Wildfire mapping in interior alaska using deep neural networks on imbalanced datasets

Wildfires are the dominant disturbance impacting many regions in Alaska and are expected to intensify due to climate change. Accurate tracking and quantification of wildfires are important for climate modeling and ecological studies in this region. Remote sensing platforms (e.g., MODIS, Landsat) are valuable tools for mapping wildfire events (burned or burning areas) in Alaska. Deep neural networks (DNN) have exhibited superior performance in many classification problems, such as high-dimensional remote sensing data. Detection of wildfires is an imbalanced classification problem where one class contains a much smaller or larger sample size, and performance of DNNs can decline. We take a known weight-selection strategy during DNN training and apply those weights to MODIS variables (e.g., NDVI, surface reflectance) for binary classification (i.e., wildfire or no-wildfire) across Alaska during the 2004 wildfire year, when Alaska experienced a record number of large wildfires. The method splits the input training data into subsets, one for training the DNN to update weights and the other for performance validation to select the weights based on the best validation-loss score. This approach was applied to two sampled datasets, such as where the no-wildfire class can significantly outweigh the wildfire class. The normal DNN training strategy was unable to map wildfires for the highly imbalanced dataset; however, the weight-selection strategy was able to map wildfires very accurately (0.96 recall score for 78,702 wildfire pixels (500 × 500 m)).