CMIP6 multi-model ensemble projection of reference evapotranspiration using machine learning algorithms

Abstract

Changes in reference crop evapotranspiration (ET o ) due to climate change (CC) can severely impact food and water security, emphasizing the need for integrating ET o projections into agricultural water management strategies. In this study, ET o changes were projected for two future time slices with respect to the baseline using several machine learning techniques, incorporating minimum and maximum temperature, diurnal temperature range, and extraterrestrial radiation across Iran. Additionally, an ensemble of 10 CMIP6 Global Climate Models, downscaled by the NASA Earth Exchange Global Daily Downscaled Projections (NEX-GDDP-CMIP6), was employed. The X-means clustering algorithm was also exploited to classify ET o based on various characteristics, including minimum, maximum, average, skewness, and standard deviation, as well as ET o ranges of 0–5, 5–10, and greater than 10 mm d⁻¹. This clustering approach divided the study area into five distinct clusters. Apart from cluster I, where the Support Vector Machine outperformed, the Random Forest technique provided more accurate ET o predictions. The findings project an average ET o increase of 4.8 % and 5.3 % during 2030–2049, and 8.0 % and 13.3 % for 2080–2099 under SSP245 and SSP585, respectively. Geographically, the highest ET o increases are anticipated primarily in the northern and western parts of the country, predominantly within clusters I and II. Notably, the ET o rise will exceed 40 % relative to the baseline during the late century under the SSP585. Furthermore, the most significant ET o increment is expected during winter. Future projections also indicate that cluster V, which already experiences significant daily ET o peaks, will face even more ET o extremes. Given the critical importance of these regions for sustaining food and water security and preserving natural resources, the substantial rise in ET o under future CC poses a significant threat to natural sustainability in Iran. This highlights the critical necessity for adaptive strategies in agricultural water management to mitigate the adverse CC effects. In this context, the current findings can assist decision-makers in identifying hotspots and quantifying CC impacts, thereby enabling the design of crucial adaptations. • Climate change impacts on ET o were projected using a novel methodology. • RF outperformed other ML techniques in modeling ET o . • The highest ET o projections were found in wetter regions of northern Iran. • ET o projections can aid in designing adaptive agricultural water management.

Topics & Concepts