We aim to design  and deploy artificial intelligence, data science  and mathematical methodologies and technologies for measuring and forecasting green house gas (GHG) emissions from oil sands tailing ponds (OSTP) and end pit lakes (EPL).  


  • Improve the accuracy of detection, quantification, and localization of methane emissions in the oil and gas sector for effective design of mitigation solutions;
  • Reduce uncertainties in methane emissions measurement and quantification;
  • Improve methods for the integration and/or standardization of multi-scale methane emissions data collected from different technologies for effective monitoring; and
  • Advance approaches for the timely reporting of emissions data to track the performance of producers’ emission reduction initiatives and provide actionable information to stakeholders

Subproject 1 Air  Quality monitoring device

 The aim is to design an air quality monitoring device that is capable of measuring several key pollutants and environmental factors, including: Methane, Particulate Matter, Carbon Monoxide, Nitrogen Dioxide, Sulfur Dioxide, Volatile Organic Compounds, Temperature and Humidity, Noise Levels, and Radiation Levels. It combines state-of-the-art air quality sensors with a low-cost Internet-of-Things (IoT) network architecture powered  by artificial intelligence. Detailed information about then project can be found here.

Subproject 2: A methane emission detection and response tool supported by artificial intelligence, mathematical models and a multi-source real-time data collection platform.

Alberta’s oil sector emits approximately 70 million tonnes of greenhouse gases (GHG) annually, with no set limits in place. A significant portion of these emissions comes from the methane produced by bacteria living in oil sands tailings ponds and end-pit lakes. Accurately predicting GHG emissions from oil sands tailings can play a crucial role in estimating specific emission limits to mitigate the impacts of climate change. Additionally, the methane generated by these bacteria can harm wildlife in end-pit lakes and the surrounding areas, hindering efforts for land reclamation.


The objective of this project is to develop and deploy AI, data science, and mathematical methodologies and technologies for methane emission detection, quantification, forecast and localization; GHG data management and processing, and real-time model validation and calibration using advanced computational methods.

Selected Publications related to this Theme

  1. Kong, J. D., Wang, H., Siddique, T., Foght, J., Semple, K., Burkus, Z., & Lewis, M. A. (2019). Second-generation stoichiometric mathematical model to predict methane emissions from oil sands tailings. Science of the total environment, 694, 133645.
  2. Kong, J. D., Salceanu, P., & Wang, H. (2018). A stoichiometric organic matter decomposition model in a chemostat culture. Journal of Mathematical Biology, 76, 609-644.
  3. Kong, J. D. (2017). Modeling microbial dynamics: effects on environmental and human health.