气候变化领域集成服务门户(CCPortal): Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets

CCPortal

DOI	10.5194/hess-23-5089-2019
	Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets
	Kratzert F.; Klotz D.; Shalev G.; Klambauer G.; Hochreiter S.; Nearing G.
发表日期	2019
ISSN	1027-5606
起始页码	5089
结束页码	5110
卷号	23 期号:12
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.
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
来源期刊	Hydrology and Earth System Sciences
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/159542
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
推荐引用方式 GB/T 7714	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],2019,23(12).
APA	Kratzert F.,Klotz D.,Shalev G.,Klambauer G.,Hochreiter S.,&Nearing G..(2019).Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets.Hydrology and Earth System Sciences,23(12).
MLA	Kratzert F.,et al."Towards learning universal; regional; and local hydrological behaviors via machine learning applied to large-sample datasets".Hydrology and Earth System Sciences 23.12(2019).