Global S&T Development Trend Analysis Platform of Resources and Environment
DOI | 10.1029/2018WR024463 |
Prediction and Inference of Flow Duration Curves Using Multioutput Neural Networks | |
Worland, Scott. C.1,2; Steinschneider, Scott2; Asquith, William3; Knight, Rodney1; Wieczorek, Michael4 | |
2019-08-01 | |
发表期刊 | WATER RESOURCES RESEARCH |
ISSN | 0043-1397 |
EISSN | 1944-7973 |
出版年 | 2019 |
卷号 | 55期号:8页码:6850-6868 |
文章类型 | Article |
语种 | 英语 |
国家 | USA |
英文摘要 | We develop multioutput neural network models to predict flow-duration curves (FDCs) in 9,203 ungaged locations in the Southeastern United States for six decades between 1950 and 2009. The model architecture contains multiple response variables in the output layer that correspond to individual quantiles along the FDC. During training, predictions are made for each quantile, and a combined loss function is used for back propagation and parameter updating. The loss function accounts for the covariance between the quantiles and generates physically consistent outputs (i.e., monotonically increasing quantiles with increasing nonexceedance probabilities). We use neural network dropout to generate posterior-predictive distributions for FDCs and test model performance under cross validation. Finally, we demonstrate how local surrogate models, via the Local Interpretable Model-agnostic Explanations method, can be used to infer the relation between basin characteristics and the predicted FDCs. Results suggest that multioutput neural network models can learn the monotonic relations between adjacent quantiles on an FDC; they result in better predictions than single-output neural network models that predict each quantile independently, and basin characteristics are most useful for predicting smaller quantiles, whereas bias terms from neighboring quantiles are most informative for predicting higher quantiles. |
领域 | 资源环境 |
收录类别 | SCI-E |
WOS记录号 | WOS:000490973700028 |
WOS关键词 | REGIONAL PATTERNS ; PHYSICAL CONTROLS ; UNGAUGED SITES ; FREQUENCY-ANALYSIS ; UNREASONABLE EFFECTIVENESS ; DAILY STREAMFLOW ; REGIME CURVE ; MODEL ; FRAMEWORK ; RESPONSES |
WOS类目 | Environmental Sciences ; Limnology ; Water Resources |
WOS研究方向 | Environmental Sciences & Ecology ; Marine & Freshwater Biology ; Water Resources |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.173/C666/handle/2XK7JSWQ/185868 |
专题 | 资源环境科学 |
作者单位 | 1.US Geol Survey, Lower Mississippi Gulf Water Sci Ctr, Nashville, TN 37211 USA; 2.Cornell Univ, Dept Biol & Environm Engn, Ithaca, NY 14850 USA; 3.US Geol Survey, TexasWater Sci Ctr, Lubbock, TX USA; 4.US Geol Survey, MD DE DC Water Sci Ctr, Catonsville, MD USA |
推荐引用方式 GB/T 7714 | Worland, Scott. C.,Steinschneider, Scott,Asquith, William,et al. Prediction and Inference of Flow Duration Curves Using Multioutput Neural Networks[J]. WATER RESOURCES RESEARCH,2019,55(8):6850-6868. |
APA | Worland, Scott. C.,Steinschneider, Scott,Asquith, William,Knight, Rodney,&Wieczorek, Michael.(2019).Prediction and Inference of Flow Duration Curves Using Multioutput Neural Networks.WATER RESOURCES RESEARCH,55(8),6850-6868. |
MLA | Worland, Scott. C.,et al."Prediction and Inference of Flow Duration Curves Using Multioutput Neural Networks".WATER RESOURCES RESEARCH 55.8(2019):6850-6868. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论