Analyzing Multispectral Satellite Imagery of South American Wildfires Using Deep Learning

TL;DR

This study develops a deep learning approach using multispectral satellite imagery to detect wildfires in South America, demonstrating that feature engineering can reduce computational costs without sacrificing accuracy.

Contribution

It introduces a novel wildfire detection model trained on Landsat 8 data and shows how image segmentation improves training efficiency.

Findings

High validation and test accuracy achieved.

Feature engineering reduces training time.

Segmentation maintains accuracy while simplifying data.

Abstract

Since frequent severe droughts are lengthening the dry season in the Amazon Rainforest, it is important to detect wildfires promptly and forecast possible spread for effective suppression response. Current wildfire detection models are not versatile enough for the low-technology conditions of South American hot spots. This deep learning study first trains a Fully Convolutional Neural Network on Landsat 8 images of Ecuador and the Galapagos, using Green and Short-wave Infrared bands to predict pixel-level binary fire masks. This model achieves a 0.962 validation F2 score and a 0.932 F2 score on test data from Guyana and Suriname. Afterward, image segmentation is conducted on the Cirrus band using K-Means Clustering to simplify continuous pixel values into three discrete classes representing differing degrees of cirrus cloud contamination. Three additional Convolutional Neural Networks are trained to conduct a sensitivity analysis measuring the effect of simplified features on model accuracy and train time. The Experimental model trained on the segmented cirrus images provides a statistically significant decrease in train time compared to the Control model trained on raw cirrus images, without compromising binary accuracy. This proof of concept reveals that feature engineering can improve the performance of wildfire detection models by lowering computational expense.