Integrating random forest and synthetic aperture radar improves the estimation and monitoring of woody cover in indigenous forests of South Africa
Open Access
- 21 February 2023
- journal article
- research article
- Published by Springer Nature in Applied Geomatics
- Vol. 15 (1) , 209-225
Abstract
Woody canopy cover (CC) is important for characterising terrestrial ecosystems and understanding vegetation dynamics. The lack of accurate calibration and validation datasets for reliable modelling of CC in the indigenous forests in South Africa contributes to uncertainties in carbon stock estimates and limits our understanding of how they might influence long-term climate change. The aim of this study was to develop a method for monitoring CC in the Dukuduku indigenous forest in South Africa. Advanced Land Observing Satellite (ALOS) Phased Arrayed L-band Synthetic Aperture Radar (PALSAR) global mosaics of 2008, 2015, and 2018, polarimetric features, and Grey Level Co-occurrence Matrix (GLCMs) were used. Machine learning models Random Forest (RF) vs Support Vector Machines (SVM) were developed and calibrated using Collect Earth Online (CEO) data, a free and open-access land monitoring tool developed by the Food and Agriculture Organisation (FAO). The addition of GLCMs produced the highest accuracy in 2008, R2 (RMSE) = 0.39 (36.04%), and in 2015, R2 (RMSE) = 0.51 (27.82%), and in 2018, only SAR variables gave the highest accuracy R2 (RMSE) = 0.55 (29.50). The best-performing models for 2008, 2015, and 2018 were based on RF. During the ten-year study period, shrubland and wooded grassland had the highest transition, at 6% and 13%, respectively. The observed changes in the different canopies provide valuable insights into the vegetation dynamics of the Dukuduku indigenous forest. The modelling results suggest that the CEO calibration data can be improved by integrating airborne LiDAR data.Keywords
Funding Information
- National Research Foundation
- University of Pretoria
This publication has 70 references indexed in Scilit:
- Spectroscopic Determination of Aboveground Biomass in Grasslands Using Spectral Transformations, Support Vector Machine and Partial Least Squares RegressionSensors, 2013
- The Past in the Present: Struggles Over Land and Community in Relation to the Dukuduku Claim for Land Restitution, South AfricaForum for Development Studies, 2013
- Essential Biodiversity VariablesScience, 2013
- A universal airborne LiDAR approach for tropical forest carbon mappingOecologia, 2011
- Forests and Climate Change: Forcings, Feedbacks, and the Climate Benefits of ForestsScience, 2008
- Properties of ERS-1/2 coherence in the Siberian boreal forest and implications for stem volume retrievalRemote Sensing of Environment, 2007
- Empirical relationships between AIRSAR backscatter and LiDAR-derived forest biomass, Queensland, AustraliaRemote Sensing of Environment, 2006
- Practical selection of SVM parameters and noise estimation for SVM regressionNeural Networks, 2004
- Standardizing the calculation of the annual rate of deforestationForest Ecology and Management, 2003
- Support-vector networksMachine Learning, 1995