Hybrid machine learning for drought prediction at multiple time scales: a case study of Ağrı station, Türkiye

IF 2.3 4区 地球科学
Hatice Citakoglu, Gaye Aktürk, Vahdettin Demir
{"title":"Hybrid machine learning for drought prediction at multiple time scales: a case study of Ağrı station, Türkiye","authors":"Hatice Citakoglu,&nbsp;Gaye Aktürk,&nbsp;Vahdettin Demir","doi":"10.1007/s11600-024-01501-5","DOIUrl":null,"url":null,"abstract":"<div><p>Drought is a prolonged period of significantly reduced precipitation, resulting in water scarcity and environmental stress. In this study, Ağrı province, situated in the eastern region of Türkiye, where most of the land cannot be irrigated and the livelihood is based on agriculture, was selected as the study area. Meteorological droughts in Ağrı province were forecasted using hybrid machine-learning models, leveraging monthly precipitation and temperature series from 1965 to 2022. The study employed the standardized precipitation index (SPI), relying solely on precipitation data, and the standardized precipitation evapotranspiration index (SPEI), which also considers both temperature and precipitation data. Various timescales, including 1M (1 month), 3M, 6M, 9M, and 12M, were taken into consideration. The best model for each hybrid model was determined using data at time points t, t-<sub>1</sub>, t<sub>-2</sub>, t<sub>-3</sub>, and t<sub>-4</sub> for the relevant time series. The study combined ensemble least squares boosting algorithms (LSBoosting), adaptive network-fuzzy inference system (ANFIS), support vector machines (SVM), Gaussian process regression (GPR), and M5 model tree (M5Tree) approaches with the variational mode decomposition (VMD) technique to create hybrid models. The results indicate that certain models perform better at different timescales, with M5Tree and GPR generally providing higher accuracy. For instance, the M5Tree model achieved the lowest MAE (0.0714 and 0.0555) and RMSE (0.0909 and 0.0732) values for the <sub>9M</sub>SPI and <sub>12M</sub>SPI timescales, respectively, making it the best-performing model at these scales. Similarly, the GPR model stood out for the <sub>1M</sub>SPI and <sub>6M</sub>SPI scales with the lowest MAE values (0.1336 and 0.0736, respectively). Based on the performance criteria, the best hybrid model for the <sub>1M</sub>SPI was the GPR approach. For the SPEI, except for <sub>3M</sub>SPEI, the M5Tree approach showed the best performance at other timescales. However, since the prediction outcomes gave similar results according to classical performance criteria, a one-sided Wilcoxon sign rank test was applied to the outcomes of ANFIS, GPR, and M5Tree models for <sub>3M</sub>SPEI, <sub>6M</sub>SPI, <sub>9M</sub>SPI, and <sub>12M</sub>SPI. It has been determined that these three models are not superior to each other. Additionally, the one-sided Wilcoxon signed-rank test found no statistically significant difference between ANFIS, GPR, SVM, and M5Tree models for the <sub>3M</sub>SPI. This research concluded that the performance of hybrid machine-learning methods applied to different timescales of SPI and SPEI varies.</p></div>","PeriodicalId":6988,"journal":{"name":"Acta Geophysica","volume":"73 2","pages":"1643 - 1677"},"PeriodicalIF":2.3000,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11600-024-01501-5.