|
|
 |
| |
|
|
|
A Deep Learning Prediction Model to Predict Sustainable Development in Saudi Arabia |
|
|
|
PP: 1345-1366 |
|
|
|
doi:10.18576/amis/180615
|
|
|
|
Author(s) |
|
|
|
Fahad Aljuaydi,
Bikash K. Behera,
Ahmed M. Elshewey,
Zahraa Tarek,
|
|
|
|
Abstract |
|
|
| This paper introduces a novel deep learning model specifically designed for predicting climate change in Saudi Arabia until the year 2030. The proposed model, called CNN-BRNN, is a hybrid architecture that integrates the strengths of Bidirectional Recurrent Neural Network (BRNN) and Conventional Neural Network (CNN) models. The model is employed to provide accurate predictions for four key factors: temperature, air temperature dew point, visibility distance, and air pressure at sea level. Each of these factors is individually predicted to analyze the climate change trends in Saudi Arabia up to 2030. The CNN-BRNN model is compared to five other machine learning regressors: Random Forest, Support Vector, K-Nearest Neighbor, Gradient Boosting, and Dummy regressor. The outcomes demonstrate that the CNN-BRNN model performs better than the other models. The predictions generated by the CNN- BRNN model reveal several significant climate change trends projected for Saudi Arabia until 2030. These trends include a projected 20-degree increase in the temperature, a rise in air temperature dew point, abnormal reduction in air visibility distance, and decreased air pressure at sea level. These findings highlight the potential impacts of climate change on Saudi Arabia’s environment. Building upon the obtained results, decision-makers can successfully handle the challenges caused by climate change, guaranteeing the nation’s sustainability in the future.
|
|
|
|
|
|
|
|
