Researchers at the Institute of Water and Environmental Engineering (IIAMA) at the Universitat Politècnica de València have developed an advanced system for seasonal forecasting of meteorological droughts that enables these events to be predicted up to six months in advance, providing a key tool for water management and early warning in semi-arid regions, such as the Júcar river basin.
The study, published in the journal Earth Systems and Environment, presents a pioneering approach that integrates multi-model seasonal climate predictions, widely used drought indices, and artificial intelligence techniques, significantly improving the reliability of current forecasts.
The research, carried out by Dariana Ávila Velásquez, Héctor Macián, and Manuel Pulido, combines seasonal forecasts from four internationally recognised systems (ECMWF-SEAS5, Météo-France System8, DWD-GCF2.1, and CMCC-SPSv3. 5), available through the Copernicus Climate Change Service (C3S), with historical ERA5 data, which has been post-processed using artificial intelligence.
Key findings: high reliability in drought prediction
Using this information, the researchers calculated two of the most widely used drought indices internationally: the Standardised Precipitation Index (SPI) and the Standardised Precipitation-Evapotranspiration Index (SPEI), across different time scales (6, 12, 18, and 24 months).
'In the case of the six-month indices, reliability reaches values close to 90% in the same month the forecast is issued. Looking three months ahead, predictive ability remains above 60%, whilst for longer time scales, such as 12, 18, and 24 months, the system retains a useful predictive capability up to six months in advance," explains Dariana Ávila Velásquez, lead author of the article.
The methodology has been applied to the Júcar River Basin District, one of the most representative areas of the semi-arid Mediterranean, characterised by recurrent droughts, high pressure on water resources, and high agricultural, urban, and environmental demand.
"The results confirm that the system is particularly effective at strengthening early drought warnings, a fundamental aspect for anticipating management measures, reducing socio-economic impacts, and increasing resilience to climate change," notes Héctor Macián, a researcher at IIAMA and co-author of the study.
The main innovation: integrating models, indices, and artificial intelligence
The main contribution of the work, carried out as part of the WATER4CAST 2.0 project under the PROMETEO programme for excellence research groups of the Valencian Regional Government, lies in the joint integration of multi-model seasonal forecasts, operational drought indices (SPI and SPEI) and artificial intelligence techniques, which enable biases to be corrected and models to be better adapted at the regional level. Furthermore, the team has developed a web-based operational implementation, demonstrating the real-world applicability of the system for decision-making in water management beyond the strictly academic sphere.
"The multi-model approach we have developed significantly enhances the robustness of predictions and reduces the uncertainty associated with traditional climate forecasts. Moreover, the combination of the SPI and SPEI indices provides us with a more comprehensive view of the phenomenon, as it considers not only precipitation deficits but also the impact of rising temperatures, a key factor in the current context of climate change," emphasises Professor Manuel Pulido, a researcher at IIAMA, coordinator of WATER4CAST 2.0 alongside Professor Félix Francés (IIAMA), and head of the Hydroeconomic Modelling research group at IIAMA.
In this regard, Manuel Pulido emphasises that the methodology is fully transferable to other drought-prone basins and regions, as one of the approaches we have adopted is to use data with global coverage that is 100% open access, "which opens the door to its application in different climatic contexts and its integration into decision-support systems for water management".
Finally, the IIAMA researchers highlight that this work demonstrates how seasonal forecasts can serve as a reliable, operational tool for drought management, particularly when multiple climate models and indices are combined.
"In a scenario where the frequency and intensity of droughts are increasing due to climate change, this type of tool is essential for moving towards a more proactive, efficient, and science-based approach to water and risk management," they conclude.