Study of Climate Change Detection in North-East Africa Using Machine Learning and Satellite Data
Sara K. Ibrahim, Ibrahim Ziedan, Ayman Ahmed
Abstract
The study of climate change has become an important topic, because of its negative impact on human life. The North-East African part lacks the studies for climate change detection, despite it being one of the most affected parts worldwide. The relationship between the emission of greenhouse gases (GHGs) and climate change is an important factor to understand. To investigate this linkage, we used machine-learning models based on essential climate variables to investigate the relationship between the GHGs and the rhythm of climate variable change. The research investigates how machine learning techniques can be applied to climatic data to build an ML model that able to predict the state of climate variables for the short and long term. By selecting a candidate model, will help in climate adaptation and mitigation, also determine at what level GHGs should be kept and their corresponding concentrations in order to avoid climate events and crises. The used models are long short-term memory, autoencoders, and convolutional neural network. Alternatively, the data set has been selected from UK National Centre for Earth Observation (NCEO) and Copernicus Climate Change Services (C3Ss). We compared the performance of these techniques and the best candidate was the Head CNN; based on performance metrics such as Root-Mean-Squared-Error (RMSE): 5.378, 2.395, and 15.923, and R Coefficient: 0.607, 0.806, and 0.539 for the variables temperature, CO2, and CH4 respectively. We were able to link the greenhouse gas emission to essential climate variables with high accuracy based on the reading of this geographic area.