Systematic Literature Review of Various Neural Network Techniques for Sea Surface Temperature Prediction Using Remote Sensing Data

Abstract

The popularity of using various neural network models and deep learning-based models to predict environmental tempera ment is increasing due to their ability to comprehend and address complex systems. When examining oceans and marine systems, Sea Surface Temperature (SST) is a critical factor to consider in terms of its impact on species, water availability, and natural events such as droughts and foods. This evaluation supplements a detailed analysis of Machine Learning and Deep Learning models that have been employed for several decades to predict SST. The study highlights familiar data, data sources, performance metrics, and a range of models for SSTP (Sea Surface Temperature Prediction), including artifcial neural networks, convolutional neural networks, recurrent neural networks, graph neural networks, and ensemble neural networks. The research also examines the latest trends in this feld and suggests possible future research directions. The primary focus of this survey is to showcase the signifcant advancements made by numerous researchers, especially in the areas of DL techniques and ensemble methods for SSTP. It also provides an in-depth analysis of the most commonly used SST datasets along with their data generation source, record period, accessible resolution criteria, strengths, and weaknesses. The ultimate goal of this investigation is to provide a theoretical framework and ontology to support SSTP