A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia

Abstract

The loss of huge areas of peat swamp forest in Southeast Asia and the resulting negative environmental effects, both local and global, have led to an increasing interest in peat restoration in the region. Satellite remote sensing offers the potential to provide up‐to‐date information on peat swamp forest loss across large areas, and support spatial explicit conservation and restoration planning. Fusion of optical and radar remote sensing data may be particularly valuable in this context, as most peat swamp forests are in areas with high cloud cover, which limits the use of optical data. Radar data can ‘see through’ cloud, but experience so far has shown that it doesn't discriminate well between certain types of land cover. Various approaches to fusion exist, but there is little information on how they compare. To assess this untapped potential, we compare three different classification methods with Sentinel‐1 and Sentinel‐2 images to map the remnant distribution of peat swamp forest in the area surrounding Sungai Buluh Protection Forest, Sumatra, Indonesia. Results show that data fusion increases overall accuracy in one of the three methods, compared to the use of optical data only. When data fusion was used with the pixel‐based classification using the original pixel values, overall accuracy increased by a small, but statistically significant amount. Data fusion was not beneficial in the case of object‐based classification or pixel‐based classification using principal components. This indicates optical data are still the main source of information for land cover mapping in the region. Based on our findings, we provide methodological recommendations to help those involved in peatland restoration capitalize on the potential of big data.

Mapping Natural Forest Remnants with Multi-Source and Multi-Temporal Remote Sensing Data for More Informed Management of Global Biodiversity Hotspots

“…Recent studies have shown that combining radar with optical data improves detection of tropical rainforests [88], mangrove forests [91], forest plantations [33], and upland vegetation [92], as well as forest attributes such as above-ground biomass or volume-growing stock [30,34,93]. Results of this study are in concordance with this knowledge as the best performing model included two microwave texture variable groups.…”

Improving the accuracy of land cover classification in cloud persistent areas using optical and radar satellite image time series

“…Unlike previous attempts to map peat land cover in the region creating a manual cloud‐free composite (see e.g. Crowson et al, ), no manual inputs are required (except to form the reference dataset, including persistent cloud cover polygons, but this step is essential to all supervised classifications); the proposed method is thus time‐saving and less sensitive to human errors.…”

“…The climate is tropical humid, with an average annual precipitation of 2,400 mm (Hapsari et al, ). Even during the dry season (June to September), monthly precipitation is above 100 mm, meaning that the region is primarily subject to a low level of seasonality (Aldrian & Susanto, ; Crowson et al, ; Karger et al, ).…”

“…These reference data were generated in an opportunistic way but ensure a good spatial distribution of the polygons over the whole study area (Figure ). We primarily used the same classes as Crowson et al (), namely peat swamp forest, water, urban, palm trees (all combined), acacia trees, fern/scrublands, bare ground; only a mangrove class was added to this original list. Mangrove polygons were digitized using the USGS Global distribution of mangroves (http://data.unep-wcmc.org/datasets/4).…”

“…Therefore, most land cover maps generated for these regions are based on single‐date (when cloud‐free images are available) or cloud‐free composites (see e.g. Crowson et al, ; Erinjery, Singh, & Kent, ). Cloud‐free composites can, however, be difficult and time‐consuming to build.…”