-geo data set, which provides river width, depth, width/depth ratio, and river and stream surface area (%RSSA) for nearly 2.7 million NHDPlus stream reaches across the contiguous US.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"194 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142488714","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}

{"title":"Bridging Hydrological Ensemble Simulation and Learning Using Deep Neural Operators","authors":"Alexander Y. Sun, Peishi Jiang, Pin Shuai, Xingyuan Chen","doi":"10.1029/2024wr037555","DOIUrl":"https://doi.org/10.1029/2024wr037555","url":null,"abstract":"Ensemble-based simulation and learning (ESnL) has long been used in hydrology for parameter inference, but computational demands of process-based ESnL can be quite high. To address this issue, we propose a deep neural operator learning approach. Neural operators are generic machine learning algorithms that can learn functional mappings between infinite-dimensional spaces, providing a highly flexible tool for scientific machine learning. Our approach is built upon DeepONet, a specific deep neural operator, and is designed to address several common problems in hydrology, namely, model parameter estimation, prediction at ungaged locations, and uncertainty quantification. Here we demonstrate the effectiveness of our DeepONet-based workflow using an existing large model ensemble created for an eastern U.S. watershed that is instrumented with 10 streamflow gages. Results suggest DeepONet achieves high efficiency in learning an ML surrogate model from the model ensemble, with the modified Kling-Gupta Efficiency exceeding 0.9 on holdout test sets. Parameter inference, carried out using the trained DeepONet surrogate model and genetic algorithm, also yields robust results. Additionally, we formulate and train a separate DeepONet model for physics-informed, seq-to-seq streamflow forecasting, which further reduces biases in the pre-trained DeepONet surrogate model. While this study focuses primarily on a single watershed, our approach is general and may be extended to enable learning from model ensembles across multiple basins or models. Thus, this research represents a significant contribution to the application of hybrid machine learning in hydrology.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"109 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487698","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}

