Neural-network modeling of solar radiation and temperature variability due to climate change in Ibadan Metropolis

his research focused on studying the variability of solar radiation and temperature under climate change in Ibadan metropolis. In study, spatial distribution, temporal variations, annual estimation prediction radiation, minimum maximum data Metropolis was collected. A Long Short-Term Memory Neural Network (LSTM-NN) model developed for using time-series obtained. An ARIMA further to compare validate LSTM-NN model. The performance models were determined root mean square error (RMSE) absolute percentage (MAPE). RMSE values minimum, predictions 1.543, 1.290, 1.967, 1.611, 1.309, 2.106 respectively, while MAPE 3.603, 4.351, 8.859, 3.840, 4.480, 9.502 respectively. had a better all categories with lower when compared ARIMA. From prediction, it observed that there will be reduction temperature, obtained data. ranged from 22.9032-23.2032(0C), predicted 19.9260- 19.977(0C) also 32.87096-33.7064(0C), 29.5159-29.5529(0C), 19.203-19.722 (W/m2 ), 14.123-14.115 ). year highest which constitutes useful energy is 2024 an average value 14.1395 W/m2