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.

The Silent Peril Reshaping Homeowners Insurance

Non-weather water damage rarely makes headlines, but it’s quietly eroding profitability across the country.
It is now the fourth costliest peril in homeowners insurance, and claim severity has increased 80% in the last decade—a trend that’s accelerating even as frequency remains relatively flat.

Traditional risk models struggle to capture the early warning signs behind these losses, leading to mispriced policies, undetected exposure, and rising volatility for carriers.

Want the full analysis? Download the complete “Winning the Fight Against Non-Weather Water Losses” guide.

Why Loss Severity Keeps Rising

Aging homes and overlooked system failures

Many of the most expensive losses stem from aging plumbing, deteriorating materials, and slow-burn failures that often go undetected until damage is significant.

Frequency is flat—severity is not

Loss patterns suggest that while the number of events hasn’t surged, the financial impact of each event has—a signal that traditional models are not capturing the right property-level predictors.

The Property Features Most Predictive of Water Losses

The overlooked attributes that traditional models miss

Standard territory- or age-based assessments often ignore the property-specific details that meaningfully influence water loss risk, including:

• supply line material and age
• plumbing configuration
• occupancy patterns
• system maintenance and upgrades
• moisture exposure and prior loss indicators

These factors vary widely between neighboring homes—yet most models treat them as identical.

Where Traditional Underwriting Falls Short

ZIP-code and age-based proxies mask true risk

Legacy approaches rely heavily on broad territory-level assumptions that overlook structural vulnerabilities and system conditions.

Limited visibility creates mispriced policies

Without property-level insight, high-risk homes are often underpriced while lower-risk homes subsidize them—driving loss ratio volatility over time.

Get deeper insights on the drivers of water loss severity in our full guide → “Winning the Fight Against Non-Weather Water Losses”

How AI and Property-Level Data Are Changing the Landscape

AI models trained on real-world claims data can identify early signals of potential water loss by analyzing the interaction between:

• plumbing systems
• property attributes
• historical patterns
• material degradation
• repair history

This enables carriers to segment risk accurately, adjust pricing, and reduce preventable losses—long before small issues turn into major claims.

What Homeowners Actually Understand About Water Risk

Misconceptions around coverage and prevention

ZestyAI’s research shows that many policyholders:

• misunderstand what is and isn’t covered
• underestimate how much damage water can cause
• rarely take preventive actions unless prompted

This disconnect creates an opportunity for carriers to strengthen education, mitigation, and customer engagement.

Steps Carriers Can Take Today

Improve segmentation and rating accuracy

Property-level signals enable more precise risk tiers and more stable long-term portfolios.

Strengthen mitigation and reduce loss severity

Insights help identify which homes are at elevated risk and where targeted mitigation can reduce exposure.

Enhance underwriting workflows with explainable insights

Transparent, explainable AI helps underwriters understand the key drivers behind elevated risk—supporting both decision-making and regulatory review.

Get the Full Guide

Our new research paper, Winning the Fight Against Non-Weather Water Losses, breaks down the trends reshaping this growing peril—and the strategies carriers can use to get ahead of it.

Access the Guide

ZestyAI announced that its Severe Convective Storm suite, including Z-HAIL™, Z-WIND™, and Z-STORM™, has received regulatory approval from the Ohio Department of Insurance.

With the addition of Ohio, ZestyAI’s Severe Convective Storm suite is now approved for use in 16 states, covering key high-risk markets across the Midwest, Great Plains, and South.

Ohio Faces Rapidly Rising Storm Losses

Ohio has experienced 36 billion-dollar loss storm events over the past five years alone, surpassing the total from the previous two decades, which saw just 33 events, according to NOAA’s National Centers for Environmental Information (NCEI). Severe convective storms, including hail, wind, and tornadoes, were the driver, contributing to over 57% of the state’s total weather-related damages since 1980.

Traditional Models Miss Critical Property-Level Differences

ZestyAI’s AI-driven platform predicts the likelihood and severity of claims from severe convective storms at the individual property level by analyzing the interaction of local climatology with property-specific characteristics. In contrast, most risk assessment models today rely on broader territory or ZIP code-level evaluations, overlooking critical property-level factors. 

Each model is built and validated on extensive real-world claims data and delivers transparent explanations of the key drivers behind every risk score, helping carriers make more accurate underwriting and rating decisions.

Key capabilities include:

• Z-HAIL: Predicts hail damage risk and claim severity using property-specific attributes like roof complexity, historical losses, and accumulated damage, identifying which homes are most likely to file a claim, even within the same neighborhood.
• Z-WIND: Combines AI-generated 3D analysis of roof condition, complexity, and potential failure points with local climatology to deliver pivotal insights into property-specific wind vulnerability and severity.
• Z-STORM: Predicts the frequency and severity of storm damage claims, examining the interaction between climatology and the unique characteristics of every structure and roof.

Regulatory Approval Reflects a Shift Toward Precision Underwriting

“Too often, storm risk is priced using rough proxies instead of accurate property insights,” said Kumar Dhuvur, Founder and Chief Product Officer at ZestyAI.

“Regulatory approval in Ohio affirms the industry’s shift toward precision underwriting and rating—and opens the door to smarter, risk-aligned decisions and fewer preventable losses in one of the nation’s most important insurance markets.

ZestyAI's analysis revealed that more than 12.6 million U.S. properties are at high risk of hail-related roof damage, representing $189.5 billion in potential replacement costs.

Powered by ZestyAI’s Z-HAIL™ model, the analysis underscores the growing financial threat of severe convective storms (SCS), including hail, tornadoes, and wind events. In 2024 alone, damages from SCS were estimated at $56 billion—surpassing losses from hurricanes.

