Meteorological data implications modeling on evapotranspiration variability in arid and semi-arid zones in Saudi Arabia using hybrid metaheuristic

This work is unique and contributes new knowledge to the field whereas it involves introducing a new method based on coupling two or three stochastic models, analyzing new data represented by drought and flooding risk relationship, and addressing a previously unexplored research question: Can we make a decision regarding future evapotranspiration-flooding risk relationship? In this paper, the Bat algorithm (BAT) with the Newton Method (NM), Bird Swarm Algorithm (BSA), Genetic Algorithm (GA), and Chicken Swarm Optimization Algorithm (CSO) are used as a hybrid model in arid and semi-arid zones in Saudi Arabia as well as for modeling rainfall, temperature, and solar radiation implications on evapotranspiration variability. Coupling between aridity and evapotranspiration over a long time can create flooding risks. This holistic modeling aims to reduce flooding risks and ensure the desired decision. Several models were employed to simulate some basins' Potential and Actual evapotranspiration as case studies. The meteorological inputs of the hybrid models were calibrated and validated with metric evaluation for input and output of evapotranspiration, respectively. The results suggest that the application of a hybrid model can improve the accuracy of evapotranspiration simulations in terms of statistical parameters, whereas BAT-GA-NM reduced MAPE from 38.88 to 4.16% for Mekkah and from 14.94 to 2.04% for Medina and NSCE from - 0.17 to 0.97 for Mekkah and from 0.82 to 0.99%. Those parameters will provide a better understanding of evapotranspiration processes in watersheds and valuable information for early warnings of flooding risks.