Developing a land cover monitoring system for South Africa

Session

Remote Sensing

Full Paper Review

No

Authors

Konrad Wessels, CSIR-Meraka, South Africa,kwessels@csir.co.za

Abstract

Internationally land cover mapping activities are being retailored to land cover monitoring programs that focus continuous change detection with intermittent land cover maps being produced at set intervals. Furthermore with the abundance satellite data such Landsat 8 land cover mapping systems are moving away from using single date images to using time-series of data that capture phenology and land cover change more effectively.

Such a time series approach require the ability to handle large volumes of data, which in turn requires high levels of automation in data pre-processing, image classification and change detection. This paper reports on the progress made towards the development of a more automated land cover monitoring system for South Africa’s mapping agency, National Geospatial Information (NGI). The system is aimed at rapid update of land cover maps for previous mapped areas using highly-automated, intelligent training data generation, highly-scalable random forest classification, accuracy assessment, change detection and rapid operator validation using Landsat data.

The technology is aimed at assisting government and industry to provide land cover data at a much higher update frequency to address the insatiable user need for land cover products and services.

No full paper was submitted