Reports & Research

A Data-Driven Conversation about the US West’s Megadrought

Current climate conditions in the West reveal that 2021 may have a higher than normal risk for wildfire losses. While much of this report focuses on California, historically the worst victim of wildfire in the US, the entire western US is of concern in 2021. In particular, the expansion of deep drought into Colorado is of major concern.

Drought is a leading factor in seasonal wildfire risk. With drought extending through every western state this spring, insurers should consider looking deeply into how they are addressing this growing peril. According to AON, last year’s wildfires in the US West cost insurers over $8 billion.

We've released a complete detailing the devastating potential for 2021's wildfire season. The full report is available here.

Research across more than 71,000 properties involved in wildfires draws significant links between fuel management and property survival.

Read Full Study 

Oakland,Calif., April 8, 2021: Zesty^AI, a leader in climate risk analytics powered by Artificial Intelligence (AI), and the Insurance Institute for Business & Home Safety (IBHS) today released new research on how fuel management impacts destruction rates from wildfires. They found property owners who clear vegetation from the perimeter of their home or building can nearly double their structure's likelihood of surviving a wildfire.

Zesty^AI, in conjunction with, IBHS studied more than 71,000 properties involved in wildfires between 2016 and 2019 to assess the relationship between vegetation, buildings, and property vulnerability. To do this, Zesty^AI leveraged a combination of computer vision and AI to analyze high resolution satellite and aerial imagery of the properties that fell within the wildfire perimeter, which allowed them to determine what effects a property's physical environment had on its likelihood of survival. They found buildings with a high amount of vegetation within 5 feet of the structure were destroyed in a wildfire 78 percent of the time -- a rate nearly twice as high as those with small amounts of perimeter vegetation. This pattern held true as Zesty^AI analyzed the other defensible zones, ranging from 30 to 100 feet around the property.

"It's common sense that increased vegetation increases wildfire risk, but this study shows just how powerful individual action can be in safeguarding structures. Mitigation actions that can cut risk nearly in half are statistically meaningful to anyone with a stake in this peril," said Attila Toth, CEO of Zesty^AI. "These findings also underscore how wildfire research at IBHS and artificial intelligence at Zesty^AI translates to real-world impact at the intersection of homeowners, community leaders, regulators, and insurance carriers. This type of collective action will help protect our communities from the devastating impact of wildfire, which unfortunately has continued to increase over the last decade."

The study also supported and confirmed takeaways from IBHS's Suburban Wildfire Adaptation Roadmaps released last year, which go beyond the home ignition zone to detail additional actions needed across eight aspects of a home to address a home's wildfire vulnerability. Zesty^AI's new research found that having other structures in close proximity to a property increases its wildfire risk, particularly for properties in areas with moderate to high vegetation coverage. Buildings in these areas that had another structure within 30 to 100 feet from the property were destroyed in a wildfire 60 percent of the time, compared to a 31 percent destruction rate for homes without another structure in close proximity.

"This research further demonstrates to homeowners, community leaders, and policy makers just how impactful taking the mitigation actions laid out in the Suburban Wildfire Adaptation Roadmaps can be in protecting homes from wildfire ignition," said Roy E. Wright, President & Chief Executive Officer at IBHS. "Quantifying the effect of mitigating fuel density risk, one of the critical actions identified in the Roadmaps, is a first piece in the larger puzzle of what groups of mitigation actions most improve the chance of home survival and by what level."

Zesty^AI is uniquely equipped to support this type of research because of the proprietary wildfire property loss database it developed for Z-FIRE™, its AI model that generates property-specific predictive risk scores. Z-FIRE™ has been trained on more than 1,200 wildfire events across several decades and accounts for the property-level factors that contribute to wildfire risk, including defensible space, building material, and roof pitch, which legacy models fail to consider.

Wright added, "While it is not possible to eliminate wildfire risk we are not powerless against it. We must take a pragmatic approach to mitigate risk at all levels and ultimately reduce property damage through data and science. Through collaborations with modelling organizations like Zesty^AI, advanced technology like computer vision and AI help us better understand the impact of these actions at a larger scale. It is encouraging to see emerging progress in just the first months of 2021."

For additional insights you can read the full research paper, ‘Wildfire Fuel Management and Risk Mitigation - Where to Start?' here. For more information on Zesty^AI please visit www.zesty.ai, and for more information on IBHS please visit www.ibhs.org.

About Zesty^AI (www.zesty.ai): Increasingly frequent natural disasters, such as wildfires, floods and hurricanes devastated communities and drove $2.2 Trillion in economic losses over the past decade. Zesty^AI uses 200Bn data points, including aerial imagery, and artificial intelligence to assess the impact of climate change one building at a time. Zesty^AI has partnered with leading insurance companies and property owners helping them protect homes, businesses and support thriving communities. Zesty^AI was named Top 100 Most Innovative AI Company in the world by CB Insights in 2020, and Gartner Cool Vendor in Insurance by Gartner Research in 2019. For more information visit: https://www.zesty.ai/

‍

About the Insurance Institute for Business & Home Safety (IBHS)

The IBHS mission is to conduct objective, scientific research to identify and promote effective actions that strengthen homes, businesses and communities against natural disasters and other causes of loss. Learn more about IBHS at DisasterSafety.org.

