Monitoring Deforestation Using Multivariate Bayesian Online Changepoint Detection with Outliers

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 computationally efficient, exact Bayesian method for change detection. Incorporation of prior information allows for relaxed dependence on dense data and an extensive stable period, making this method applicable to relatively short time series and multiple changepoint detection. In this paper we conduct BOCPD with a multivariate linear regression framework that supports seasonal trends. We introduce a mechanism to make BOCPD robust against occasional outliers without compromising the computational efficiency of an exact posterior change distribution nor the detection latency. We show via simulations that the method effectively detects change in the presence of outliers. The method is then applied to monitor deforestation in Myanmar where we show superior performance compared to current online changepoint detection methods.

[1]  S. Panchapakesan,et al.  Inference about the Change-Point in a Sequence of Random Variables: A Selection Approach , 1988 .

[2]  Ryan P. Adams,et al.  Bayesian Online Changepoint Detection , 2007, 0710.3742.

[3]  Diane J. Cook,et al.  A survey of methods for time series change point detection , 2017, Knowledge and Information Systems.

[4]  P. Fearnhead,et al.  Optimal detection of changepoints with a linear computational cost , 2011, 1101.1438.

[5]  Paul Fearnhead,et al.  On optimal multiple changepoint algorithms for large data , 2014, Statistics and Computing.

[6]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[7]  Curtis E. Woodcock,et al.  Improved change monitoring using an ensemble of time series algorithms , 2020 .

[8]  Rob J Hyndman,et al.  Detecting trend and seasonal changes in satellite image time series , 2010 .

[9]  P. Fearnhead,et al.  On‐line inference for multiple changepoint problems , 2007 .

[10]  Yukun Lin,et al.  A change detection method using spatial-temporal-spectral information from Landsat images , 2020, International Journal of Remote Sensing.

[11]  Martin Herold,et al.  Transitioning from change detection to monitoring with remote sensing: A paradigm shift , 2020 .

[12]  M. Claverie,et al.  Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product. , 2016, Remote sensing of environment.

[13]  Benjamin Letham,et al.  Forecasting at Scale , 2018, PeerJ Prepr..

[14]  M. Herold,et al.  Near real-time disturbance detection using satellite image time series , 2012 .

[15]  C. Woodcock,et al.  Continuous monitoring of forest disturbance using all available Landsat imagery , 2012 .

[16]  C. Woodcock,et al.  Continuous change detection and classification of land cover using all available Landsat data , 2014 .

[17]  Piotr Fryzlewicz,et al.  Wild binary segmentation for multiple change-point detection , 2014, 1411.0858.

[18]  A. Scott,et al.  A Cluster Analysis Method for Grouping Means in the Analysis of Variance , 1974 .

[19]  Belinda A. Margono,et al.  Humid tropical forest disturbance alerts using Landsat data , 2016 .

[20]  Jan Verbesselt,et al.  A Bayesian Approach to Combine Landsat and ALOS PALSAR Time Series for Near Real-Time Deforestation Detection , 2015, Remote. Sens..

[21]  Rob J Hyndman,et al.  Phenological change detection while accounting for abrupt and gradual trends in satellite image time series , 2010 .

[22]  J. Hartigan,et al.  A Bayesian Analysis for Change Point Problems , 1993 .

[23]  Paul Fearnhead,et al.  Changepoint Detection in the Presence of Outliers , 2016, Journal of the American Statistical Association.

[24]  Raphael Gottardo,et al.  On-line changepoint detection and parameter estimation with application to genomic data , 2012, Stat. Comput..

[25]  Joshua I. Gold,et al.  Bayesian Online Learning of the Hazard Rate in Change-Point Problems , 2010, Neural Computation.

[26]  R. Oaxaca.  Another Look at Tests of Equality between Sets of Coefficients in Two Linear Regressions , 1974 .

[27]  P. Perron,et al.  Estimating and testing linear models with multiple structural changes , 1995 .

[28]  Theodoros Damoulas,et al.  Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection , 2018, ICML.