Year-end Sale % OFF 
Abstract
Abstract. In recent years, the methods for detecting structural changes in time series have been adapted for forest disturbance monitoring using satellite data. The BFAST (Breaks For Additive Season and Trend) Monitor framework, which detects forest cover disturbances from satellite image time series based on empirical fluctuation tests, is particularly used for near real-time deforestation monitoring, and it has been shown to be robust in detecting forest disturbances. Typically, a vegetation index that is transformed from spectral bands into feature space (e.g. normalised difference vegetation index (NDVI)) is used as input for BFAST Monitor. However, using a vegetation index for deforestation monitoring is a major limitation because it is difficult to separate deforestation from multiple seasonality effects, noise, and other forest disturbance. In this study, we address such limitation by exploiting the multi-spectral band of satellite data. To demonstrate our approach, we carried out a case study in a deciduous tropical forest in Bolivia, South America. We reduce the dimensionality from spectral bands, space and time with projective methods particularly the Principal Component Analysis (PCA), resulting in a new index that is more suitable for change monitoring. Our results show significantly improved temporal delay in deforestation detection. With our approach, we achieved a median temporal lag of 6 observations, which was significantly shorter than the temporal lags from conventional approaches (14 to 21 observations).
Highlights
Near real-time change monitoring has important application in forest management
Monitoring deforestation on single vegetation index has several limitations: 1) the harmonic model might not be sufficient to capture the complex seasonality in tropical forest, 2) one model is not sufficient for spatially heterogeneous tree species. 3) deforestation can be hard to separate from drought, other disturbances, and noise, 4) training data is required to identify if the detected change is deforestation
Our results show that using the score of PC3 has resulted in significantly improved overall accuracy and a shorter temporal delay than when monitoring deforestation using normalised difference moisture index (NDMI) index(Table 1)
Summary
Near real-time change monitoring has important application in forest management. Open access to satellite data (e.g Landsat and Sentinels) enables for near real-time detection of forest disturbance using advanced time series analysis methods (Banskota et al, 2014; Forkel et al, 2013; Kuan and Hornik, 1995). Most of the recent studies on near real-time forest disturbance monitoring have applied BFAST Monitor (Verbesselt et al, 2012), which detects forest disturbances by identifying a historical period, fit a linear regression model for historical time series, and monitor change in newly acquired observation either with a cumulative sum (CUSUM) or moving sums (MOSUM) process of the differences between new data and model predictions. Studies applying BFAST monitor mostly use normalised difference vegetation index (NDVI), normalised difference moisture index (NDMI), and enhanced vegetation index (EVI). These indices contrast the absorption and reflection properties of vegetation between near or short-wave infrared bands and visible bands. Recent studies attempted to solve the limitation (3) by integrating data from two sensors and introducing a climate variable (Dutrieux et al, 2015), or attempted to reduce the effect of multiple seasonality with a vegetation index that is normalized to spatially neighboring pixels (Hamunyela et al, 2016)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
