干旱区生态环境知识资源中心(Arid): A hybrid framework for forecasting monthly reservoir inflow based on machine learning techniques with dynamic climate forecasts, satellite-based data, and climate phenomenon information

Arid

DOI	10.1007/s00477-021-02023-y
	A hybrid framework for forecasting monthly reservoir inflow based on machine learning techniques with dynamic climate forecasts, satellite-based data, and climate phenomenon information
	Tian, Di; He, Xiaogang; Srivastava, Puneet; Kalin, Latif
通讯作者	Tian, D (corresponding author), Auburn Univ, Dept Crop Soil & Environm Sci, Auburn, AL 36849 USA.
来源期刊	STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
ISSN	1436-3240
EISSN	1436-3259
出版年	2021-04
英文摘要	In this study, we developed and evaluated a hybrid framework for reservoir inflow forecast. This framework is unprecedented, which integrates new quasi-globally available observation-, satellite-, or model-based datasets using machine learing models to forecast inflow at the local scale. Under this framework, we compared random forests, gradient boosting machine, extreme learning machine, M5-cubist, elastic net, as well as their multi-model ensemble using Bayesian model averaging (BMA), and tested contributions from different input datasets, including retrospective forecast (reforecast) from florecast oriented low ocean resolution (FLOR) dynamic climate model, satellite-based hydrologic products, and climate phenomenon information. The performance was evaluated using Kling-Gupta efficiency (KGE) and correlation coefficient (R) in two headwater reservoirs, Harris reservoir in the humid Alabama-Coosa-Tallapoosa river basin and the Navajo reservoir in the arid Upper Colorado River Basin (UCRB). The results showed that for the Harris reservoir, the BMA combining five models with antecedent inflow and satellite-based hydrologic information as model inputs provided the best performance (KGE = 0.66, R = 0.76). For the Navajo reservoir, the gradient boosting machine model with all variables combined as input showed the best performance (KGE = 0.76, R = 0.83). Satellite-based soil moisture and evaporation consistently showed significant contributions to the inflow forecast. Benefits from climate indices and FLOR reforecast varied by locations, with more benefits coming from climate indices than FLOR potential evaporation reforecast at the Navajo reservoir in UCRB. Given the global coverage of the model inputs, our approach can be potentially applicable to improve reservoir inflow forecasts in different regions of the world.
英文关键词	Reservoir inflow forecast Machine learning Dynamic climate forecast Climate indices Satellite-based soil moisture and evaporation Multi-model ensemble
类型	Article ; Early Access
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000642380800002
WOS类目	Engineering, Environmental ; Engineering, Civil ; Environmental Sciences ; Statistics & Probability ; Water Resources
WOS研究方向	Engineering ; Environmental Sciences & Ecology ; Mathematics ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/367508
作者单位	[Tian, Di] Auburn Univ, Dept Crop Soil & Environm Sci, Auburn, AL 36849 USA; [He, Xiaogang] Stanford Univ, Water West, Stanford, CA USA; [Srivastava, Puneet] Univ Maryland, Coll Agr & Nat Resources, College Pk, MD USA; [Kalin, Latif] Auburn Univ, Sch Forestry & Wildlife Sci, Auburn, AL USA
推荐引用方式 GB/T 7714	Tian, Di,He, Xiaogang,Srivastava, Puneet,et al. A hybrid framework for forecasting monthly reservoir inflow based on machine learning techniques with dynamic climate forecasts, satellite-based data, and climate phenomenon information[J],2021.
APA	Tian, Di,He, Xiaogang,Srivastava, Puneet,&Kalin, Latif.(2021).A hybrid framework for forecasting monthly reservoir inflow based on machine learning techniques with dynamic climate forecasts, satellite-based data, and climate phenomenon information.STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT.
MLA	Tian, Di,et al."A hybrid framework for forecasting monthly reservoir inflow based on machine learning techniques with dynamic climate forecasts, satellite-based data, and climate phenomenon information".STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT (2021).