Global solar radiation prediction over North Dakota using air temperature: Development of novel hybrid intelligence model

Accurate solar radiation (SR) prediction is one of the essential prerequisites harvesting energy. The current study proposed a novel intelligence model through hybridization Adaptive Neuro-Fuzzy Inference System (ANFIS) with two metaheuristic optimization algorithms, Salp Swarm Algorithm (SSA) and Grasshopper Optimization (GOA) (ANFIS-muSG) for global SR at different locations North Dakota, USA. performance ANFIS-muSG was compared classical ANFIS, ANFIS-GOA, ANFIS-SSA, ANFIS-Grey Wolf Optimizer (ANFIS-GWO), ANFIS-Particle (ANFIS-PSO), ANFIS-Genetic (ANFIS-GA) ANFIS-Dragonfly (ANFIS-DA). Consistent maximum, mean minimum air temperature data nine years (2010–2018) were used to build models. showed 25.7%–54.8% higher accuracy in terms root square error other models areas. developed this can be employed from only. results indicate potential ANFIS algorithms improvement accuracy.