利用集合模型和机器学习模型预报气象干旱

IF 6 3区 环境科学与生态学 Q1 ENVIRONMENTAL SCIENCES
Chaitanya Baliram Pande, Lariyah Mohd Sidek, Abhay M. Varade, Ismail Elkhrachy, Neyara Radwan, Abebe Debele Tolche, Ahmed Elbeltagi
{"title":"利用集合模型和机器学习模型预报气象干旱","authors":"Chaitanya Baliram Pande,&nbsp;Lariyah Mohd Sidek,&nbsp;Abhay M. Varade,&nbsp;Ismail Elkhrachy,&nbsp;Neyara Radwan,&nbsp;Abebe Debele Tolche,&nbsp;Ahmed Elbeltagi","doi":"10.1186/s12302-024-00975-w","DOIUrl":null,"url":null,"abstract":"<div><p>This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R<sup>2</sup> = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.</p></div>","PeriodicalId":546,"journal":{"name":"Environmental Sciences Europe","volume":"36 1","pages":""},"PeriodicalIF":6.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s12302-024-00975-w.pdf","citationCount":"0","resultStr":"{\"title\":\"Forecasting of meteorological drought using ensemble and machine learning models\",\"authors\":\"Chaitanya Baliram Pande,&nbsp;Lariyah Mohd Sidek,&nbsp;Abhay M. Varade,&nbsp;Ismail Elkhrachy,&nbsp;Neyara Radwan,&nbsp;Abebe Debele Tolche,&nbsp;Ahmed Elbeltagi\",\"doi\":\"10.1186/s12302-024-00975-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R<sup>2</sup> = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.</p></div>\",\"PeriodicalId\":546,\"journal\":{\"name\":\"Environmental Sciences Europe\",\"volume\":\"36 1\",\"pages\":\"\"},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1186/s12302-024-00975-w.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Sciences Europe\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://link.springer.com/article/10.1186/s12302-024-00975-w\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Sciences Europe","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1186/s12302-024-00975-w","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

摘要

干旱现象在印度的灌溉、饮用水供应以及维持生态与经济平衡方面发挥着至关重要的作用。因此,基于机器学习(ML)模型的干旱预报对于未来的干旱规划非常重要。因此,我们选择了 3 个月和 6 个月的标准化降水指数(SPI),并将其用于该地区未来的干旱预报方案。十个输入 SPI-1- 和 SPI-10 的组合被用于 SPI-3 和 SPI-6 时间尺度的预测模型,该模型是基于 1989 年至 2019 年的历史 SPI 数据集开发的。SPI-3 和 SPI-6 的最大值和最小值分别为 SPI-3(2.03 和 -5.522)和 SPI-6(1.94 和 -6.93)。SPI 是一种常用的干旱分析估算方法,在全球范围内得到广泛应用。通过子集回归模型和敏感性研究,选出了输入变量的最佳组合,并对所开发的模型进行了相互比较。然后,使用有效输入参数预测 SPI-3 和 SPI-6 值,以了解半干旱地区的干旱情况。在 Ml 模型中使用了最佳输入变量组合,并建立了五种新型模型,如稳健线性回归模型、袋装树模型、助推树模型、支持向量回归模型(SVM-Linear)和高斯过程回归模型(Matern GPR)。此类模型首次应用于未来干旱状况的预测。通过使用超参数调整、bagging 和 boosting 模型,对整个模型进行了优化和改进。使用不同的统计指标对整个 ML 模型的准确性进行了比较。与五个 ML 模型的准确性相比,我们发现 Matern GPR 模型的准确性优于其他 ML 模型。在预测该地区的 SPI-3 和 SPI-6 值时,最佳模型精度 R2 = 0.95 和 0.93,RMSE、MSE、MAE、MARE 和 NSE 值分别为 0.95 和 0.93。因此,与其他算法相比,Matern GPR 模型被认为是预测 SPI-3 和 SPI-6 的最佳 ML 算法。这项研究证明了 Matern GPR 模型在预测气候变化下的多尺度 SPI-3 和 SPI-6 方面的功效。它有助于水土资源保护规划和管理,以及了解印度整个流域地区的干旱情况。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Forecasting of meteorological drought using ensemble and machine learning models

Forecasting of meteorological drought using ensemble and machine learning models

This study highlights drought forecasting for understanding the semi-arid area in India, where drought phenomena play vital role in the irrigation, drinking water supplies, and sustaining the ecological with economic balance for every nation. Therefore, drought forecasting is important for the future drought planning based on the machine learning (ML) models. Hence, The Standardized Precipitation Index (SPI) at 3- and 6-month periods have been selected and used for future drought forecasting scenarios in area. The combinations of ten inputs SPI-1- and SPI-10 were used for predicting modeling for SPI-3 and SPI-6 timescales, that modeling developed based on the historical SPI datasets from 1989 to 2019 years. The SPI-3 and SPI-6 maximum and minimum values are shown SPI-3 (2.03 and -5.522) and SPI-6 (1.94 and -6.93). The SPI is a popular method for estimating the drought analysis and has been used everywhere at global level. The developed models have been compared with each other, with the best combination of input variables selected using subset regression models and sensitivity studies. After that, the active input parameters were used for forecasting of SPI-3 and SPI-6 values to understanding of drought in semi-arid area. The finest input variables combination have been used in the Ml models and established the novel five models such as robust linear regression, bagged trees, boosted trees, support vector regression (SVM-Linear), and Matern Gaussian Process Regression (Matern GPR) models. Such kind of models first time has been applied for the forecasting of future drought conditions. Whole models were fine and improved modeling by using hyperparameters tuning, bagging, and boosting models. Entire ML models’ accuracy was compared using different statistical metrics. Compared with five ML models accuracy, we have found that the Matern GPR model better accuracy than other ML models. The best model accuracy is R2 = 0.95 and 0.93, RMSE, MSE, MAE, MARE, and NSE values, respectively, for predicting SPI-3 and SPI-6 values in the area. Therefore, the Matern GPR model was identified as the finest ML algorithm for predicting SPI-3 and SPI-6 associated with other algorithms. This research demonstrates the Matern GPR model's efficacy in predicting multiscale SPI-3 and SPI-6 under climate variations. It can be helpful in soil and water resource conservation planning and management and understanding droughts in the entire basin areas of the country India.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Environmental Sciences Europe
Environmental Sciences Europe Environmental Science-Pollution
CiteScore
11.20
自引率
1.70%
发文量
110
审稿时长
13 weeks
期刊介绍: ESEU is an international journal, focusing primarily on Europe, with a broad scope covering all aspects of environmental sciences, including the main topic regulation. ESEU will discuss the entanglement between environmental sciences and regulation because, in recent years, there have been misunderstandings and even disagreement between stakeholders in these two areas. ESEU will help to improve the comprehension of issues between environmental sciences and regulation. ESEU will be an outlet from the German-speaking (DACH) countries to Europe and an inlet from Europe to the DACH countries regarding environmental sciences and regulation. Moreover, ESEU will facilitate the exchange of ideas and interaction between Europe and the DACH countries regarding environmental regulatory issues. Although Europe is at the center of ESEU, the journal will not exclude the rest of the world, because regulatory issues pertaining to environmental sciences can be fully seen only from a global perspective.
×
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