Global Land Temperature Forecasting Using Long Short-Term Memory Network

Abstract

Based on NASA’s 40 years of satellite data, earth has experienced drastic climatic changes in the form of sea-level rise, an increase in oceanic and atmospheric temperatures, depletion of the Ozone layer, and decrease in sea ice and snow cover. These observations point to the fact that the world is getting warmer, which significantly impacts humans and ecological systems. Forecasting global land temperature could help to identify the extent of devasting consequences on the natural habitat and shed light on the impact of policies, designed to mitigate them. Previous studies have attempted to forecast regional temperatures using traditional machine learning models. This paper uses a standard multi-layer perceptron, a simple Recurrent Neural Network, and a Long Short-Term Memory network to forecast next month’s global land temperature. Our results show that deep learning outperforms traditional machine learning models, including decision tree, random forest, and ridge regression.