Deep-Learning-Based Gas Leak Source Localization From Sparse Sensor Data

Abstract

In this article, we address the problem of estimating the location of gas leak sources using sparse unreliable spatio-temporal chemical sensor data. We pose the task of estimating the underlying gas signal and predicting the source location as an inverse problem. For this purpose, we develop a novel deep-learning projection-based framework. We incorporate traditional projection-onto-convex-sets (POCS) iteration in the structure of the deep model to obtain a regularized solution that conforms to our prior knowledge of the spatio-temporal structure of the gas concentration distribution. We use discrete cosine transform (DCT) layers to model the smooth nature of the gas plume signal. In the DCT domain, we project the feature maps onto a low-pass region, whose boundary is determined during training using the backpropagation algorithm. This operation is equivalent to projecting onto a convex set. Furthermore, these projection operations are embedded in the nonlinear structure of a convolutional neural network. We address two different types of data: methane–propane leak from industrial plants and isopropyl alcohol (isopropanol) vapor leak in an indoor environment. Experimental results are presented. Our results show that we can obtain a smooth estimate of the underlying gas signal while obtaining a good source location prediction with high accuracy.