{"title":"Sediment Transport and Flood Risk: Impact of Newly Constructed Embankments on River Morphology and Flood Dynamics in Kathmandu, Nepal","authors":"Saraswati Thapa, Hugh D. Sinclair, Maggie J. Creed, Alistair G. L. Borthwick, C. Scott Watson, Manoranjan Muthusamy","doi":"10.1029/2024wr037742","DOIUrl":"https://doi.org/10.1029/2024wr037742","url":null,"abstract":"Floodplain encroachment by embankments heightens flood risk. This is exacerbated by climate change and land-use modifications. This paper assesses the impact of embankments on sediment transport, channel geometry, conveyance capacity, and flood inundation of a reach of the Nakkhu River, Nepal. Using the CAESAR-Lisflood landscape evolution model based on a 2-m digital elevation model, we simulate four flood scenarios with and without embankments and sediment transport: a historical 25-year return period flood event used to design the embankments, 50-year, 100-year, and 1000-year return period flood events forecast using the Generalized Logistic Model (using data from 1992 to 2017). Our results indicate that flow confinement by embankments reduces inundation by 99% (from 22.5 to 0.3 ha) for the historical 25-year flood discharge of 42.23 &lt;span data-altimg=\"/cms/asset/e8aa5bf6-5a8c-4281-ae9f-df9d782c62f2/wrcr27519-math-0001.png\"&gt;&lt;/span&gt;&lt;mjx-container ctxtmenu_counter=\"85\" ctxtmenu_oldtabindex=\"1\" jax=\"CHTML\" role=\"application\" sre-explorer- style=\"font-size: 103%; position: relative;\" tabindex=\"0\"&gt;&lt;mjx-math aria-hidden=\"true\" location=\"graphic/wrcr27519-math-0001.png\"&gt;&lt;mjx-semantics&gt;&lt;mjx-mrow data-semantic-children=\"2,4\" data-semantic-content=\"3\" data-semantic- data-semantic-role=\"division\" data-semantic-speech=\"normal m cubed divided by normal s\" data-semantic-type=\"infixop\"&gt;&lt;mjx-msup data-semantic-children=\"0,1\" data-semantic- data-semantic-parent=\"5\" data-semantic-role=\"latinletter\" data-semantic-type=\"superscript\"&gt;&lt;mjx-mi data-semantic-annotation=\"clearspeak:simple\" data-semantic-font=\"normal\" data-semantic- data-semantic-parent=\"2\" data-semantic-role=\"latinletter\" data-semantic-type=\"identifier\"&gt;&lt;mjx-c&gt;&lt;/mjx-c&gt;&lt;/mjx-mi&gt;&lt;mjx-script style=\"vertical-align: 0.363em;\"&gt;&lt;mjx-mn data-semantic-annotation=\"clearspeak:simple\" data-semantic-font=\"normal\" data-semantic- data-semantic-parent=\"2\" data-semantic-role=\"integer\" data-semantic-type=\"number\" size=\"s\"&gt;&lt;mjx-c&gt;&lt;/mjx-c&gt;&lt;/mjx-mn&gt;&lt;/mjx-script&gt;&lt;/mjx-msup&gt;&lt;mjx-mo data-semantic- data-semantic-operator=\"infixop,/\" data-semantic-parent=\"5\" data-semantic-role=\"division\" data-semantic-type=\"operator\" rspace=\"1\" space=\"1\"&gt;&lt;mjx-c&gt;&lt;/mjx-c&gt;&lt;/mjx-mo&gt;&lt;mjx-mi data-semantic-annotation=\"clearspeak:simple\" data-semantic-font=\"normal\" data-semantic- data-semantic-parent=\"5\" data-semantic-role=\"latinletter\" data-semantic-type=\"identifier\"&gt;&lt;mjx-c&gt;&lt;/mjx-c&gt;&lt;/mjx-mi&gt;&lt;/mjx-mrow&gt;&lt;/mjx-semantics&gt;&lt;/mjx-math&gt;&lt;mjx-assistive-mml display=\"inline\" unselectable=\"on\"&gt;&lt;math altimg=\"urn:x-wiley:00431397:media:wrcr27519:wrcr27519-math-0001\" display=\"inline\" location=\"graphic/wrcr27519-math-0001.png\" xmlns=\"http://www.w3.org/1998/Math/MathML\"&gt;&lt;semantics&gt;&lt;mrow data-semantic-=\"\" data-semantic-children=\"2,4\" data-semantic-content=\"3\" data-semantic-role=\"division\" data-semantic-speech=\"normal m cubed divided by normal s\" data-semantic-type=\"infixop\"&gt;&lt;msup data-semantic-=\"\" data-semantic-children=\"0,1\" data-semantic-parent=\"5\" data-semantic-role=","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"21 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142486402","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}

{"title":"Quantifying the Wind-Induced Bias of Rainfall Measurements for the Thies CLIMA Optical Disdrometer","authors":"E. Chinchella, A. Cauteruccio, L. G. Lanza","doi":"10.1029/2024wr037366","DOIUrl":"https://doi.org/10.1029/2024wr037366","url":null,"abstract":"The wind-induced bias of rainfall measurements obtained from non-catching instruments is addressed in this work with reference to the Laser Precipitation Monitor (LPM) optical disdrometer manufactured by Thies CLIMA. A numerical simulation approach is adopted to quantify the expected bias, involving three different models with increasing complexity. Computational Fluid-Dynamics simulation of the airflow field around the instrument with an embedded Lagrangian particle-tracking module to obtain raindrop trajectories are performed by solving the Unsteady Reynolds Averaged Navier-Stokes (URANS) equations and a Large Eddy Simulation (LES) model. URANS-uncoupled, LES-uncoupled, and LES-coupled approaches are tested to assess the impact of modeling the airflow turbulent fluctuations in detail. Due to the non-radially symmetric external shape of the instrument, various combinations of the wind speed and direction are considered. Catch ratios for monodisperse rain are obtained as a function of the particle Reynolds number and the wind direction and fitted to obtain site-independent curves to support application of the simulation results. Based on literature expressions to link the drop size distribution of real rainfall events with the rainfall intensity (which instead depend on the local rainfall climatology at the measurement site), sample collection efficiency curves are obtained from the catch ratios of monodisperse rain. The resulting adjustment curves allow rainfall measurements to be corrected using either a real-time or post-processing approach. However, at high wind speed and assuming that the wind blows parallel to the instrument sensing area, the instrument may fail to report precipitation altogether.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"194 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142486403","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}

