Applicability of denoising-based artificial intelligence to forecast the environmental externalities
Dongsheng Cai, Ghazala Aziz, Suleman Sarwar, Majid Ibrahim Alsaggaf, Avik Sinha
Abstract
The current study attempts to compare the hybrid artificial intelligence models to forecast the environmental externalities in Saudi Arabia. We have used the denoising based artificial intelligence models to construct hybrid models. While comparing the denoising techniques, the CSD-based denoising has outperformed. However, we have used the CSD-based hybrid models. CSD-ANN and CSD-RNN are used for denoising-based artificial intelligence models, whereas CSD-ARIMA is used for denoising-based traditional models. All these models are used to check and compare their performance in terms of level and direction of prediction for PM10. The results show that the CSD-based ANN model has a higher predictability for PM10 levels in Saudi Arabia due to low error values and higher Dstat values. In comparing original and forecasted data, the superiority of CSD-ANN is evident in predicting the PM10 in Saudi Arabia. Hence, this hybrid model can predict the environmental externalities for non-linear and highly noised data. Moreover, the findings can be useful in achieving the sustainable development goal.