Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China
Reliable drought prediction plays a significant role in drought management. Applying machine learning models in drought prediction is getting popular in recent years, but applying the stand-alone models to capture the feature information is not sufficient enough, even though the general performance...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IWA Publishing
2023-06-01
|
Series: | Water Science and Technology |
Subjects: | |
Online Access: | http://wst.iwaponline.com/content/87/11/2756 |
_version_ | 1797782962743279616 |
---|---|
author | Shaoxuan Li Jiancang Xie Xue Yang Xin Jing |
author_facet | Shaoxuan Li Jiancang Xie Xue Yang Xin Jing |
author_sort | Shaoxuan Li |
collection | DOAJ |
description | Reliable drought prediction plays a significant role in drought management. Applying machine learning models in drought prediction is getting popular in recent years, but applying the stand-alone models to capture the feature information is not sufficient enough, even though the general performance is acceptable. Therefore, the scholars tried the signal decomposition algorithm as a data pre-processing tool, and coupled it with the stand-alone model to build ‘decomposition-prediction’ model to improve the performance. Considering the limitations of using the single decomposition algorithm, an ‘integration-prediction’ model construction method is proposed in this study, which deeply combines the results of multiple decomposition algorithms. The model tested three meteorological stations in Guanzhong, Shaanxi Province, China, where the short-term meteorological drought is predicted from 1960 to 2019. The meteorological drought index selects the Standardized Precipitation Index on a 12-month time scale (SPI-12). Compared with stand-alone models and ‘decomposition-prediction’ models, the ‘integration-prediction’ models present higher prediction accuracy, smaller prediction error and better stability in the results. This new ‘integration-prediction’ model provides attractive value for drought risk management in arid regions.
HIGHLIGHTS
Machine learning model has great value in short-term meteorological drought prediction.;
Signal decomposition algorithm as a data pre-processing tool can significantly improve the prediction performance of machine learning model.;
Deeply combining the results of multiple decomposition algorithms could achieve higher prediction accuracy.;
The ‘integration-prediction’ model provides a new way for drought prediction in arid regions.; |
first_indexed | 2024-03-13T00:19:22Z |
format | Article |
id | doaj.art-6f3e805b07044de5a6e1af13f6490029 |
institution | Directory Open Access Journal |
issn | 0273-1223 1996-9732 |
language | English |
last_indexed | 2024-03-13T00:19:22Z |
publishDate | 2023-06-01 |
publisher | IWA Publishing |
record_format | Article |
series | Water Science and Technology |
spelling | doaj.art-6f3e805b07044de5a6e1af13f64900292023-07-11T16:43:35ZengIWA PublishingWater Science and Technology0273-12231996-97322023-06-0187112756277510.2166/wst.2023.162162Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, ChinaShaoxuan Li0Jiancang Xie1Xue Yang2Xin Jing3 State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi 710048, China State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi 710048, China State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi 710048, China State Key Laboratory of Eco-hydraulics in Northwest Arid Region, Xi'an University of Technology, Xi'an, Shaanxi 710048, China Reliable drought prediction plays a significant role in drought management. Applying machine learning models in drought prediction is getting popular in recent years, but applying the stand-alone models to capture the feature information is not sufficient enough, even though the general performance is acceptable. Therefore, the scholars tried the signal decomposition algorithm as a data pre-processing tool, and coupled it with the stand-alone model to build ‘decomposition-prediction’ model to improve the performance. Considering the limitations of using the single decomposition algorithm, an ‘integration-prediction’ model construction method is proposed in this study, which deeply combines the results of multiple decomposition algorithms. The model tested three meteorological stations in Guanzhong, Shaanxi Province, China, where the short-term meteorological drought is predicted from 1960 to 2019. The meteorological drought index selects the Standardized Precipitation Index on a 12-month time scale (SPI-12). Compared with stand-alone models and ‘decomposition-prediction’ models, the ‘integration-prediction’ models present higher prediction accuracy, smaller prediction error and better stability in the results. This new ‘integration-prediction’ model provides attractive value for drought risk management in arid regions. HIGHLIGHTS Machine learning model has great value in short-term meteorological drought prediction.; Signal decomposition algorithm as a data pre-processing tool can significantly improve the prediction performance of machine learning model.; Deeply combining the results of multiple decomposition algorithms could achieve higher prediction accuracy.; The ‘integration-prediction’ model provides a new way for drought prediction in arid regions.;http://wst.iwaponline.com/content/87/11/2756‘integration-prediction’ modelmachine learningmeteorological drought predictionsignal decomposition algorithmspi |
spellingShingle | Shaoxuan Li Jiancang Xie Xue Yang Xin Jing Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China Water Science and Technology ‘integration-prediction’ model machine learning meteorological drought prediction signal decomposition algorithm spi |
title | Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China |
title_full | Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China |
title_fullStr | Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China |
title_full_unstemmed | Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China |
title_short | Comparison of hybrid machine learning models to predict short-term meteorological drought in Guanzhong region, China |
title_sort | comparison of hybrid machine learning models to predict short term meteorological drought in guanzhong region china |
topic | ‘integration-prediction’ model machine learning meteorological drought prediction signal decomposition algorithm spi |
url | http://wst.iwaponline.com/content/87/11/2756 |
work_keys_str_mv | AT shaoxuanli comparisonofhybridmachinelearningmodelstopredictshorttermmeteorologicaldroughtinguanzhongregionchina AT jiancangxie comparisonofhybridmachinelearningmodelstopredictshorttermmeteorologicaldroughtinguanzhongregionchina AT xueyang comparisonofhybridmachinelearningmodelstopredictshorttermmeteorologicaldroughtinguanzhongregionchina AT xinjing comparisonofhybridmachinelearningmodelstopredictshorttermmeteorologicaldroughtinguanzhongregionchina |