Yet many insurers still rely on traditional models designed to estimate portfolio-level exposure, not property-level risk. As hail events increase in severity and frequency, these models often miss the structural and environmental conditions that drive real losses.

Kumar Dhuvur, Co-Founder and Chief Product Officer at ZestyAI said:

“Catastrophe models have helped insurers understand where storms may strike and how losses might add up at a portfolio level. But they weren’t built to assess risk at the individual property level, and they often miss the specific conditions that drive hail damage. By analyzing the interaction between structure-specific features and local storm patterns, we can distinguish risk between neighboring properties—enabling smarter underwriting, more precise pricing, and better protection for policyholders.”

Z-HAIL evaluates hail risk using a proprietary blend of climate, aerial, and property-specific data. By applying advanced machine learning to these inputs, Z-HAIL delivers highly granular predictions that reflect both the physical characteristics of a structure and the storm activity in its immediate surroundings.

Key findings from the analysis:

• 12.6 million U.S. structures flagged as high risk for hail-related roof damage
• $189.5 billion in total potential roof replacement exposure

Top five states by dollar exposure:

• Texas ($68B)
• Colorado ($16.7B)
• Illinois ($10.8B)
• North Carolina ($10.4B)
• Missouri ($9.5B)

States with the lowest dollar exposure:

• Maine ($4.7M)
• Idaho ($12.8M)
• New Hampshire ($18.5M)
• Nevada ($49.3M)
• Vermont ($64.7M)

In recent case studies, Z-HAIL has demonstrated the ability to pinpoint which properties are most susceptible to hail damage—even within the same neighborhood and exposed to the same storm. In one example from Allen, Texas, following a storm with 2.5-inch hailstones, Z-HAIL segmented risk across 483 policies, identifying no losses among properties rated “Very Low” by the model. This level of intra-territory precision gives insurers the ability to refine risk selection with confidence—even in the most hail-prone regions of the country.

ZestyAI helped carriers and insurers of last resort extend coverage to over 511,000 properties previously deemed uninsurable in 2024. This year, ZestyAI aims to double its impact, helping to bring coverage options to over a million families and businesses, ensuring that those in catastrophe-prone regions have access to sustainable, risk-aligned insurance.

A 2024 Deloitte survey found that nearly a quarter of homeowners in high-risk states are struggling to find coverage, while over half cite affordability as a growing concern—underscoring the industry’s need for granular insights that support underwriting and pricing decisions aligned with true property-level risk.

“For too long, insurers have had to make high-stakes decisions with incomplete information,” said Attila Toth, Founder and CEO of ZestyAI. “Advanced AI models are changing that. With granular, property-specific risk insights, insurers can close protection gaps and build a more resilient market.”

Traditional risk assessment methods rely on territory- or ZIP code-level evaluations, overlooking the property-level characteristics that drive risk. This approach leads to adverse selection, inaccurate pricing, and widespread market withdrawal.

ZestyAI replaces this approach with transparent, AI-powered models that integrate climatology, geospatial data, historical losses and structural attributes to deliver precise views of wildfire, hail, and wind risk, among other perils.

The results:

• Clear mitigation guidance to help policyholders take action.
• Risk-aligned premiums that support responsible market expansion.
• Improved underwriting precision through AI-driven risk scores and near-complete U.S. coverage.
• Optimized loss cost controls via more effective deductible, Actual Cash Value (ACV), and coverage strategies.
• A supportive experience for carriers, families, and businesses—enabling faster decisions, better communication, and greater confidence in coverage options.
• Streamlined inspections that lower expenses and improve efficiency.

ZestyAI collaborates closely with regulators to ensure transparency, validation, and model oversight. Its wildfire model, Z-FIRE, is approved across all Western states, while its severe convective storm models have gained broad acceptance from Texas to Colorado and throughout the Midwest and Great Plains.

As regulators support the use of advanced models, they are also paving the way for smarter risk-based pricing and proactive mitigation—revitalizing insurance’s core mission: protecting the livelihood of home and business owners and their communities.

Severe convective storms are becoming more frequent and costly, putting pressure on insurers to refine underwriting and risk management strategies. 

On April 2, our experts covered:

• Key drivers behind increasing severe storm losses
• What La Niña means for the 2025 season
• How AI-powered risk models improve risk segmentation
• Live Q&A – Get expert answers to your toughest questions!

Missed the live event? Stream now! 

ZestyAI has partnered with EarthDaily Analytics (EarthDaily), a global provider of Earth Observation analytics and data.

Through this partnership, ZestyAI’s advanced models—including Z-FIRE™, Z-HAIL™, Z-WIND™, and Z-STORM™—will be available through EarthDaily’s Ascend platform, delivering geospatial data, risk modeling, and post-event insights to insurers.

With the insurance industry facing escalating challenges from climate-driven catastrophes and increasing pressure to accurately price risk, ZestyAI’s models provide granular, property-level risk data. These models analyze factors like vegetation density, construction materials, and historical weather patterns to offer insights beyond traditional methods.

“At EarthDaily, we’re committed to delivering cutting-edge property insights to customers navigating today’s climate risks,” said Rachel Olney, VP of Insurance at EarthDaily.

With advanced AI models covering wildfire, hail, wind, and property data, ZestyAI is an ideal partner to support our mission.

"By including their advanced analytics in our Ascend platform, we’re excited to empower clients to take proactive steps in managing and mitigating risk with confidence."

ZestyAI’s solutions achieve nearly 100% hit rates, offering actionable insights that insurers and businesses can trust. By bolstering the data available in the Ascend platform with property-level insights, the partnership provides decision-makers with a new level of clarity to mitigate risks, improve underwriting, and allocate resources more effectively.

The collaboration exemplifies the growing importance of innovative technology in the insurance and property management sectors, especially as global climate risks continue to evolve.