Detecting Deforestation Using Robust Online Bayesian Monitoring

• Activity Number: 561 - Statistical Analyses for Environmental Monitoring
• Type: Contributed
• Date/Time: Thursday, August 11, 2022 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Laura J Wendelberger* and Brian James Reich and Alyson G Wilson and Josh M Gray
• Companies: North Carolina State University and North Carolina State University and North Carolina State University and North Carolina State University
• Keywords: monitoring; outliers; remote sensing; robust; streaming data

Abstract

Near real time change detection is important for a variety of Earth monitoring applications and remains a high priority for remote sensing science. Data sparsity, subtle changes, seasonal trends, and the presence of outliers make detecting actual landscape changes challenging. Adams and MacKay (2007) introduced Bayesian Online Changepoint Detection (BOCPD), a com- putationally efficient, exact Bayesian method for change detection. In this paper, we conduct BOCPD with a multivariate linear regression framework that supports seasonal trends. We adapt BOCPD to introduce Robust Online Bayesian Monitoring (roboBayes), which includes a mechanism to make BOCPD robust against occasional outliers, such as corrupted images, without compromising the computational efficiency of an exact posterior. Without this robustness feature, the change detection algorithm cannot be employed autonomously without an inflated false positive rate. The method is then applied to monitor deforestation events in Myanmar.