The 2023 Canadian wildfire season caused significant disruption and financial losses to the nation’s vital oil and gas production sectors. Alberta’s key shale gas regions, which produce 2.7 million barrels of oil daily, were under persistent extreme wildfire warnings throughout the summer (link). 

These conditions led to operational shutdowns, with Chevron halting all activities at the Kaybob Duvernay fields in central Alberta and Paramount suspending production at multiple sites, including a natural gas processing facility (link). The peak drop on production due to these events was approximately 319,000 barrels per day, with Kaybob production losses of around 59,000 per day, and Paramount of around 40,000 (link). These production halts in a high-output region like Canada not only resulted in immediate financial losses but also contributed to a noticeable rise in global oil prices, highlighting the far-reaching economic consequences of climate-driven hazards.

Figure 1 Wildfire impacts to Duvernay shale formation in Alberta, CA in 2023. [A] Baseline wildfire risk exposure map over Duvernay shale formation [B] Overlay of oil and gas pipelines (blue), oil drilling sites (black) and 2023 fire perimeters (purple) causing suspended operations. [C] Zoom in on north western formation highlighting impacts to oil fields and pipeline infrastructure. Wildfire data provided by Sust Global. Shale formation outline courtesy Alberta Geological Survey. 

Transforming real world modeling and multimodal data into financial insights

Sust Global has pioneered AI-powered physics based modeling of wildfire conditions, which is a prerequisite for accurate financial analysis for 21st century global business.

The 2023 Canadian wildfires are the most recent example of catastrophic events driven by extreme fire weather (link). Around 4% of Canada’s total forest area burned in 2023, an area approximately twice the size of Portugal. The wildfires more than doubled the previous records for burned areas and carbon emissions (link). Such events cost tens of millions of dollars in economic damages caused by business interruption and structural damage leading to financial loss. 

Despite the unprecedented nature of the wildfires, Sust Global’s wildfire model captures over 93% of the observed 2023 Canadian wildfires (Fig 2). By province, this skill ranges from over 88% (Ontario and Quebec) to 100% (Yukon) (Fig 2). This strong model performance on  extreme events strengthens its credibility in making wildfire forecasts under novel climate conditions.

Figure 2 Despite the unprecedented nature of the wildfires, Sust Global’s wildfire model captures over 93% of the observed 2023 Canadian wildfires. By province, this skill ranges from over 88% (Ontario and Quebec) to 100% (Yukon). 2023 fire perimeters (purple), Observed count (red) and modeled projections counts (black) shown for each province. Perimeter dataset courtesy the Canadian wildland fire information service (link).

Projections from Sust Global’s wildfire model reveal that as the climate continues to warm, the frequency and intensity of wildfire events across Canada are expected to increase significantly. This rising risk is driven by climate-induced changes, including higher temperatures and reduced precipitation, which create drier conditions that lower fuel moisture content, making vegetation more flammable and susceptible to ignition. These conditions not only accelerate the spread and intensity of wildfires but also extend the duration of fire seasons, posing a growing threat to industries and infrastructure.

Oil and gas facilities, particularly those in wildfire-prone regions like Alberta, are highly vulnerable to these emergent risks. Sust Global’s geospatial intelligence platform enables these facilities to be comprehensively mapped, analyzed, and assessed for exposure to wildfire hazards. 

By integrating spatial data on infrastructure locations—such as pipelines, drilling sites, and processing plants—with wildfire risk projections, operators can pinpoint high-risk assets and quantify the potential business impacts. This capability extends beyond static assessments, allowing dynamic analysis of risk trends over time, enabling better-informed operational and financial planning.

Quantifying the probability of extreme fire weather and its business impacts is inherently complex. Many regions are already experiencing unprecedented weather patterns, a trend that is projected to escalate. Traditional, empirically driven models relying solely on historical data are inadequate for predicting wildfire risks under future climate scenarios. Sust Global addresses this gap with a hybrid modeling approach that combines historical data with advanced physical wildfire modeling and state-of-the-art AI inference techniques. 

This methodology generates interpretable insights and extends predictive capabilities to scenarios beyond the model’s training data, providing more accurate and actionable forecasts for decision-makers.

This analysis becomes even more important in the future – as temperatures continue to rise, droughts become more severe, and extreme weather events become ubiquitous. For example, in many US States, future fire weather indices are forecasted to be higher than anything observed in the past.

