Estimating Deforestation using Machine Learning Algorithms

Keanu Nichols, Patrick Hosein

Abstract: Due to the urgency of the Climate Change phenomenon, it has become important to estimate the rate of deforestation in various countries since forests are essential for oxygen generation. The advent of popular machine learning algorithms, such as those that are applied to the field of computer vision, has led to the use of approaches, such as fully convolutional neural networks (FCN), for performing semantic segmentation on satellite images to determine forested and non-forested areas. However, these models tend to be computationally intensive and, even with the advancement of specialized hardware such as GPU’s (Graphical Processing Units), these approaches can still be quite costly especially for Small Island Developing States (SIDS) which are dis-proportionally affected by Climate Change. We consider the use of less computationally intensive approaches such as, logistic regression, linear support vector machine and Naive Bayes to achieve similar performance to a FCN but at a much lower cost. We perform semantic segmentation on satellite images to determine the percentage of forested areas and use this information to determine the rate of change of deforestation over a period of time. We compare the performance, computing requirements, storage requirements and robustness of different Machine Learning techniques.