Mapping Construction Grade Sand: Stepping Stones Towards Sustainable Development
Keywords: Sand mining, Sustainable development, Information systems, Geographic information system, Computing methodologies, Object detection
TL;DR: We develop machine learning methods to map the world’s sand and gravel resources, as a first step towards creating effective policy that can ameliorate the harms of excessive sand mining, while achieving sustainable development
Abstract: Sand and gravel are critical inputs to economic growth as the primary constituents of concrete and asphalt. While demand for these materials has skyrocketed due to large construction and reclamation demands, rates of extraction are unsustainable and result in adverse environmental and socio-economic consequences, especially in the Global South. Excessive sand and gravel mining threatens biodiversity and hydrological functions, heightens the risk of damage to critical infrastructure, and increases vulnerability to extreme climatic events. In this paper, we argue that mapping the world’s sand and gravel resources is the first step towards informing effective policy that can ameliorate these harms while achieving sustainable development. We have developed flexible machine learning algorithms which can detect construction-grade sand and gravel resources in river basins and coastlines at global scale with high spatial resolution (10 m). Our approach uses object based image analysis methods fusing freely available Sentinel-1 and Sentinel-2 multispectral satellite datasets. This method achieves an F1 score of 87.5% and accuracy of 88.71% using a random forest classifier trained on a newly aggregated global dataset of in-situ grain size observations. We further validate performance in sections of the River Ganga where a gravel to sand transition is known to occur, and in a section of the River Sone where a number of known sand mining concessions exist. This work lays the foundation to build end-to-end deep learning models that can predict where illegal sand mining occurs.
Submission Number: 2
Loading