Where Data Science
Meets Domain Expertise

Commodity Price Forecasting

Using deep learning architectures including LSTM networks and Transformer models to forecast commodity market prices across multiple time horizons. The models incorporate multi-variate time-series data and custom attention mechanisms for improved prediction accuracy.

Key Techniques

Approach

• • Multi-horizon forecasting with custom neural architectures
• • Feature engineering from macroeconomic and market indicators
• • Ensemble methods combining statistical and DL models
• • Backtesting framework for strategy evaluation

Retirement Decumulation Modeling

Ruin probability comparison across 10 withdrawal strategies at varying initial wealth levels

Developing stochastic models for optimal retirement portfolio withdrawal strategies. This work applies Monte Carlo simulation and risk-adjusted frameworks to determine sustainable decumulation rates under various market conditions and longevity scenarios.

Key Techniques

Research Focus

• • Optimal withdrawal rate modeling under market volatility
• • Longevity risk integration into decumulation strategies
• • Dynamic asset allocation during retirement phase
• • Core researcher at Canada’s Financial Wellness Lab

Hydrogen Integrated Greenhouse Horticultural (HIGH) Energy Project

Funded by Ontario’s Independent Electricity System Operator (IESO) through the Hydrogen Innovation Fund, the HIGH Energy project explores using wind-powered green hydrogen to decarbonize the greenhouse sector in Southwestern Ontario. Led by the University of Windsor in collaboration with Kruger Energy and the Ontario Greenhouse Vegetable Growers, this research assesses the technical and economic feasibility of blending hydrogen with natural gas to provide clean heat and power for large-scale horticultural facilities.

The Part 1 report identifies a lowest levelized cost of hydrogen (LCOH) of CAD $4.6/kg using a 10% H₂/90% natural gas blend at $33.07/MWh electricity rate. Economic viability is optimized at 5 days of storage and 2,190 annual operating hours, with analysis covering 9 scenarios across various blending ratios and delivery methods.

Key Techniques

Research Scope

• • 9 scenarios across H₂ blending ratios (10%, 20%, 100%) and delivery methods
• • Wind-powered PEM electrolysis coupled with 200MW wind farm
• • Levelized cost, payback period, IRR, and discounted payback analysis
• • Market analysis and regulatory review for Ontario grid integration

Project Links

Road Salt Environmental Analysis

Data-driven environmental impact assessment of road salt application in Canadian municipalities. Statistical modeling of chloride contamination in freshwater ecosystems, groundwater, and soil, with predictive frameworks for long-term environmental effects.

Key Techniques

Research Areas

• • Chloride contamination trend analysis in waterways
• • Predictive modeling of ecosystem impact
• • Alternative de-icing strategy evaluation
• • Policy recommendations based on data analysis

Microplastics Detection via ML

DETR object detection output: microplastics classified as Glitter (1.00) and Fragment (0.99) from Great Lakes samples

Using DETR (Detection Transformer) and CNN-based deep learning to automate the detection and classification of microplastics gathered from the Great Lakes. Applying state-of-the-art object detection models for rapid, accurate identification of microplastic particles in environmental samples.

Key Techniques

Methodology

• • DETR (Detection Transformer) for microplastic detection
• • CNN-based classification of microplastic types
• • Great Lakes environmental sample analysis
• • Object detection pipeline for automated identification

Medical Imaging AI

Brain image generation using Denoising Diffusion Probabilistic Models (DDPM) — created by Dr. Petrov

14+ years of medical imaging research at the Robarts Research Institute. Expertise spans deep learning for MRI motion correction, metal artifact reduction in CT, cardiac micro-CT imaging, and diffusion-based generative models for brain image synthesis.

Key Techniques

Selected Work

• • Deep learning motion correction for multichannel MRI (NMR in Biomedicine, 2024)
• • Brain image generation with DDPM diffusion models
• • Metal artifact reduction in CT scans
• • Cardiac micro-CT iterative reconstruction
• • 3D cardiac imaging with portable cone-beam scanner

Credibility Depletion in Strategic Bargaining

Belief evolution trajectories: DP-optimal vs bluff-heavy bargaining strategies

Exploring negotiation tactics via dynamic programming and reinforcement learning. The model captures how credibility depletes over multiple bargaining rounds and derives optimal offer strategies under reputation dynamics. Joint work with Matt Davison, targeting the journal Group Decision and Negotiation (GDN).

Key Techniques

Key Results

• • DP-optimal strategy outperforms bluff-heavy heuristics by +0.292 utility
• • Continuous-reputation and terminal-penalty robustness checks strengthen the mechanism
• • Two-player bilateral extension with equilibrium analysis
• • Paper at v14 after 9 rounds of AI-assisted peer review

Belief-State DP for Submarine-Launched UUV Reserve Management

Formulating the reserve-management problem for submarine-launched unmanned underwater vehicles (UUVs) as a partially observable stochastic control problem. The mothership carries a typed inventory of ISR, mine countermeasures (MCM), and anti-submarine warfare (ASW) vehicles, with a shared handling bottleneck preventing simultaneous launches. The hidden threat follows a three-state continuous-time Markov chain (peacetime, tension, conflict). Joint work with Matt Davison, NSERC-supported.

Key Techniques

Key Results

• • Optimal policy yields mean reward of 12.54 vs 8.36 (myopic) over 4,000 Monte Carlo missions
• • Hold region occupies ~77% of belief simplex at mission start
• • ISR dominates in tension; MCM/ASW emerge only under high conflict posterior
• • Flexibility premium increases with regime volatility and vehicle endurance

Optimal Stockpiling of Defence-Critical Minerals

Regime-switching price dynamics for nickel, copper, and cobalt (1990–2024)

Canada produces ten of twelve NATO defence-critical minerals yet lacks a quantitative stockpiling framework. This work develops a regime-switching model where the stockpile manager minimizes procurement, holding, and shortage costs via backward DP on joint price–inventory–belief state. Calibrated to World Bank Ni/Cu and Investing.com Co data. Joint work with Matt Davison, targeting Resources Policy.

Key Techniques

Key Results

• • Regime-aware policy reduces shortage months by 98–100% vs fixed-rate benchmarks
• • Cost savings of 19–59% versus fixed-rate procurement
• • Cobalt shows persistent volatility consistent with HHI = 5399 supply concentration
• • Robust across 16-fold range of penalty assumptions

Dual-Belief Framework for UUV Payload Management

Concept note extending a belief-state payload-allocation model with a second uncertainty dimension: the internal health state of stored vehicles. Combines (i) belief-state control for external threat, (ii) a reduced-order digital-twin library for latent structural health states, and (iii) an interpretable classifier mapping noisy diagnostics to health posteriors. The health posterior modifies expected deployment value through effectiveness reduction and health-related penalties.

Key Techniques

Architecture

• • External: three-state threat regime (peacetime / tension / conflict)
• • Internal: latent health states estimated via physics-informed digital twin library
• • Interpretable classifier for high-stakes operational decisions
• • Extends Petrov & Davison (2024) belief-state payload management model