Big geospatial data analysis for Canada's Air Pollutant Emissions Inventory (APEI): using google earth engine to estimate particulate matter from exposed mine disturbance areas

Particulate Matter (PM) emissions originating from mine waste and mine tailings can be hazardous to human health, depending on the ore type and processes used to extract ore. Until now, only a single, simple estimate of the total area of mine waste area across all of Canada has been available for calculating air quality emissions from this source. This single estimate, based on manual satellite interpretation completed in 1977, was extrapolated to estimate mine areas for all years from 1990 to the present. These area estimates were used annually to calculate the particulate matter from mines for the Canadian Air Pollutant Emissions Inventory (APEI); however, there is high uncertainty in these measurements of mine area and therefore in emissions estimates. In order to increase certainty in emissions estimates, the exposed mine waste areas must be mapped for each year. Mapping mine waste over areas as large as the Canadian landmass requires enormous quantities of data and considerable computational power, which will be compounded when a time-series analysis is required. Therefore, in this study, we have employed Google Earth Engine (GEE) Javascript API to map exposed mine areas in four "benchmark" years (1990, 2000, 2010, and current year 2018) as part of the APEI. A random forest classifier was trained using two separate datasets (Landsat-5 year 2000; and a combination of Landsat-8, Sentinel-1, and Sentinel-2 for the year 2018). Transfer learning was then used to apply the year 2000 model to the year 1990 and 2010 Landsat-5 imagery, which produced classification results for the four "benchmark" years in our time series. This tool has enabled the monitoring of mine growth over a 30-year period and has confirmed that overall the area of mines is growing in Canada. Overall, Google Earth Engine proved to be an invaluable tool in mapping exposed mine waste areas and would be similarly useful for any organization with large-area monitoring mandates or those interested in time-series analysis of the Landsat archive.