article · Climate Risk Management
An investigation in Morocco's Upper Drâa Basin examined meteorological drought conditions between 1980 and 2019 using climate records and computational models. Standardised drought indices, specifically the Standardized Precipitation Index and the Standardized Precipitation Evapotranspiration Index, were calculated across timescales of one, three, nine, and twelve months. Trend analyses showed a declining pattern in index values across the basin, indicating worsening drought conditions that vary regionally. To forecast future drought, four machine learning models were tested for three-month and twelve-month projections. Random Forest, Voting Regressor, and AdaBoost Regressor delivered the strongest predictive accuracy, yielding Nash-Sutcliffe Efficiency scores between 0.74 and 0.93. The K-Nearest Neighbors Regressor performed less reliably, with scores from 0.44 to 0.84. Maximising future predictive value will require broader spatial data collection and additional monitoring stations across the basin.
Semi-arid regions face mounting water security pressures from changing climate conditions. Demonstrating that machine learning tools can accurately forecast drought indices over short and medium periods gives water resource managers and policymakers critical foresight. With better forecasting models and expanded local weather monitoring, regional authorities can make evidence-based decisions to mitigate water shortages and allocate scarce supplies more effectively.
This work demonstrates applied predictive models tested on regional historical data, positioning it at an applied research stage. The methods could be integrated into decision-support software for water resource management experts, agricultural planners, and public policymakers. However, operational deployment requires improved local data collection methodologies and an expanded network of physical measurement sites to address geographic variations and maintain accuracy.
AI-generated from the published abstract. Always read the original work before citing.
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.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.crm.2024.100630
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