As of September 18th, between $5.9Bn and $9.8Bn in losses have occurred this year alone.

The Zest
Zesty^AI has been keeping a close eye on the wildfires burning in the Western United States. Whether by evacuation or smoke, most of our employees have felt the impact firsthand.
Utilizing our vast wildfire data and artificial intelligence resources, we have estimated that as of September 18th, between $5.9Bn and $9.8Bn in losses have occurred this year alone.

What has made 2020 unique?
Two key aspects have made the 2020 Wildfire Season exceptional: the number of acres burned and the timing of the fires.

2018, which previously held the California record for acres burned at 1,975,086 has been eclipsed with months left in the seasons. More than 3.3 million acres have already been charred by wildfire this year in California alone, and more than 5 million in the Western US.

Fire season tends to start in September and peak in November. In August, a large scale lightning event occurred, triggering many of the California wildfires. Oregon, which typically has a shorter wildfire season has also seen early and widespread wildfires.

Analysis Methodology
Using Zesty^AI’s comprehensive historical wildfire loss data, up-to-date wildfire perimeter locations for the 2020 season, residential and commercial property information, and fueled by Zesty^AI’s AI-driven wildfire damage risk scores, the expected destruction and cost of the 2020 wildfire season so far was calculated for California, Oregon, and Washington.

To estimate the destruction and damages, Zesty^AI identified every structure involved in the 2020 wildfire perimeters and their associated wildfire vulnerabilities. Using the historical relationship between the risk profile of the structure, asset value, and economic loss, Zesty^AI was able to estimate the full economic loss of those events (including non-insured assets such as uninsured property, and non-insured economic cost). Actual information from CalFire on CZU and LNU incident was used to validate the methodology.

From our extensive historical loss data, a relationship between structural damage expected and the cost of wildfire events was developed based on local property and loss information and expanded to include additional considerations such as smoke damage, displacement costs, and construction.

The 5 Most Destructive Fires So Far
Our estimates place the Claremont-Bear (North Complex) at the top of the list of most destructive in terms of number of properties lost. Four of these five wildfires occurred in California with the Alameda Drive fire occurring in Oregon.

The 5 Most Expensive Fires So Far
While the Claremont-Bear (North Complex) fire is estimated to have destroyed the most properties, the CZU Lightning Complex fire is currently estimated to be the most costly at up to $2.6B. That makes it responsible for ~27% of all total economic losses from fires in the 2020 season so far. 

Putting Numbers on Destruction
By Zesty^AI estimates, between $5.9Bn and $9.8Bn of economic losses have occurred in California, Oregon, and Washington so far this year. California, which also leads in acres burned (5M+) makes up the lion’s share at up to $7.9B.

It’s important to state that the fire season is not yet over. In much of the Western US, it could be just beginning. With a number of fires still active and the potential for more to start, these numbers are almost certain to rise between now and the end of the year.

Looking Forward
Multiple estimates place the 2018 wildfire season at around $15Bn in total losses. While exceptional in terms of total acres burned, the 2020 wildfire season has not yet reached that level of economic loss. Without any doubt, this will be one of the costliest years on record, and with months left in the season, the potential exists for this year to surpass 2018 if it continues at its current pace.

Zesty^AI will continue to monitor this fire season. As in years past, new data continues to refine our models and analyses. Insurance professionals and media who would like more information about this analysis or about how artificial intelligence can help insurers protect themselves and their customers from wildfire should contact us.

ZestyAI today announced that Logic Underwriters has adopted ZestyAI’s Z-PROPERTY™, Z-HAIL™, and Z-WIND™ solutions to improve underwriting and rating precision across its personal and commercial property portfolio in Texas.

Texas is the most expensive severe convective storm market in the United States, with hail and damaging wind driving billions of dollars in insured losses every year.

"Texas is one of the most challenging storm markets in the U.S., and we need tools that match that reality," said Bill Motz, Director of Operations, Logic Underwriters.

"ZestyAI's detailed property insights and dedicated hail and wind models will help us continue to provide exemplary service to our clients—from more accurate risk assessments to better loss prevention guidance in increasingly volatile weather conditions."

ZestyAI’s property-specific hail and wind models predict the likelihood and severity of storm-driven claims by analyzing how local climatology interacts with detailed property characteristics—helping underwriters to distinguish meaningful differences in risk within the same rating territory. Each model is trained on validated claims data, offering transparent explanations of the key factors driving risk.

Z-PROPERTY applies AI to high-resolution aerial imagery and multi-source data to assess roof condition, structural complexity, and parcel-level features such as vegetation overhang, yard debris, and secondary structures—factors that directly influence claim frequency and severity across multiple perils.

