Sustainable utilization of the freely available solar radiation as renewable energy source requires accurate predictive models to quantitatively evaluate future energy potentials. In this research, an evaluation of the preciseness of extreme learning machine (ELM) model as a fast and efficient framework for estimating global incident solar radiation (G) is undertaken. Daily meteorological datasets suitable for G estimation belongs to the northern parts of the Cheliff Basin in Northwest Algeria, is used to construct the estimation model. Cross-correlation functions are applied between the inputs and the target variable (i.e., G) where several climatological information’s are used as the predictors for surface level G estimation. The most significant model inputs are determined in accordance with highest cross-correlations considering the covariance of the predictors with the G dataset. Subsequently, seven ELM models with unique neuronal architectures in terms of their input-hidden-output neurons are developed with appropriate input combinations. The prescribed ELM model’s estimation performance over the testing phase is evaluated against multiple linear regressions (MLR), autoregressive integrated moving average (ARIMA) models and several well-established literature studies. This is done in accordance with several statistical score metrics. In quantitative terms, the root mean square error (RMSE) and mean absolute error (MAE) are dramatically lower for the optimal ELM model with RMSE and MAE = 3.28 and 2.32 Wm-2 compared to 4.24 and 3.24 Wm-2 (MLR) and 8.33 and 5.37 Wm-2 (ARIMA).

This study uses machine learning (ML) models for a high-resolution prediction (0.1°×0.1°) of air fine particular matter (PM_2.5) concentration, the most harmful to human health, from meteorological and soil data. Iraq was considered the study area to implement the method. Different lags and the changing patterns of four European Reanalysis (ERA5) meteorological variables, rainfall, mean temperature, wind speed and relative humidity, and one soil parameter, the soil moisture, were used to select the suitable set of predictors using a non-greedy algorithm known as simulated annealing (SA). The selected predictors were used to simulate the temporal and spatial variability of air PM_2.5 concentration over Iraq during the early summer (May-July), the most polluted months, using three advanced ML models, extremely randomized trees (ERT), stochastic gradient descent backpropagation (SGD-BP) and long short-term memory (LSTM) integrated with Bayesian optimizer. The spatial distribution of the annual average PM_2.5 revealed the population of the whole of Iraq is exposed to a pollution level above the standard limit. The changes in temperature and soil moisture and the mean wind speed and humidity of the month before the early summer can predict the temporal and spatial variability of PM_2.5 over Iraq during May-July. Results revealed the higher performance of LSTM with normalized root-mean-square error and Kling-Gupta efficiency of 13.4% and 0.89, compared to 16.02% and 0.81 for SDG-BP and 17.9% and 0.74 for ERT. The LSTM could also reconstruct the observed spatial distribution of PM_2.5 with MapCurve and Cramer's V values of 0.95 and 0.91, compared to 0.9 and 0.86 for SGD-BP and 0.83 and 0.76 for ERT. The study provided a methodology for forecasting spatial variability of PM_2.5 concentration at high resolution during the peak pollution months from freely available data, which can be replicated in other regions for generating high-resolution PM_2.5 forecasting maps.