Dynamic Identification and Risk Analysis of Tailings Dam Failure for Mining Operations
Recently, there have been multiple failures of large tailings dams that store mining wastes, around the world, with devastating impacts (e.g., https://en.wikipedia.org/wiki/Brumadinho_dam_disaster). These dams are unique in that they continue to be raised as waste piles up and can get as tall as 400m. The risk and impact of failure increases as the dam gets taller. There are several thousand such dams around the world. The concept of the project is to develop a continuous status monitoring and risk analysis of these dams, automatically, using globally available satellite data from multiple bands, as well as regularly updated climate data products. Overtopping of the dam during an intense or persistent rainfall event is the leading mode of failure. Foundation failure which leads to a liquefaction or deformation of the dam is the second leading failure mode.
The intern will help develop initial examples and machine learning based tools to a) identify dams from satellite imagery given their approximate location (known mine locations, but not dam locations), b) monitor changes in dam height, waste perimeter and height behind the dam, and c) integrate this information with precipitation and soil moisture information into a spatio-temporal risk product for threshold exceedances. A variety of tools, including CNN, semantic segmentation, spatio-temporal models using Markov Random fields and Support vector machines are candidates for different aspects of the analysis. We have identified ~ 4000 dam locations, 200 manually classified images of dams, 60 a variety of satellite and climate data products, and preliminary CNN based classification work, and a Bayesian failure impact model has been done. If this proof of concept work that we want to do is successful, we expect to develop a larger project for external funding.
This is project is NOT accepting applications.
- Professor: upmanu lall
- Department/School: Earth & Environmental Engineering, SEAS
- Location: 842 Mudd
- Climate and Water Risk Assessment & Mitigation. Water Sustainability. Decentralized Infrastructure Networks. Systems Optimization and Economics
- Earliest starting date: 10/15/2019
- End date: 9/1/2020
- Number of hours per week of research expected during Fall 2019: ~15
- Skill sets: Machine Learning, Statistics, Geospatial Modeling
- Student eligibility:
freshman, sophomore, junior, senior, master’s
- International students on F1 or J1 visa: eligible