Environment & Climate Change

At AIMMLab, our environment and climate research applies AI, mathematical modelling, and data science to some of the most urgent ecological challenges facing Canada and the world from greenhouse gas emissions in Alberta's oil sands to the collapse of aquatic food webs under a warming climate. This work sits at the intersection of the lab's Climate & Environment and Health & Well-Being thematic pillars, recognising that environmental degradation and human health are inseparable.

Greenhouse Gas Emissions & Air Quality Monitoring

Environmental conditions including weather patterns, seasonal temperature shifts, and industrial bitumen production directly influence methane biogenesis rates from Oil Sands Tailings Ponds (OSTP) and End Pit Lakes (EPL) in Alberta. Methane is a potent greenhouse gas with a global warming potential more than 80 times that of CO₂ over a 20-year period, yet emissions from these industrial sites remain poorly quantified and difficult to monitor at scale.

AIMMLab addresses this gap by combining data mining, satellite imagery, real-time IoT sensor networks, and AI-driven analysis to detect, quantify, and forecast methane emissions informing both regulatory frameworks and land reclamation strategies.

AIr System — Smart Air Quality Monitoring

The AIr System is AIMMLab's low-cost IoT and AI-powered air quality monitoring platform, designed to democratise access to environmental data in both developed and developing regions. It monitors a broad range of pollutants and environmental factors including methane, particulate matter (PM2.5/PM10), CO, NO₂, SO₂, VOCs, temperature, humidity, noise, and radiation and delivers timely, scalable air pollution forecasts to support public health decisions.

Subproject 1: Smart Monitoring Device

Development of a field-deployable device monitoring methane, particulate matter, CO, NO₂, SO₂, VOCs, temperature, humidity, noise, and radiation providing continuous, multi-pollutant sensing at scale.

Subproject 2: Methane Detection Platform

Targeting Alberta's oil sands OSTP and EPL, this platform integrates real-time AI, mathematical modelling, and field data to set evidence-based emissions limits and inform long-term land reclamation strategies.

Expected Outcomes

  • Improved detection and quantification of methane and multi-pollutant emissions from industrial sites
  • Reduced uncertainty in large-scale GHG emission measurements
  • Standardised, multi-scale monitoring frameworks applicable across oil sands and beyond
  • Actionable, policy-relevant insights for climate change mitigation and land reclamation
GHG Monitoring Pipeline Flow from IoT sensors through AI analysis to policy outcomes for greenhouse gas monitoring. IoT Sensors Field & satellite data AI & ML Analysis Pattern detection & forecast Emission Forecasts Quantified, real-time outputs Policy & Mitigation Regulations & land reclamation

Figure: AIMMLab's GHG monitoring pipeline — from IoT field sensors to evidence-based climate policy.

Aquatic Ecosystem Dynamics

Aquatic ecosystems — lakes, rivers, and oceans — are among the most sensitive indicators of planetary health, yet they are under mounting pressure from climate change, industrial activity, and anthropogenic disturbance. AIMMLab uses AI and mathematical modelling to understand how these pressures reshape aquatic systems, from fish populations to the microscopic organisms that underpin all life on Earth.

Subproject 1: Fish & Fishing Community Adaptation

This subproject investigates the complex interactions between rapid climate change, fishing pressure, and marine sustainability and how communities adapt their livelihoods and governance in response.

Key questions: How do climate shifts alter species abundance and distribution? What governance structures promote sustainable fisheries? How do coastal communities adapt when ecosystems change faster than policy?

Subproject 2: Phytoplankton Dynamics Modelling

Phytoplankton are responsible for nearly 50% of global oxygen production and form the foundation of the marine food web. They regulate atmospheric CO₂ through the biological pump transporting billions of metric tons of carbon to the ocean floor each year. AIMMLab models how light availability, nutrient levels (nitrogen, phosphorus), water column depth, and temperature change affect phytoplankton growth, distribution, and carbon sequestration capacity with direct implications for climate forecasting and ocean health policy.

Why phytoplankton matter: Despite being invisible to the naked eye, phytoplankton produce roughly half the oxygen in Earth's atmosphere and drive the ocean's biological carbon pump sequestering an estimated 10 billion metric tons of carbon from the atmosphere each year. As global temperatures rise, warmer and more stratified oceans reduce nutrient availability in surface waters where phytoplankton live, threatening both marine food webs and the planet's primary carbon sink. Understanding and predicting these dynamics is one of the most consequential challenges in Earth system science.

Research Outcomes

  • Predictive models for fish population responses to climate velocity and fishing pressure
  • Evidence-based recommendations for sustainable fisheries governance and community adaptation
  • High-resolution phytoplankton dynamics models linking nutrient cycles, carbon sequestration, and ocean health
  • Integrated climate-health insights applicable to Canadian, African, and global aquatic ecosystems

📚 Selected Refereed Journal Publications

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. Science of the total environment, 694, 133645. .

Kong, J. D., Salceanu, P., & Wang, H. (2018). A stoichiometric organic matter decomposition model in a chemostat culture. Journal of Mathematical Biolog, 11, 76, 609-644. .