气候变化领域集成服务门户(CCPortal): Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index

CCPortal

DOI	10.1007/s11269-023-03440-0
	Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index
	Pande, Chaitanya B.; Kushwaha, N. L.; Orimoloye, Israel R.; Kumar, Rohitashw; Abdo, Hazem Ghassan; Tolche, Abebe Debele; Elbeltagi, Ahmed
发表日期	2023
ISSN	0920-4741
EISSN	1573-1650
起始页码	1367
结束页码	1399
卷号	37 期号:3
英文摘要	This paper focus on the drought monitoring and forecasting for semi-arid region based on the various machine learning models and SPI index. Drought phenomena are crucial role in the agriculture and drinking purposes in the area. In this study, Standardized Precipitation Index (SPI) was used to predicted the future drought in the upper Godavari River basin, India. We have selected the ten input combinations of ML model were used to prediction of drought for three SPI timescales (i.e., SPI -3, SPI-6, and SPI-12). The historical data of SPI from 2000 to 2019 was used for creation of ML models SPI prediction, these datasets was divided into training (75% of the data) and testing (25% of the data) models. The best subset regression method and sensitivity analysis were applied to estimate the most effective input variables for estimation of SPI 3, 6, and 12. The improved support vector machine model using sequential minimal optimization (SVM-SMO) with various kernel functions i.e., SMO-SVM poly kernel, SMO-SVM Normalized poly kernel, SMO-SVM PUK (Pearson Universal Kernel) and SMO-SVM RBF (radial basis function) kernel was developed to forecasting of the SPI-3,6 and 12 months. The ML models accuracy were compared with various statistical indicators i.e., root mean square error (RMSE), mean absolute error (MAE), relative absolute error (RAE), root relative squared error (RRSE), and correlation coefficient (r). The results of study area have been showed that the SMO-SVM poly kernel model precisely predicted the SPI-3 (R-2 = 0.819) and SPI-12 (R-2 = 0.968) values at Paithan station; the SPI-3 (R-2 = 0.736) and SPI-6 (R-2 = 0.841) values at Silload station, respectively. The SMO-SVM PUK kernel is found that the best ML model for the prediction of SPI-6 (R-2 = 0.846) at Paithan station and SPI-12 (R-2 = 0.975) at the Silload station. The compared with SVM-SMO poly kernel and SVM-SMO PUK kernel was observed, these models are best forecasting of drought (i.e. SPI-6 and SPI-12), while SVM-SMO poly kernel is good for SPI-3 prediction at both stations. The results have been showed the ability of the SVM-SMO algorithm with various kernel functions successfully applied for the forecasting of multiscale SPI under the climate changes. It can be helpful for decision making in water resource management and tackle droughts in the semi-arid region of central India.
英文关键词	SPI; Sensitivity analysis; Support vector machine; Best subset regression; Kernel functions
语种	英语
WOS研究方向	Engineering, Civil ; Water Resources
WOS类目	Science Citation Index Expanded (SCI-EXPANDED)
WOS记录号	WOS:000924491500003
来源期刊	WATER RESOURCES MANAGEMENT
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/281606
作者单位	Ministry of Earth Sciences (MoES) - India; Indian Institute of Tropical Meteorology (IITM); Indian Council of Agricultural Research (ICAR); ICAR - Indian Agricultural Research Institute; University of the Free State; University West Indies Mona Jamaica; University West Indies Saint Augustine; Sher-e-Kashmir University of Agricultural Sciences & Technology of Kashmir (SKUAST Kashmir); Tartous University; Haramaya University; Egyptian Knowledge Bank (EKB); Mansoura University; Universiti Tenaga Nasional; Damascus University
推荐引用方式 GB/T 7714	Pande, Chaitanya B.,Kushwaha, N. L.,Orimoloye, Israel R.,et al. Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index[J],2023,37(3).
APA	Pande, Chaitanya B..,Kushwaha, N. L..,Orimoloye, Israel R..,Kumar, Rohitashw.,Abdo, Hazem Ghassan.,...&Elbeltagi, Ahmed.(2023).Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index.WATER RESOURCES MANAGEMENT,37(3).
MLA	Pande, Chaitanya B.,et al."Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index".WATER RESOURCES MANAGEMENT 37.3(2023).