The Bow, Mountain View Room, 500 Centre St S,
Calgary AB
Canada
In person with webinar option.
Environmental Contaminated Sites professionals have a challenging role to obtain a clear picture of the contamination impacts to soil and groundwater on their sites. Factors such daily and seasonal groundwater fluctuations, challenging lithology, and the cost of invasive sampling work impede the ability to achieve consistent, representative data required to adequately assess risk and confidently make decisions on next steps. The traditional approach includes:
- Routine sampling of water and soil is typically used to estimate pollutant fate and transport.
- Owners incorporate this sporadic data into their conceptual site models, then plan and evaluate remedial action plans.
- Groundwater and soil fate models become challenging to calibrate with limited data points and often fail to capture changing site conditions even when calibrated.
Environmental Material Science Inc. (EMS) provides a new generation of contaminated site modeling to overcome prior site model’s limitations. By leveraging increased data density from cost-effective IoT sensors, EMS data facilitates models that continuously calibrate, update, and improve predictability and enable adaptive management of contaminated sites.
EMS manufactures and deploys subsurface sensors from our Saskatoon headquarters. These autonomous sensors measure hydrocarbons in soil and groundwater, in addition to measuring temperature, pressure, humidity, as well as methane, carbon dioxide, oxygen, and nitrous oxide concentrations. These sensors transmit data as frequent as every 30 minutes wirelessly via secure LoRaWan channels. From there data is fed into our models and continually updated through highly parameterized inversion using the Parameter Estimation (PEST++) software suite.
EMS presents a family of artificially intelligent models that leverages the latest in modern data assimilation to quantify and reduce the uncertainty in contaminant fate and transport modeling. We will show how these models can be continuously updated with our low footprint, low power, cost-effective sensors to overcome traditional limitations with modeling. Our case studies will highlight real-world examples of EMS’ AI Modeling and Remote Autonomous Sensor Technology providing clear data trends, in months, to enable faster pathways to closure.
Presenter: Nico Higgs, Environmental Material Science (EMS)