“Logic Underwriters is exactly the kind of forward-looking partner that is redefining underwriting in high-exposure states,” said Attila Toth, Founder and CEO of ZestyAI.

"This collaboration shows how property-level intelligence can support underwriting excellence and disciplined decision-making while helping policyholders better understand and protect their properties. When insurers can identify specific risk factors like roof condition or vegetation overhang, they can provide actionable guidance that helps clients reduce their exposure and minimize losses."

ZestyAI’s severe convective storm models are approved in 30 states, spanning the nation’s highest-exposure hail and wind markets, and used by leading insurers across the country.

Wildfire risk in the United States is no longer confined to the edges of forests or traditionally high-risk zones. New analysis using ZestyAI’s property-level wildfire models shows that millions of homes classified as low or no wildfire risk under federal assessments face elevated wildfire danger when evaluated at the property level.

This analysis was recently featured in Vox, which examined how wildfire behavior is evolving — and why broad, backward-looking risk maps are increasingly misaligned with how fires spread today.

👉 Read the full article on Vox → https://www.vox.com/climate/476932/california-wildfire-los-angeles-risk-ai-housing-climate

Wildfire risk is closer — and more granular — than most maps show

Many homes damaged or destroyed in the 2025 Los Angeles wildfires were still classified as “low risk” under federal wildfire assessments. ZestyAI’s property-level analysis provides a different perspective.

By evaluating individual structures — including vegetation proximity, defensible space, building characteristics, and neighborhood-level fire dynamics — ZestyAI identified more than 3,000 properties worth approximately $2.4 billion in areas impacted by the Palisades and Eaton fires that showed elevated wildfire risk despite being classified as low or no risk under FEMA’s census-level assessments.

Across California, the classification gap is even broader. Approximately 1.2 million properties, representing roughly $940 billion in residential property value, are designated as low or no wildfire risk under federal maps, despite AI-driven property-level models indicating elevated wildfire danger.

Why census-level wildfire maps fall short

Wildfires do not spread evenly across census tracts or counties. Ember-driven ignition, structure-to-structure spread, wind conditions, and localized vegetation patterns create uneven outcomes, where one home survives and the next is destroyed.

Federal wildfire assessments are designed to provide a baseline view of community-level risk. FEMA has noted that its National Risk Index is not intended to serve as a property-specific risk assessment. When risk is evaluated at the individual property level, meaningful differences emerge that aggregated maps are not designed to capture.

What more granular wildfire risk intelligence enables

More detailed wildfire risk data can support:

• Targeted mitigation efforts at the property and neighborhood level
• More informed rebuilding and land-use decisions
• Clearer, more defensible underwriting and portfolio strategies
• Improved dialogue between insurers, regulators, and communities

A shift in how wildfire risk is understood

Wildfire risk is evolving faster than the systems built to measure it. Homes are no longer just adjacent to wildfire hazards; they increasingly influence how fires ignite, spread, and intensify, even in dense urban environments.

Property-level risk intelligence does not remove hard decisions. But without it, those decisions are made using an incomplete picture of where wildfire risk truly exists.

Read the full Vox article here.

 General Star (GenStar), a respected provider of excess and surplus specialty property and casualty insurance and a member of the Berkshire Hathaway family of companies, has selected ZestyAI to further strengthen how it underwrites hail, wind, and severe convective storm risk across its commercial property portfolio. 

The carrier will use ZestyAI’s Z-STORM™ model to gain more precise, property-level insight for multi-structure apartment and condominium risks, further supporting underwriting, pricing, and coverage decisions.

“Z-STORM gives us a more actionable view of hail risk at the individual property level,” said Matt Brown, Senior Vice President, Delegated Division at GenStar.

“In our evaluation, the model demonstrated compelling risk-splitting lift, which allows us to further differentiate risk more effectively, price with greater precision, and ultimately strengthen relationships with our customers and distribution partners.”

Z-STORM predicts the expected frequency and severity of severe convective storm losses by combining climatology with detailed property-specific characteristics. The model is designed to support more refined wind and hail peril rating, improved deductible and endorsement strategies, and earlier visibility into accumulating and emerging storm risk across a carrier’s portfolio.

By adopting Z-STORM, GenStar aims to further:

• Improve underwriting clarity by incorporating a clearer, property-level view of hail and wind risk into core underwriting decisions
• Expand policy availability by applying deductibles, endorsements, and exclusions more precisely—helping keep coverage available even in hail-prone markets
• Align pricing with risk, potentially offering more competitive premiums for favorable risks while refining pricing for higher-risk properties
• Identify emerging storm risk sooner, enabling proactive risk management and loss mitigation before exposures become potentially costlier for both GenStar and insureds

“GenStar joins a growing number of carriers using AI to modernize property underwriting,” said Attila Toth, Founder and CEO of ZestyAI.

“With Z-STORM delivering a sharper, property-level view of hail risk across complex apartment and condo portfolios, GenStar can further strengthen underwriting and pricing decisions and identify emerging exposures earlier—before they potentially turn into avoidable losses.”