globalchange  > 气候变化与战略
DOI: 10.5194/hess-23-5089-2019
论文题名:
Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets
作者: Kratzert F.; Klotz D.; Shalev G.; Klambauer G.; Hochreiter S.; Nearing G.
刊名: Hydrology and Earth System Sciences
ISSN: 1027-5606
出版年: 2019
卷: 23, 期:12
起始页码: 5089
结束页码: 5110
语种: 英语
Scopus关键词: Benchmarking ; Catchments ; Deep learning ; Large dataset ; Machine learning ; Runoff ; Benchmark models ; Data-driven approach ; Hydrological models ; Improve performance ; Learning models ; Rainfall-runoff modeling ; Short term memory ; Time-series data ; Long short-term memory ; catchment ; data set ; hydrological response ; machine learning ; rainfall-runoff modeling ; time series analysis
英文摘要: Regional rainfall-runoff modeling is an old but still mostly outstanding problem in the hydrological sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone. In this paper, we propose a novel, data-driven approach using Long Short-Term Memory networks (LSTMs) and demonstrate that under a "big data" paradigm, this is not necessarily the case. By training a single LSTM model on 531 basins from the CAMELS dataset using meteorological time series data and static catchment attributes, we were able to significantly improve performance compared to a set of several different hydrological benchmark models. Our proposed approach not only significantly outperforms hydrological models that were calibrated regionally, but also achieves better performance than hydrological models that were calibrated for each basin individually. Furthermore, we propose an adaption to the standard LSTM architecture, which we call an Entity-Aware-LSTM (EA-LSTM), that allows for learning catchment similarities as a feature layer in a deep learning model. We show that these learned catchment similarities correspond well to what we would expect from prior hydrological understanding. © 2019 Royal Society of Chemistry. All rights reserved.
Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/162832
Appears in Collections:气候变化与战略

Files in This Item:

There are no files associated with this item.


作者单位: Kratzert, F., LIT AI Lab and Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria; Klotz, D., LIT AI Lab and Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria; Shalev, G., Google Research, Tel Aviv, Israel; Klambauer, G., LIT AI Lab and Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria; Hochreiter, S., LIT AI Lab and Institute for Machine Learning, Johannes Kepler University Linz, Linz, Austria; Nearing, G., Department of Geological Sciences, University of Alabama, Tuscaloosa, AL, United States

Recommended Citation:
Kratzert F.,Klotz D.,Shalev G.,et al. Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets[J]. Hydrology and Earth System Sciences,2019-01-01,23(12)
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[Kratzert F.]'s Articles
[Klotz D.]'s Articles
[Shalev G.]'s Articles
百度学术
Similar articles in Baidu Scholar
[Kratzert F.]'s Articles
[Klotz D.]'s Articles
[Shalev G.]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[Kratzert F.]‘s Articles
[Klotz D.]‘s Articles
[Shalev G.]‘s Articles
Related Copyright Policies
Null
收藏/分享
所有评论 (0)
暂无评论
 

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.