Energy has become an integral part of our society and global economic development in the twenty-first century. Despite tremendous technological advancements, fossil fuels (coal, natural gas, and oil) continue to be the world’s primary source of energy. Global energy scenarios indicate a change in coal consumption trends in the future, which in turn will have commercial, geopolitical, and environmental consequences. We investigated coal consumption up to 2030 using a new hybrid method of WOANFIS (whale optimization algorithm and adaptive neuro-fuzzy inference system). The WOANFIS method’s performance was assessed by the MSE (Mean Squared Error), MAE (Mean Absolute Error), STD (error standard deviation), RMSE (Root Mean Squared Error), and coefficient of correlation (R2) among the real dataset and the WOANFIS result. For the prediction of global coal consumption, the proposed WOANFIS had the best MAE, RMSE, and correlation coefficient (R2) values, which were 0.00113, 0.0047, and 0.98, respectively. Lastly, future global coal consumption was predicted up to 2030 by WOANFIS. Following 150 years of coal dominance, the results demonstrate that WOANFIS is a suitable method for estimating worldwide coal consumption, which makes it possible to plan for the transition away from coal.

Coal as a fossil and non-renewable fuel is one of the most valuable energy minerals in the world with the largest volume reserves. Artificial neural networks (ANN), despite being one of the highest breakthroughs in the field of computational intelligence, has some significant disadvantages, such as slow training, susceptibility to falling into a local optimal points, sensitivity of initial weights, and bias. To overcome these shortcomings, this study presents an improved ANN structure, that is optimized by a proposed hybrid method. The aim of this study is to propose a novel hybrid method for predicting coal consumption in Iran based on socio-economic variables using the bat and grey wolf optimization algorithm with an artificial neural network (BGWAN). For this purpose, data from 1981 to 2019 have been used for modelling and testing the method. The available data are partly used to find the optimal or near-optimal values of the weighting parameters (1980–2014) and partly to test the model (2015–2019). The performance of the BGWAN is evaluated by mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), standard deviation error (STD), and correlation coefficient (R^2) between the output of the method and the actual dataset. The result of this study showed that BGWAN performance was excellent and proved its efficiency as a useful and reliable tool for monitoring coal consumption or energy demand in Iran.