A novel feature extraction-selection technique for long lead time agricultural drought forecasting

IF 5.9 1区 地球科学 Q1 ENGINEERING, CIVIL
Mehdi Mohammadi Ghaleni , Mansour Moradi , Mahnoosh Moghaddasi
{"title":"A novel feature extraction-selection technique for long lead time agricultural drought forecasting","authors":"Mehdi Mohammadi Ghaleni ,&nbsp;Mansour Moradi ,&nbsp;Mahnoosh Moghaddasi","doi":"10.1016/j.jhydrol.2024.132332","DOIUrl":null,"url":null,"abstract":"<div><div>Long-term drought forecasting plays a crucial role in mitigating drought risks by providing early warnings. Researchers have long been interested in achieving accurate long-term drought forecasting, which is challenging since accuracy generally decreases by increasing the forecasting period. The primary aim of this research is to propose a new method for high-accuracy long lead time drought forecasting by combining various Feature Extraction (FE) and selection techniques. In this study, monthly time-series datasets encompassing precipitation, potential evapotranspiration, actual evapotranspiration, runoff, surface and root-zone soil moisture—were utilized to forecast SPEI-6 over various lead times including 1-, 3-, 6-, 9-, 12-, 18-, and 24-months using global gridded products with a 0.5<sup>O</sup> × 0.5<sup>O</sup> spatial resolution spanning the years January 1980 to December 2022. The method was evaluated using two different approaches, namely Gaussian Process Regression (GPR) as a simple machine learning technique and Long Short-Term Memory (LSTM) as a deep learning method. The findings provided improved accuracy, particularly for long-term forecasting when employing the proposed methodology. When utilizing LSTM with FE instead of the original datasets as inputs, the error reduced from RMSE = 0.16 to RMSE = 0.07 (a 56 % decrease), while the correlation increased from R = 0.65 to R = 0.90 (a 38 % increase) when forecasting SPEI-6 12 months ahead. The results showed that the GPR with FE and selection model outperformed the LSTM with original datasets model for SPEI-6 (t + 24) with a correlation coefficient (R) of 0.9811 and a Normalized Root Mean Square Error (NRMSE) of 0.1380, compared to R = 0.6517 and NRMSE = 0.4307 for the LSTM with original datasets. These findings can offer valuable insights for early agricultural drought warning in arid areas.</div></div>","PeriodicalId":362,"journal":{"name":"Journal of Hydrology","volume":"647 ","pages":"Article 132332"},"PeriodicalIF":5.9000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydrology","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022169424017281","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

Abstract

Long-term drought forecasting plays a crucial role in mitigating drought risks by providing early warnings. Researchers have long been interested in achieving accurate long-term drought forecasting, which is challenging since accuracy generally decreases by increasing the forecasting period. The primary aim of this research is to propose a new method for high-accuracy long lead time drought forecasting by combining various Feature Extraction (FE) and selection techniques. In this study, monthly time-series datasets encompassing precipitation, potential evapotranspiration, actual evapotranspiration, runoff, surface and root-zone soil moisture—were utilized to forecast SPEI-6 over various lead times including 1-, 3-, 6-, 9-, 12-, 18-, and 24-months using global gridded products with a 0.5O × 0.5O spatial resolution spanning the years January 1980 to December 2022. The method was evaluated using two different approaches, namely Gaussian Process Regression (GPR) as a simple machine learning technique and Long Short-Term Memory (LSTM) as a deep learning method. The findings provided improved accuracy, particularly for long-term forecasting when employing the proposed methodology. When utilizing LSTM with FE instead of the original datasets as inputs, the error reduced from RMSE = 0.16 to RMSE = 0.07 (a 56 % decrease), while the correlation increased from R = 0.65 to R = 0.90 (a 38 % increase) when forecasting SPEI-6 12 months ahead. The results showed that the GPR with FE and selection model outperformed the LSTM with original datasets model for SPEI-6 (t + 24) with a correlation coefficient (R) of 0.9811 and a Normalized Root Mean Square Error (NRMSE) of 0.1380, compared to R = 0.6517 and NRMSE = 0.4307 for the LSTM with original datasets. These findings can offer valuable insights for early agricultural drought warning in arid areas.
用于长周期农业干旱预报的新型特征提取-选择技术
长期干旱预报通过提供预警,在减轻干旱风险方面发挥着至关重要的作用。长期以来,研究人员一直致力于实现准确的长期干旱预报,但这一工作极具挑战性,因为随着预报周期的延长,准确性通常会降低。本研究的主要目的是结合各种特征提取(FE)和选择技术,提出一种新的高精度长周期干旱预报方法。在这项研究中,利用月度时间序列数据集,包括降水、潜在蒸散量、实际蒸散量、径流、地表和根区土壤水分,使用 0.5O × 0.5O 空间分辨率的全球网格产品,跨越 1980 年 1 月至 2022 年 12 月,在 1、3、6、9、12、18 和 24 个月等不同提前期预测 SPEI-6。使用两种不同的方法对该方法进行了评估,即作为简单机器学习技术的高斯过程回归(GPR)和作为深度学习方法的长短期记忆(LSTM)。研究结果表明,在采用所建议的方法时,准确度有所提高,尤其是长期预测。当使用带有 FE 的 LSTM 代替原始数据集作为输入时,误差从 RMSE = 0.16 降低到 RMSE = 0.07(降低了 56%),而在预测 SPEI-6 时,相关性从 R = 0.65 提高到 R = 0.90(提高了 38%)。结果表明,对于 SPEI-6(t + 24),带有 FE 和选择模型的 GPR 优于带有原始数据集的 LSTM 模型,相关系数 (R) 为 0.9811,归一化均方根误差 (NRMSE) 为 0.1380,而带有原始数据集的 LSTM 的相关系数 (R) 为 0.6517,归一化均方根误差 (NRMSE) 为 0.4307。这些发现可为干旱地区的早期农业干旱预警提供有价值的见解。
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
Journal of Hydrology
Journal of Hydrology 地学-地球科学综合
CiteScore
11.00
自引率
12.50%
发文量
1309
审稿时长
7.5 months
期刊介绍: The Journal of Hydrology publishes original research papers and comprehensive reviews in all the subfields of the hydrological sciences including water based management and policy issues that impact on economics and society. These comprise, but are not limited to the physical, chemical, biogeochemical, stochastic and systems aspects of surface and groundwater hydrology, hydrometeorology and hydrogeology. Relevant topics incorporating the insights and methodologies of disciplines such as climatology, water resource systems, hydraulics, agrohydrology, geomorphology, soil science, instrumentation and remote sensing, civil and environmental engineering are included. Social science perspectives on hydrological problems such as resource and ecological economics, environmental sociology, psychology and behavioural science, management and policy analysis are also invited. Multi-and interdisciplinary analyses of hydrological problems are within scope. The science published in the Journal of Hydrology is relevant to catchment scales rather than exclusively to a local scale or site.
×
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