An artificial neural network emulator of the rangeland hydrology and erosion model

作     者：Mahmoud Saeedimoghaddam Grey Nearing Mariano Hernandez Mark A.Nearing David C.Goodrich Loretta J.Metz Mahmoud Saeedimoghaddam;Grey Nearing;Mariano Hernandez;Mark A.Nearing;David C.Goodrich;Loretta J.Metz

作者机构：Department of LandAir&Water ResourcesUniversity of CaliforniaDavisCAUSA Google ResearchMountain ViewCAUSA USDA-Agricultural Research ServiceSouthwest Watershed Research CenterTucsonAZUSA USDA-NRCS Resource Inventory and Assessment DivisionxoCEAP-Grazing LandsTucsonAZUSA 

出 版 物：《International Soil and Water Conservation Research》 (国际水土保持研究（英文）)

年 卷 期：2024年第12卷第2期

页      面：241-257页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 082804[工学-农业电气化与自动化] 081104[工学-模式识别与智能系统] 08[工学] 0828[工学-农业工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the U.S.Department of Agriculture Natural Resources Conservation Service Conservation Effects Assessment Project(CEAP)Grazing Lands Component under agreement number NR193A750007C002 

主　　题：RHEM Sediment yield Soil loss Runoff Deep learning 

摘      要：Machine learning(ML)is becoming an ever more important tool in hydrologic *** studies have shown the higher prediction accuracy of those ML models over traditional process-based ***,there is another advantage of ML which is its lower computational *** is important for the applications such as hydraulic soil erosion estimation over a large area and at a finer spatial *** traditional models like Rangeland Hydrology and Erosion Model(RHEM)requires too much computation time and *** this study,we designed an Artificial Neural Network that is able to recreate the RHEM outputs(annual average runoff,soil loss,and sediment yield and not the daily storm event-based values)with high accuracy(Nash-Sutcliffe Efficiency≈1.0)and a very low computational time(13 billion times faster on average using a GPU).We ran the RHEM for more than a million synthetic scenarios and train the Emulator with *** also,fine-tuned the trained Emulator with the RHEM runs of the real-world scenarios(more than 32,000)so the Emulator remains comprehensive while it works specifically accurately for the real-world *** also showed that the sensitivity of the Emulator to the input variables is similar to the RHEM and it can effectively capture the changes in the RHEM outputs when an input variable ***,the dynamic prediction behavior of the Emulator is statistically similar to the RHEM.