Figure 3 Global wildfire risk projections for baseline and future wildfire projections under the Business as Usual (BAU) / High Emissions climate scenario (SSP5-RCP8.5). Mapping on probabilities in log scale from 0.0001 to 10%. 

Sust Global’s wildfire projection model combines millions of satellite observations of historic fires with high-resolution data across dozens of variables—daily precipitation, temperature, topography, land cover, ignition sources, and fire suppressibility. This multi-modal approach integrates spatial data, customer-specific financial inputs, and AI-powered inference to uncover complex relationships that traditional models and human analysis cannot decipher.

Sust Global’s unique physics-based geospatial models disaggregate fire risk into two interpretable layers: baseline fire risk and weather-dependent fire risk. This design ensures transparency while enabling the model to make accurate, scientifically grounded predictions, even in scenarios beyond its training data.

The result is a highly performant model that provides multi-scenario wildfire projections at global scale. The “peak fire weather” seen in eastern Canada over May-August 2023 was at least two times more likely and 20% more intense due to human-induced climate change, according to a recent study (link). 

Assessing financial assets

The application of physical risk datasets, such as those generated by Sust Global’s geospatial inference platform, to the S&P Global 1200 provides a transformative lens for financial investors, asset managers, and hedge funds to evaluate climate-driven risks. Analysis from S&P (link) shows that 92% of the world’s largest companies face at least one asset classified as highly exposed to physical climate hazards by the 2050s—a figure that rises to 98% by the 2090s under the Business-as-Usual (BAU) climate scenario (SSP5-RCP8.5). This underscores the systemic nature of climate risk, particularly for portfolios heavily weighted in vulnerable sectors.

For industries like Utilities, Energy, and Materials, the stakes are even higher. Over 70% of companies in these sectors have assets where the financial impact of climate change-related risks—such as wildfires, flooding, or extreme heat—could equate to 20% or more of an asset’s value. This kind of exposure demands proactive risk management strategies to safeguard long-term value and meet investor expectations for sustainability-aligned decision-making.

Figure 4 Projected increase to global wildfire risk from baseline (2010-2020) and future (2045-2055) under the Business as Usual (BAU) / High Emissions climate scenario (SSP5-RCP8.5), expressed as percentage of baseline risk. Mapping on percentages in linear scale from 0.0 to 200% (representing a 3-fold increase). 

Unlocking Unique Insights Through Multi-Modal Data Fusion

What sets Sust Global’s approach apart is its ability to layer traditional physical risk models with multi-modal datasets, including financial metrics, spatial data, and real-time satellite-derived observations. This enables a deeper understanding of risk not only at the macro level but also for specific assets, geographies, and financial instruments. By incorporating loan-level data, operational dependencies, and geographic distribution of assets, investors can pinpoint vulnerabilities, quantify exposure, and model financial impacts in ways that traditional risk assessments cannot achieve.

For example:

• Asset managers can prioritize investments in more resilient regions or assets, reducing the downside risk of climate-exposed portfolios.

• Institutional investors can use this data to meet ESG mandates and align with net-zero transition goals, ensuring regulatory compliance and stakeholder trust.

The Role of Sub-Seasonal Weather Analytics

Sust Global’s advanced sub-seasonal weather analytics further amplifies the value of this multi-modal approach. By providing granular forecasts for periods ranging from weeks to months, these tools allow financial stakeholders to anticipate short-term climate impacts on operations and revenues. For instance:

• Utility companies can plan for increased cooling demand during heatwaves or manage risks of supply disruptions from wildfires.

• Commodity investors can adjust strategies based on weather-driven price fluctuations, such as impacts on crop yields or energy production.

• Real estate portfolio managers can use these insights to assess near-term risks to properties, guiding maintenance schedules or insurance strategies.

Delivering Actionable Insights

The integration of Sust Global’s datasets into financial workflows ensures that climate risk is no longer a vague future concern but a quantifiable, actionable metric. Whether through API integrations, customized dashboards, or bulk data feeds, these insights empower investors to evaluate, forecast, and mitigate risks with precision, ensuring smarter decisions in an increasingly uncertain world. By coupling long-term scenario planning with sub-seasonal analytics, financial stakeholders gain a holistic toolkit to navigate the challenges and opportunities presented by a rapidly changing climate.