A remote sensing-based approach to investigate changes in land use and land cover in the lower uMfolozi floodplain system, South Africa

Abstract

The goal of this study was to understand land use and land cover (LULC) changes within the lower uMfolozi floodplain system, South Africa, and relate those changes to wetland loss. Changes in LULC were assessed using a geographic object-based image analysis (GEOBIA) algorithm to classify multi-date Landsat images into eight cover types over a period of 20 years, between 1997 and 2017. Post-classification accuracy assessment of all map-outputs was conducted by compiling confusion matrixes and calculating producer, user, and global accuracies and kappa coefficients (K) for each map-output. Levels of accuracy for all map-outputs were within acceptable limits, ranging between 79% and 88% (K = 0.76 and 0.86, respectively). Thereafter, paired t-tests were applied to determine whether the changes in LULC over the study period were significant. Results of this investigation showed a significant (p-value, < 0.01) conversion of wetland to cultivation, by 14%. This finding is important because it demonstrates that in this environment, human agency is one of the major drivers of a persistent decrease in the wetland ecosystem. The major insight from this observation is that there is an urgent need to formulate and implement objectively informed interventions to enhance the sustainability of the uMfolozi floodplain system and that of others elsewhere.