Meteorological drought forecasting based on a statistical model with machine learning techniques in Shaanxi province, China

Drought is a major natural disaster that causes severe social and economic losses. The prediction of regional droughts may provide important information for drought preparedness and farm irrigation. The existing drought prediction models are mainly based on a single weather station. Efforts need to...

Full description

Saved in:

Bibliographic Details
Published in:	The Science of the total environment 2019-05, Vol.665, p.338-346
Main Authors:	Zhang, Rong, Chen, Zhao-Yue, Xu, Li-Jun, Ou, Chun-Quan
Format:	Article
Language:	eng
Subjects:	Distributed lag nonlinear model Drought prediction Shaanxi province XGBoost
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Drought is a major natural disaster that causes severe social and economic losses. The prediction of regional droughts may provide important information for drought preparedness and farm irrigation. The existing drought prediction models are mainly based on a single weather station. Efforts need to be taken to develop a new multistation-based prediction model. This study optimizes the predictor selection process and develops a new model to predict droughts using past drought index, meteorological measures and climate signals from 32 stations during 1961 to 2016 in Shaanxi province, China. We applied and compared two methods, including a cross-correlation function and a distributed lag nonlinear model (DLNM), in selecting the optimal predictors and specifying their lag time. Then, we built a DLNM, an artificial neural network model and an XGBoost model and compared their validations for predicting the Standardized Precipitation Evapotranspiration Index (SPEI) 1–6 months in advance. The DLNM was better than the cross-correlation function in predictor selection and lag effect determination. The XGBoost model more accurately predicted SPEI with a lead time of 1–6 months than the DLNM and the artificial neural network, with cross-validation R2 values of 0.68–0.82, 0.72–0.89, 0.81–0.92, and 0.84–0.95 at 3-, 6-, 9- and 12-month time scales, respectively. Moreover, the XGBoost model had the highest prediction accuracy for overall droughts (89%–97%) and for three specific drought categories (i.e., moderate, severe, and extreme) (76%–94%). This study offers a new modeling strategy for drought predictions based on multistation data. The incorporation of nonlinear and lag effects of predictors into the XGBoost method can significantly improve prediction accuracy of SPEI and drought. [Display omitted] •A new modeling strategy was developed to predict SPEI and droughts at 32 stations in Shaanxi province, China.•The distributed lag non-linear model outperformed CCF in selecting the optimal predictors and specifying their lag time.•XGBoost had better prediction accuracy for droughts with a lead time of 1-6 months (89%~97%) than ANN.
ISSN:	0048-9697 1879-1026