REAL Decision Lab

The developing REAL Decision Lab research program and current Mitacs Accelerate watershed research.

Research Lab · Developing research program

Resilient Agricultural Landscapes Decision Lab

How can agricultural landscapes remain productive while protecting water, soil, and ecosystems? REAL Decision Lab connects observation, understanding environmental processes, conservation planning, and learning from outcomes.

Four connected research areas

  1. 01 · OBSERVE

    Landscape Monitoring & Earth Observation

    What is changing, where, and when?

    Connect long-term monitoring, field observations, satellite imagery, and geospatial data.

  2. 02 · UNDERSTAND

    Environmental Processes, Modelling & GeoAI

    Why is it changing?

    Use process-based models and GeoAI—AI for geographic data—to explain patterns, pathways, and risk.

  3. 03 · PLAN

    Precision & Multi-Benefit Conservation

    What should be done, and where?

    Compare conservation options for water quality, ecosystems, production, cost, and resilience.

  4. 04 · DECIDE & LEARN

    Adaptive Decision Support & Learning

    What worked, and what should change next?

    Use indicators, practical decision-support tools, monitoring, and evaluation to update priorities.

Adaptive return from Area 4 to Area 1: Monitor outcomes, compare results with expectations, learn, update models and priorities, and observe again.

Adaptive learning · Area 4 → Area 1

  1. Monitor outcomes
  2. Compare results with expectations
  3. Learn
  4. Update models and priorities
  5. Observe again
↑ Return to Area 1: Observe

Shared outcomesWater quality · Healthy soils and ecosystems · Resilient production · Climate resilience

Current and developing projects

PhD foundation

Precision Conservation in Tile-Drained Agricultural Watersheds

Integrate geospatial analysis, machine learning, and watershed modelling to prioritise conservation practices.

Published foundations →

Under review · OMAFA proposal

Field-Specific Precision Conservation in Ontario’s Lake Erie Basin

Extend my PhD research using the Agricultural Conservation Planning Framework (ACPF) to compare conservation opportunities, expected benefits, and costs.

Proposal and project-team context →

Developing · Emerging methods

Earth Observation & GeoAI for Agricultural Landscapes

Extend established geospatial and modelling expertise to understand landscape change and environmental risk.

Current project: Healthy Lake Huron

Active Mitacs Accelerate research · Postdoctoral Scholar

From watershed evidence to conservation decisions

My current postdoctoral project at the University of Guelph works with Healthy Lake Huron partners. Ausable Bayfield Conservation Authority (ABCA) is the formal Mitacs partner.

  1. Monitoring & Data
  2. Modelling & Scenarios
  3. Indicators
  4. Decisions

Long-term tributary monitoring and high-resolution watershed models help explain nutrient and sediment loss and compare conservation and climate scenarios. Intended outputs include conservation-priority maps, indicator scorecards, and monitoring recommendations.

IMWEBs (Integrated Modelling for Watershed Evaluation of BMPs) is the project’s process-based watershed model. BMPs are beneficial management practices, such as cover crops, buffers, and drainage-water management.

Applied collaboration and partner context →

Methods and foundations

My established work combines GIS, environmental monitoring, machine learning, and watershed modelling. Earth observation and GeoAI are growing directions. Spatial optimisation means comparing where conservation actions could provide the greatest benefits within available resources and other constraints.

GIS & geostatisticsEnvironmental monitoringMachine learningWatershed modellingSpatial optimisationMulti-criteria decision analysis

Read the published research → · Discuss a collaboration →