{"title":"利用机器学习算法和气候数据评估和预测气象干旱","authors":"Khalid En-Nagre , Mourad Aqnouy , Ayoub Ouarka , Syed Ali Asad Naqvi , Ismail Bouizrou , Jamal Eddine Stitou El Messari , Aqil Tariq , Walid Soufan , Wenzhao Li , Hesham El-Askary","doi":"10.1016/j.crm.2024.100630","DOIUrl":null,"url":null,"abstract":"<div><p>Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted in Morocco’s Upper Drâa Basin (UDB), analyzed data spanning from 1980 to 2019, focusing on the calculation of drought indices, specifically the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as the Mann-Kendall test and the Sen’s Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost Regressor, and K-Nearest Neighbors Regressor, were evaluated to predict the SPEI values for both three and 12-month periods. The algorithms’ performance was measured using statistical indices. The study revealed that drought distribution within the UDB is not uniform, with a discernible decreasing trend in SPEI values. Notably, the four ML algorithms effectively predicted SPEI values for the specified periods. Random Forest, Voting Regressor, and AdaBoost demonstrated the highest Nash-Sutcliffe Efficiency (NSE) values, ranging from 0.74 to 0.93. In contrast, the K-Nearest Neighbors algorithm produced values within the range of 0.44 to 0.84. These research findings have the potential to provide valuable insights for water resource management experts and policymakers. However, it is imperative to enhance data collection methodologies and expand the distribution of measurement sites to improve data representativeness and reduce errors associated with local variations.</p></div>","PeriodicalId":54226,"journal":{"name":"Climate Risk Management","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2212096324000470/pdfft?md5=86c5c7e81b15816365b705592e8fb810&pid=1-s2.0-S2212096324000470-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Assessment and prediction of meteorological drought using machine learning algorithms and climate data\",\"authors\":\"Khalid En-Nagre , Mourad Aqnouy , Ayoub Ouarka , Syed Ali Asad Naqvi , Ismail Bouizrou , Jamal Eddine Stitou El Messari , Aqil Tariq , Walid Soufan , Wenzhao Li , Hesham El-Askary\",\"doi\":\"10.1016/j.crm.2024.100630\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted in Morocco’s Upper Drâa Basin (UDB), analyzed data spanning from 1980 to 2019, focusing on the calculation of drought indices, specifically the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as the Mann-Kendall test and the Sen’s Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost Regressor, and K-Nearest Neighbors Regressor, were evaluated to predict the SPEI values for both three and 12-month periods. The algorithms’ performance was measured using statistical indices. The study revealed that drought distribution within the UDB is not uniform, with a discernible decreasing trend in SPEI values. Notably, the four ML algorithms effectively predicted SPEI values for the specified periods. Random Forest, Voting Regressor, and AdaBoost demonstrated the highest Nash-Sutcliffe Efficiency (NSE) values, ranging from 0.74 to 0.93. In contrast, the K-Nearest Neighbors algorithm produced values within the range of 0.44 to 0.84. These research findings have the potential to provide valuable insights for water resource management experts and policymakers. However, it is imperative to enhance data collection methodologies and expand the distribution of measurement sites to improve data representativeness and reduce errors associated with local variations.</p></div>\",\"PeriodicalId\":54226,\"journal\":{\"name\":\"Climate Risk Management\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2212096324000470/pdfft?md5=86c5c7e81b15816365b705592e8fb810&pid=1-s2.0-S2212096324000470-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Climate Risk Management\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2212096324000470\",\"RegionNum\":2,\"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":"Climate Risk Management","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212096324000470","RegionNum":2,"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}
Assessment and prediction of meteorological drought using machine learning algorithms and climate data
Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted in Morocco’s Upper Drâa Basin (UDB), analyzed data spanning from 1980 to 2019, focusing on the calculation of drought indices, specifically the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as the Mann-Kendall test and the Sen’s Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost Regressor, and K-Nearest Neighbors Regressor, were evaluated to predict the SPEI values for both three and 12-month periods. The algorithms’ performance was measured using statistical indices. The study revealed that drought distribution within the UDB is not uniform, with a discernible decreasing trend in SPEI values. Notably, the four ML algorithms effectively predicted SPEI values for the specified periods. Random Forest, Voting Regressor, and AdaBoost demonstrated the highest Nash-Sutcliffe Efficiency (NSE) values, ranging from 0.74 to 0.93. In contrast, the K-Nearest Neighbors algorithm produced values within the range of 0.44 to 0.84. These research findings have the potential to provide valuable insights for water resource management experts and policymakers. However, it is imperative to enhance data collection methodologies and expand the distribution of measurement sites to improve data representativeness and reduce errors associated with local variations.
期刊介绍:
Climate Risk Management publishes original scientific contributions, state-of-the-art reviews and reports of practical experience on the use of knowledge and information regarding the consequences of climate variability and climate change in decision and policy making on climate change responses from the near- to long-term.
The concept of climate risk management refers to activities and methods that are used by individuals, organizations, and institutions to facilitate climate-resilient decision-making. Its objective is to promote sustainable development by maximizing the beneficial impacts of climate change responses and minimizing negative impacts across the full spectrum of geographies and sectors that are potentially affected by the changing climate.