Designing a Classifier for Active Fire Detection From Multispectral Satellite Imagery Using Neural Architecture Search

Wildfires are becoming increasingly devastating, and detecting them early is essential to containing them. Deep learning-based wildfire detection systems have increased in complexity dramatically in recent years, and in order to manage this added complexity, techniques have been proposed to automate the design of neural network architectures. Such techniques are usually referred to as neural architecture search (NAS). This article showcases the use of a reinforcement learning-based neural architecture search (NAS) agent to design a small neural network to perform active fire detection on multispectral satellite imagery. Specifically, we aim to automatically design a neural network that can determine if a single multispectral pixel is a part of a fire, and do so within the constraints of a low earth orbit nanosatellite with a limited power budget, to facilitate on-board processing of sensor data. A regression model that predicts the F1 score obtained by a particular architecture following quantization is used as a reward function. This model is trained on the classification performance statistics of a sample of neural network architectures. Besides the F1 score, we also include the total number of parameters in our reward function to limit the size of the designed model. Finally, we deployed the best neural network to the Google Coral Micro Dev Board and evaluated its inference latency and power consumption. This neural network consists of 1716 parameters, takes on average 984 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mu$</tex-math></inline-formula>s to inference, and consumes around 800 mW to perform inference. These results show that our approach can be applied to new problems.