Reference Evapotranspiration Projections in Southern Spain (until 2100) using temperature-based machine learning models

Abstract

In this research, the primary focus revolves around evaluating the efficacy of machine learning models based on temperature variables in estimating reference evapotranspiration (ET0), an essential parameter for water management in agriculture, ecosystems, and hydrology. Data from 122 Automated Weather Stations (AWS) across different regions in Southern Spain has been studied and four machine learning models have been developed and assessed: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Random Forest (RF), and Extreme Learning Machine (ELM). The results show that machine learning models enhance the traditional Hargreaves-Samani method in this task. Besides, MLP using the diurnal temperature range (DTR), the minimum, mean and maximum air temperature (Tx, Tm, Tn, respectively), and Extraterrestrial solar radiation features (Ra) was found to be the fittest model in one region, while ELM using Tx, Tn, Tm and Ra as input features performed best in another. Once the models were validated, they have been applied to future 5km gridded projection datasets, using different Representative Concentration Pathway (RCP) scenarios, in order to estimate ET0 up to the year 2100. In general, the projected ET0 was found to increase significantly in the future, highlighting the need for proactive water management strategies to address the potential impact of climate change on water resources. The ET0 is expected to increase from 1300-1600 mm to 1500-1700 mm using the RCP4.5 and to 1900 mm using the RCP8.5 in Andalusia, with the highest increase occurring in the south coastal region. This study provides important insights into the application of machine learning models to estimate ET0 and its implications for future water management strategies.