Global S&T Development Trend Analysis Platform of Resources and Environment
DOI | 10.1029/2019WR026065 |
Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning | |
Kratzert, Frederik1,2; Klotz, Daniel1,2; Herrnegger, Mathew3; Sampson, Alden K.4; Hochreiter, Sepp1,2; Nearing, Grey S.5 | |
2019-12-23 | |
发表期刊 | WATER RESOURCES RESEARCH
![]() |
ISSN | 0043-1397 |
EISSN | 1944-7973 |
出版年 | 2019 |
卷号 | 55期号:12页码:11344-11354 |
文章类型 | Article |
语种 | 英语 |
国家 | Austria; USA |
英文摘要 | Long short-term memory (LSTM) networks offer unprecedented accuracy for prediction in ungauged basins. We trained and tested several LSTMs on 531 basins from the CAMELS data set using k-fold validation, so that predictions were made in basins that supplied no training data. The training and test data set included similar to 30 years of daily rainfall-runoff data from catchments in the United States ranging in size from 4 to 2,000 km(2) with aridity index from 0.22 to 5.20, and including 12 of the 13 IGPB vegetated land cover classifications. This effectively "ungauged" model was benchmarked over a 15-year validation period against the Sacramento Soil Moisture Accounting (SAC-SMA) model and also against the NOAA National Water Model reanalysis. SAC-SMA was calibrated separately for each basin using 15 years of daily data. The out-of-sample LSTM had higher median Nash-Sutcliffe Efficiencies across the 531 basins (0.69) than either the calibrated SAC-SMA (0.64) or the National Water Model (0.58). This indicates that there is (typically) sufficient information in available catchment attributes data about similarities and differences between catchment-level rainfall-runoff behaviors to provide out-of-sample simulations that are generally more accurate than current models under ideal (i.e., calibrated) conditions. We found evidence that adding physical constraints to the LSTM models might improve simulations, which we suggest motivates future research related to physics-guided machine learning. |
英文关键词 | prediction in ungauged basins machine learning CAMELS LSTM |
领域 | 资源环境 |
收录类别 | SCI-E |
WOS记录号 | WOS:000503924400001 |
WOS关键词 | SOIL-MOISTURE ; DATA SET ; BENCHMARKING ; SIMULATION ; TIME |
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/224001 |
专题 | 资源环境科学 |
作者单位 | 1.Johannes Kepler Univ Linz, LIT AI Lab, Linz, Austria; 2.Johannes Kepler Univ Linz, Inst Machine Learning, Linz, Austria; 3.Univ Nat Resources & Life Sci, Inst Hydrol & Water Management, Vienna, Austria; 4.Natel Energy Inc, Upstream Tech, Alameda, CA USA; 5.Univ Alabama, Dept Geol Sci, Tuscaloosa, AL 35487 USA |
推荐引用方式 GB/T 7714 | Kratzert, Frederik,Klotz, Daniel,Herrnegger, Mathew,et al. Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning[J]. WATER RESOURCES RESEARCH,2019,55(12):11344-11354. |
APA | Kratzert, Frederik,Klotz, Daniel,Herrnegger, Mathew,Sampson, Alden K.,Hochreiter, Sepp,&Nearing, Grey S..(2019).Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning.WATER RESOURCES RESEARCH,55(12),11344-11354. |
MLA | Kratzert, Frederik,et al."Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning".WATER RESOURCES RESEARCH 55.12(2019):11344-11354. |
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