Detecting small-scale mines in Ghana
Michael Lanzetta and Elena Terenzi offer an overview of a collaboration between Microsoft and the Royal Holloway University that applied deep learning to locate illegal small-scale mines in Ghana using satellite imagery, scaled training using Kubernetes, and investigated the mines' impact on surrounding populations and environment.
Talk Title | Detecting small-scale mines in Ghana |
Speakers | Elena Terenzi (Microsoft), Michael Lanzetta (Microsoft) |
Conference | Strata Data Conference |
Conf Tag | Making Data Work |
Location | London, United Kingdom |
Date | May 22-24, 2018 |
URL | Talk Page |
Slides | Talk Slides |
Video | |
Illegal small-scale mining is a growing industry in many developing countries. In these mines, gold and other precious minerals are extracted in a low-tech, labor-intensive process. While these mines provide huge employment and income potential for poverty-stricken communities, they are also linked to environmental damages, health hazards, and social ills. However, since these small mining operations are mostly illegal, there is virtually no data to analyze their exact impact. Michael Lanzetta and Elena Terenzi offer an overview of a collaboration between Microsoft and the Royal Holloway University, London, that applies deep learning to locate illegal small-scale mines in Ghana using satellite imagery and investigates their impact on surrounding populations and environment. The goal of the project is to enable better-informed policy decisions by relevant stakeholders. First, the team built an image classification model in Keras and scaled the training of the model using Kubernetes on Azure. Once the mines were identified, the team investigated the impact of those mines on surrounding environments and populations in Python.