{"title":"Constructing Long-Term Hydrographs for River Climate-Resilience: A Novel Approach for Studying Centennial to Millennial River Behavior","authors":"Mohamed M. Fathi, Virginia Smith, Ayman G. Awadallah, Anjali M. Fernandes, Michael T. Hren, Dennis O. Terry","doi":"10.1029/2024wr037666","DOIUrl":"https://doi.org/10.1029/2024wr037666","url":null,"abstract":"Studying the centennial or millennial timescale response of large rivers to changing patterns in precipitation, discharge, flood intensity and recurrence, and associated sediment erosion is critical for understanding long-term fluvial geomorphic adjustment to climate. Long hydrographs, maintaining reliable Flow Duration Curves (FDCs), are a fundamental input for such simulations; however, recorded discharge series rarely span more than a few decades. The absence of robust methodologies for generating representative long-term hydrographs, especially those incorporating coarse temporal resolution or lacking continuous simulations, is therefore a fundamental challenge for climate resilience. We present a novel approach for constructing multi-century hydrographs that successfully conserve the statistical, especially frequency analysis, and stochastic characteristics of observed hydrographs. This approach integrates a powerful combination of a weather generator with a fine disaggregation technique and a continuous rainfall-runoff transformation model. We tested our approach to generate a statistically representative 300-year hydrograph on the Ninnescah River Basin in Kansas, using a satellite precipitation data set to address the considerable gaps in the available hourly observed data sets. This approach emphasizes the similarities of FDCs between the observed and generated hydrographs, exhibiting a reasonably acceptable range of average absolute deviation between 6% and 18%. We extended this methodology to create projected high-resolution hydrographs based on a range of climate change scenarios. The projected outcomes present pronounced increases in the FDCs compared to the current condition, especially for more distant futures, which necessitates more efficient adaptation strategies. This approach represents a paradigm shift in long-term hydrologic modeling.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"1 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142451918","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}

{"title":"Physics-Informed Neural Networks for the Augmented System of Shallow Water Equations With Topography","authors":"Susanna Dazzi","doi":"10.1029/2023wr036589","DOIUrl":"https://doi.org/10.1029/2023wr036589","url":null,"abstract":"Physics-informed neural networks (PINNs) are gaining attention as an alternative approach to solve scientific problems governed by differential equations. This work aims at assessing the effectiveness of PINNs to solve a set of partial differential equations for which this method has never been considered, namely the augmented shallow water equations (SWEs) with topography. Differently from traditional SWEs, the bed elevation is considered as an additional conserved variable, and therefore one more equation expressing the fixed-bed condition is included in the system. This approach allows the PINN model to leverage automatic differentiation to compute the bed slopes by learning the topographical information during training. PINNs are here tested for different one-dimensional cases with non-flat topography, and results are compared with analytical solutions. Though some limitations can be highlighted, PINNs show a good accuracy for the depth and velocity predictions even in the presence of non-horizontal bottom. The solution of the augmented system of SWEs can therefore be regarded as a suitable alternative strategy to deal with flows over complex topography using PINNs, also in view of future extensions to realistic problems.","PeriodicalId":23799,"journal":{"name":"Water Resources Research","volume":"12 1","pages":""},"PeriodicalIF":5.4,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142448477","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}