Acid Mine Drainage (AMD) and Coal Mine Drainage (CMD) Detection System: Advanced Remote Sensing for Environmental Monitoring

  The detection of cryptic pollution, particularly coal mine drainage (CMD) neutralized by carbonate
  bedrock, remains a significant challenge in hydrogeology because these waters often retain toxic
  sulfate loads despite exhibiting a neutral pH. This automated remote sensing workflow identifies
  these anomalies without constant extensive ground sampling. We adapted the automated AMD detection
  method originally proposed by Rockwell et al. (2021) for the USGS, translating the workflow into
  custom Python algorithms for rapid processing of Landsat 8/9 and Sentinel-2 for higher resolution
  results. The method was modified to detect spectral anomalies specifically within water bodies,
  utilizing the iron sulfate index and new filtering equations to map potential pollution dispersion.
  Preliminary application to Ganau Pond (Kurdistan Region, Iraq), a site with high sulfate (>700 mg/L),
  revealed distinct spectral increases corresponding with suspected pollution inflows. Validated against
  ground truth geochemical data from the Muskingum Watershed, Ohio. This research presents a cost-effective,
  automated tool for preliminary water quality assessment in data-scarce regions. Presented at the 40th
  Annual Graduate Research Symposium, Kent State University.

Visit My Website: https://www.climtawy.com
Check my Poster @ResearchGate: https://www.researchgate.net/publication/403521974_Automating_the_Detection_of_Cryptic_Sulfate_Pollution_Python_and_Machine_Learning_Implementation_for_Neutralized_Waters?utm_source=twitter&rgutm_meta1=eHNsLTc1cXZKeXF5YS84eFdZemFPUUllQS9DQ1JYL0o4OFF0TnlxelpNbFp6L0JRQ2tldXJLd3VRN2JQZ01xU2tvNStjcWMxSGpXUVVEdVRNSjFjMEl4QTJWUT0%3D