Abstract
Understanding the drivers of land degradation and regeneration is crucial for planning appropriate responses within both degraded and non-degraded land. In this paper, using Kenya as the study area, we sought to identify the key drivers that affect greening and browning trends within the 4 main land cover types (agriculture, forest, grassland and shrubland) and within an area characterised by land cover change. The methodological approach used was the random forest classification algorithm, whereby the dependent variable was represented as 4 classes of NDVI greening and browning trends (strong browning, moderate browning, moderate greening, and strong greening). The explanatory variables (n = 28) were broadly grouped into 2 categories, natural and anthropogenic, and included a number of variables as proxies for broad socio-economic development. All models showed strong performance, and the mean values for accuracy and Kappa were 0.96 and 0.95, respectively. Variables that repeatedly featured as the 5 most important variables across the datasets were: travel time to an urban area, distance to towns, distance to roads, distance to rivers, slope and vulnerability to climate change impacts. When the variables were grouped by SDGs, the results obtained showed that the variables grouped under the SDGs 15 (life on land), 8 (economic growth) and 13 (climate action) cumulatively accounted for approximately 80% of the prediction of the greening and browning trends. Our results raise the following considerations to enrich on-going and future policy and planning discussions aimed at addressing LDN: the implementation of LDN should be anchored on tried and tested SLM interventions; further analysis of the drivers of greening and browning trends should be undertaken at the sub-national level; integrated approaches that lead to greater alignment across multiple development priorities, including climate change, should be promoted; and targeted enforcement of environmental legislation is needed to deter processes and activities that are likely to lead to the degradation of land.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Remote Sensing Applications: Society and Environment
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.