Mapping Tree Canopy Cover and Aboveground Biomass in Sudano-Sahelian Woodlands Using Landsat 8 and Random Forest

• Published in: Remote sensing (Basel, Switzerland) Vol. 7; no. 8; pp. 10017 - 10041
• Main Authors: Karlson, Martin, Ostwald, Madelene, Reese, Heather, Sanou, Josias, Tankoano, Boalidioa, Mattsson, Eskil
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 2015
• Subjects: aboveground biomass; Biomass; Canopies; Environmental research; Environmental Sciences related to Agriculture and Land-use; Fjärranalysteknik; Forest Science; Geosciences, Multidisciplinary; Imagery; Landsat; Landsat 8; Mapping; Mathematical models; Miljö- och naturvårdsvetenskap; multi-temporal imagery; Multidisciplinär geovetenskap; Natural resource management; Phenology; Random Forest; Remote Sensing; Skogsvetenskap; Sudano-Sahel; Texture; tree canopy cover; Trees; variable selection; woodland; Woodlands; Landsat 8; multi-temporal imagery; woodland; phenology; aboveground biomass; variable selection; tree canopy cover; Sudano-Sahel; Random Forest
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs70810017

Accurate and timely maps of tree cover attributes are important tools for environmental research and natural resource management. We evaluate the utility of Landsat 8 for mapping tree canopy cover (TCC) and aboveground biomass (AGB) in a woodland landscape in Burkina Faso. Field data and WorldView-2 imagery were used to assemble the reference dataset. Spectral, texture, and phenology predictor variables were extracted from Landsat 8 imagery and used as input to Random Forest (RF) models. RF models based on multi-temporal and single date imagery were compared to determine the influence of phenology predictor variables. The effect of reducing the number of predictor variables on the RF predictions was also investigated. The model error was assessed using 10-fold cross validation. The most accurate models were created using multi-temporal imagery and variable selection, for both TCC (five predictor variables) and AGB (four predictor variables). The coefficient of determination of predicted versus observed values was 0.77 for TCC (RMSE = 8.9%) and 0.57 for AGB (RMSE = 17.6 tons times ha-1). This mapping approach is based on freely available Landsat 8 data and relatively simple analytical methods, and is therefore applicable in woodland areas where sufficient reference data are available.