A Survey on Remote Sensing-Based Climate Change Prediction Using Artificial Intelligence Techniques

Climate change prognosis is one of the most important fields of study that has attracted much interest in the last decade because of its implication for environmental and social development. The developments in remote sensing technologies that deliver data on various climatic factors have been integrated with Artificial Intelligence techniques to improve climate change prediction models. This paper aims to review the research done between the years 2014–2024 and how the AI methods were applied along with the remote sensing data for climate change prediction. The survey covers different AI techniques, including machine learning, deep learning, combined approaches, and their application to vast RS datasets. Major trends and issues in this rapidly developing multidisciplinary area are discussed, and the strengths and weaknesses of different AI methods are compared. Furthermore, recent AI techniques used in remote-sensing-based climate change prediction include Neural Networks, Support Vector Machines (SVMs), Random Forests and Decision trees with physical climate models. However, these models have limitations like difficulties in handling heterogeneous information from different sensors, high computational costs, limited labelled datasets, and issues interpreting complicated AI model results. It also points to the directions for future research, noting that there is a need for better, more powerful and easily understandable AI frameworks to handle the issue of climate change. This paper seeks to give the reader an insight into the current state of AI in climate change prediction and the use of remote sensing data in this area of research.