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Geophysica","FirstCategoryId":"89","ListUrlMain":"https://link.springer.com/article/10.1007/s11600-024-01501-5","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Drought is a prolonged period of significantly reduced precipitation, resulting in water scarcity and environmental stress. In this study, Ağrı province, situated in the eastern region of Türkiye, where most of the land cannot be irrigated and the livelihood is based on agriculture, was selected as the study area. Meteorological droughts in Ağrı province were forecasted using hybrid machine-learning models, leveraging monthly precipitation and temperature series from 1965 to 2022. The study employed the standardized precipitation index (SPI), relying solely on precipitation data, and the standardized precipitation evapotranspiration index (SPEI), which also considers both temperature and precipitation data. Various timescales, including 1M (1 month), 3M, 6M, 9M, and 12M, were taken into consideration. The best model for each hybrid model was determined using data at time points t, t-1, t-2, t-3, and t-4 for the relevant time series. The study combined ensemble least squares boosting algorithms (LSBoosting), adaptive network-fuzzy inference system (ANFIS), support vector machines (SVM), Gaussian process regression (GPR), and M5 model tree (M5Tree) approaches with the variational mode decomposition (VMD) technique to create hybrid models. The results indicate that certain models perform better at different timescales, with M5Tree and GPR generally providing higher accuracy. For instance, the M5Tree model achieved the lowest MAE (0.0714 and 0.0555) and RMSE (0.0909 and 0.0732) values for the 9MSPI and 12MSPI timescales, respectively, making it the best-performing model at these scales. Similarly, the GPR model stood out for the 1MSPI and 6MSPI scales with the lowest MAE values (0.1336 and 0.0736, respectively). Based on the performance criteria, the best hybrid model for the 1MSPI was the GPR approach. For the SPEI, except for 3MSPEI, the M5Tree approach showed the best performance at other timescales. However, since the prediction outcomes gave similar results according to classical performance criteria, a one-sided Wilcoxon sign rank test was applied to the outcomes of ANFIS, GPR, and M5Tree models for 3MSPEI, 6MSPI, 9MSPI, and 12MSPI. It has been determined that these three models are not superior to each other. Additionally, the one-sided Wilcoxon signed-rank test found no statistically significant difference between ANFIS, GPR, SVM, and M5Tree models for the 3MSPI. This research concluded that the performance of hybrid machine-learning methods applied to different timescales of SPI and SPEI varies.

多时间尺度的混合机器学习干旱预测:以Ağrı站为例,t rkiye
干旱是指长时间降水显著减少,导致水资源短缺和环境压力。本研究选取了位于 rkiye省东部的Ağrı省作为研究区域,该省大部分土地无法灌溉,以农业为主要生计。利用1965年至2022年的月降水和温度序列,利用混合机器学习模型对Ağrı省的气象干旱进行了预测。本研究采用单纯依赖降水数据的标准化降水指数(SPI)和同时考虑温度和降水数据的标准化降水蒸散指数(SPEI)。考虑了1M(1个月)、3M、6M、9M、12M等时间尺度。利用相关时间序列的时间点t、t-1、t-2、t-3和t-4的数据确定每个混合模型的最佳模型。该研究将集成最小二乘增强算法(LSBoosting)、自适应网络模糊推理系统(ANFIS)、支持向量机(SVM)、高斯过程回归(GPR)和M5模型树(M5Tree)方法与变分模态分解(VMD)技术相结合,建立混合模型。结果表明,某些模型在不同的时间尺度上表现更好,M5Tree和GPR通常提供更高的精度。例如,M5Tree模型在9MSPI和12MSPI时间尺度上分别获得了最低的MAE(0.0714和0.0555)和RMSE(0.0909和0.0732)值,使其成为这些尺度上表现最好的模型。同样,GPR模型在1MSPI和6MSPI尺度上的MAE值最低(分别为0.1336和0.0736)。基于性能标准,1MSPI的最佳混合模型是GPR方法。对于SPEI,除3MSPEI外,M5Tree方法在其他时间尺度上表现最佳。然而,由于预测结果根据经典性能标准给出了相似的结果,因此对3mspi、6MSPI、9MSPI和12MSPI的ANFIS、GPR和M5Tree模型的结果进行了单侧Wilcoxon符号秩检验。已经确定这三种模式彼此之间并不优越。此外,单侧Wilcoxon sign -rank检验发现,ANFIS、GPR、SVM和M5Tree模型对3MSPI没有统计学差异。本研究得出混合机器学习方法应用于不同时间尺度的SPI和SPEI的性能是不同的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Acta Geophysica
Acta Geophysica GEOCHEMISTRY & GEOPHYSICS-
CiteScore
3.80
自引率
13.00%
发文量
251
期刊介绍: Acta Geophysica is open to all kinds of manuscripts including research and review articles, short communications, comments to published papers, letters to the Editor as well as book reviews. Some of the issues are fully devoted to particular topics; we do encourage proposals for such topical issues. We accept submissions from scientists world-wide, offering high scientific and editorial standard and comprehensive treatment of the discussed topics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信