MOGGP: A novel multi objective geometric genetic programming model for drought forecasting

Drought is an environmental challenge, with devastating impacts across a wide range of sectors, including agriculture, economy, and ecosystems. Accurate drought forecasting models are necessary for sustainable water resources planning. Therefore, exploring the efficacy and parsimony of emerging machine learning (ML) techniques to enhance predictive drought forecasting models’ accuracy while reducing their complexity is essential. This article introduces a novel hybrid evolutionary ML model, called MOGGP, and compares its efficiency with two evolutionary models, namely gene expression programming and multigene genetic programming as well as conventional Multilayer Perceptron. The new model integrates multi-objective geometric mean optimizer with a traditional symbolic genetic programming that allows parsimonious model selection through developing Pareto optimal solutions. Grided Standardized Precipitation Evapotranspiration Index (SPEI) datasets were employed for demonstrating MOGGP and verifying its efficiency. The results showed that annual cycle is not an effective input for the evolved evolutionary SPEI model. In addition, performance appraisal analysis revealed that the MOGGP consistently exhibits parsimonious models, superior to its counterparts, and excels in addressing multi-objective hydrological modeling problems.