FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309857501> ?p ?o ?g. }

• W4309857501 abstract "Watershed models such as the Soil and Water Assessment Tool (SWAT) consist of high-dimensional physical and empirical parameters. These parameters often need to be estimated/calibrated through inverse modeling to produce reliable predictions on hydrological fluxes and states. Existing parameter estimation methods can be time consuming, inefficient, and computationally expensive for high-dimensional problems. In this paper, we present an accurate and robust method to calibrate the SWAT model (i.e., 20 parameters) using scalable deep learning (DL). We developed inverse models based on convolutional neural networks (CNN) to assimilate observed streamflow data and estimate the SWAT model parameters. Scalable hyperparameter tuning is performed using high-performance computing resources to identify the top 50 optimal neural network architectures. We used ensemble SWAT simulations to train, validate, and test the CNN models. We estimated the parameters of the SWAT model using observed streamflow data and assessed the impact of measurement errors on SWAT model calibration. We tested and validated the proposed scalable DL methodology on the American River Watershed, located in the Pacific Northwest-based Yakima River basin. Our results show that the CNN-based calibration is better than two popular parameter estimation methods (i.e., the generalized likelihood uncertainty estimation [GLUE] and the dynamically dimensioned search [DDS], which is a global optimization algorithm). For the set of parameters that are sensitive to the observations, our proposed method yields narrower ranges than the GLUE method but broader ranges than values produced using the DDS method within the sampling range even under high relative observational errors. The SWAT model calibration performance using the CNNs, GLUE, and DDS methods are compared using R 2 and a set of efficiency metrics, including Nash-Sutcliffe, logarithmic Nash-Sutcliffe, Kling-Gupta, modified Kling-Gupta, and non-parametric Kling-Gupta scores, computed on the observed and simulated watershed responses. The best CNN-based calibrated set has scores of 0.71, 0.75, 0.85, 0.85, 0.86, and 0.91. The best DDS-based calibrated set has scores of 0.62, 0.69, 0.8, 0.77, 0.79, and 0.82. The best GLUE-based calibrated set has scores of 0.56, 0.58, 0.71, 0.7, 0.71, and 0.8. The scores above show that the CNN-based calibration leads to more accurate low and high streamflow predictions than the GLUE and DDS sets. Our research demonstrates that the proposed method has high potential to improve our current practice in calibrating large-scale integrated hydrologic models." @default.
• W4309857501 created "2022-11-29" @default.
• W4309857501 creator A5026692271 @default.
• W4309857501 creator A5060765277 @default.
• W4309857501 creator A5067616792 @default.
• W4309857501 creator A5079873685 @default.
• W4309857501 creator A5081814832 @default.
• W4309857501 date "2022-11-24" @default.
• W4309857501 modified "2023-10-14" @default.
• W4309857501 title "Scalable deep learning for watershed model calibration" @default.
• W4309857501 cites W1512208174 @default.
• W4309857501 cites W1535215576 @default.
• W4309857501 cites W1552154048 @default.
• W4309857501 cites W1590485829 @default.
• W4309857501 cites W1826204440 @default.
• W4309857501 cites W1840669069 @default.
• W4309857501 cites W1919296332 @default.
• W4309857501 cites W1968073579 @default.
• W4309857501 cites W1982125139 @default.
• W4309857501 cites W1990471334 @default.
• W4309857501 cites W1996985196 @default.
• W4309857501 cites W1999070801 @default.
• W4309857501 cites W2008179957 @default.
• W4309857501 cites W2009104157 @default.
• W4309857501 cites W2014017508 @default.
• W4309857501 cites W2020282148 @default.
• W4309857501 cites W2031471061 @default.
• W4309857501 cites W2034564799 @default.
• W4309857501 cites W2040285311 @default.
• W4309857501 cites W2054137409 @default.
• W4309857501 cites W2058998445 @default.
• W4309857501 cites W2059646894 @default.
• W4309857501 cites W2075581597 @default.
• W4309857501 cites W2076063813 @default.
• W4309857501 cites W2088081764 @default.
• W4309857501 cites W2093625674 @default.
• W4309857501 cites W2094809497 @default.
• W4309857501 cites W2121032760 @default.
• W4309857501 cites W2122315938 @default.
• W4309857501 cites W2126171847 @default.
• W4309857501 cites W2129924324 @default.
• W4309857501 cites W2157098139 @default.
• W4309857501 cites W2171366295 @default.
• W4309857501 cites W2263824596 @default.
• W4309857501 cites W2292058934 @default.
• W4309857501 cites W2467894822 @default.
• W4309857501 cites W2511016831 @default.
• W4309857501 cites W2569457803 @default.
• W4309857501 cites W2619857189 @default.
• W4309857501 cites W2739323338 @default.
• W4309857501 cites W2744788756 @default.
• W4309857501 cites W2770694866 @default.
• W4309857501 cites W2791777345 @default.
• W4309857501 cites W2792356241 @default.
• W4309857501 cites W2803801393 @default.
• W4309857501 cites W2880123591 @default.
• W4309857501 cites W2900581768 @default.
• W4309857501 cites W2962949934 @default.
• W4309857501 cites W2969497280 @default.
• W4309857501 cites W2977666392 @default.
• W4309857501 cites W2983753125 @default.
• W4309857501 cites W2985691770 @default.
• W4309857501 cites W2986457312 @default.
• W4309857501 cites W2996139122 @default.
• W4309857501 cites W2997655715 @default.
• W4309857501 cites W3000750253 @default.
• W4309857501 cites W3017246359 @default.
• W4309857501 cites W3041133507 @default.
• W4309857501 cites W3047335959 @default.
• W4309857501 cites W3084210213 @default.
• W4309857501 cites W3085796979 @default.
• W4309857501 cites W3092026988 @default.
• W4309857501 cites W3094518900 @default.
• W4309857501 cites W3106370744 @default.
• W4309857501 cites W3108531389 @default.
• W4309857501 cites W3113930266 @default.
• W4309857501 cites W3115713842 @default.
• W4309857501 cites W3119485096 @default.
• W4309857501 cites W3126492974 @default.
• W4309857501 cites W3128133613 @default.
• W4309857501 cites W3158113899 @default.
• W4309857501 cites W3160258528 @default.
• W4309857501 cites W3161804994 @default.
• W4309857501 cites W3206853999 @default.
• W4309857501 cites W3207392840 @default.
• W4309857501 cites W4229658977 @default.
• W4309857501 cites W4242163971 @default.
• W4309857501 cites W4245494944 @default.
• W4309857501 cites W4289885559 @default.
• W4309857501 cites W4297988814 @default.
• W4309857501 doi "https://doi.org/10.3389/feart.2022.1026479" @default.
• W4309857501 hasPublicationYear "2022" @default.
• W4309857501 type Work @default.
• W4309857501 citedByCount "0" @default.
• W4309857501 crossrefType "journal-article" @default.
• W4309857501 hasAuthorship W4309857501A5026692271 @default.
• W4309857501 hasAuthorship W4309857501A5060765277 @default.
• W4309857501 hasAuthorship W4309857501A5067616792 @default.
• W4309857501 hasAuthorship W4309857501A5079873685 @default.
• W4309857501 hasAuthorship W4309857501A5081814832 @default.

• next