Moji Sadegh

Climate-linked escalation of societally disastrous wildfires Climate change and land mismanagement are creating increasingly fire-prone built and natural environments. However, despite worsening fire seasons, evidence is lacking globally for trends in socially ...

Out today in @science.org, we show wildfire disasters have surged in the last decade, as climate change intensifies fire weather and exacerbates other vulnerabilities.

📄 www.science.org/doi/10.1126/...

With @pyrogeog.bsky.social @climate-guy.bsky.social

Increasing global human exposure to wildland fires despite declining burned area Although half of Earth’s population resides in the wildland-urban interface, human exposure to wildland fires remains unquantified. We show that the population directly exposed to wildland fires incre...

Whenever a story appears about increasing risk of wildfires, some helpful chap always likes to comment “that global burned area is declining so stop being alarmist.” A new paper explains the paradox.

www.science.org/doi/10.1126/...

#climatechange #wildfire #fireweather

Globally, the population directly exposed to wildland fires increased 40%, 2002-2021, despite 26% decline in burned area. Africa is, by far, the global hot spot for this exposure, w/ 85% of global exposures occurring in Africa in that period.

www.science.org/doi/epdf/10....

Increasing global human exposure to wildland fires despite declining burned area Although half of Earth’s population resides in the wildland-urban interface, human exposure to wildland fires remains unquantified. We show that the population directly exposed to wildland fires incre...

🔥 Our new research in @science.org shows that people are increasingly exposed to fires globally, driven by overlapping shifts in where #fires occur and where people live.

But changes in exposure vary hugely by region and are shaped by different population dynamics.👇

www.science.org/doi/10.1126/...

Increasing global human exposure to wildland fires despite declining burned area Although half of Earth’s population resides in the wildland-urban interface, human exposure to wildland fires remains unquantified. We show that the population directly exposed to wildland fires incre...

Happy to be on the team that looked at exposure to smoke from low intensity wildfires and impacts on global health

www.science.org/doi/10.1126/...

We have discussed it with Karen Short. Potentially coming in the new version

Compounding effects of climate change and WUI expansion quadruple the likelihood of extreme-impact wildfires in California - npj Natural Hazards npj Natural Hazards - Compounding effects of climate change and WUI expansion quadruple the likelihood of extreme-impact wildfires in California

Thrilled to share our new paper in @natureportfolio.nature.com
npj Natural Hazards: 𝐂𝐨𝐦𝐩𝐨𝐮𝐧𝐝𝐢𝐧𝐠 𝐞𝐟𝐟𝐞𝐜𝐭𝐬 𝐨𝐟 𝐜𝐥𝐢𝐦𝐚𝐭𝐞 𝐜𝐡𝐚𝐧𝐠𝐞 𝐚𝐧𝐝 𝐖𝐔𝐈 𝐞𝐱𝐩𝐚𝐧𝐬𝐢𝐨𝐧 𝐪𝐮𝐚𝐝𝐫𝐮𝐩𝐥𝐞 𝐭𝐡𝐞 𝐥𝐢𝐤𝐞𝐥𝐢𝐡𝐨𝐨𝐝 𝐨𝐟 𝐞𝐱𝐭𝐫𝐞𝐦𝐞-𝐢𝐦𝐩𝐚𝐜𝐭 𝐰𝐢𝐥𝐝𝐟𝐢𝐫𝐞𝐬 𝐢𝐧 𝐂𝐚𝐥𝐢𝐟𝐨𝐫𝐧𝐢𝐚.

www.nature.com/articles/s44...

@mojisadegh.bsky.social @climate-guy.bsky.social

Thanks to the Joint Fire Science Program for funding this research

*Our model attributed the greatest percentage of 150,247 wildfires from 1992 to 2020 for which the ignition source was unknown to equipment and vehicle use (21%), lightning (20%), and arson and incendiarism (18%).

*Our model more accurately separated wildfires ignited by natural versus human causes (93% accuracy), and discriminated among the 11 classes of human-ignited wildfires with 55% accuracy.

*ML models can identify the cause of wildfire ignitions and determine the contributions of diverse attributes to classification of cause
*Trained on wildfires from 1992 to 2020 with 12 known causes, the overall accuracy of our model exceeded 70% when applied to out-of-sample test data.

*The spatial and temporal distribution of wildfires is captured by associated biological, physical, social, and management attributes
*Wildfires are increasingly reported with an unknown cause (5-fold increase from 1992 to 2020), hindering targeted prevention strategies

Led by Yavar Pourmohammad and published in @agu.org Earth's Future, we developed #MachineLearning models to infer the cause of wildfires that were recorded with an unknown/missing cause from their physical, biological and administrative covariates: doi.org/10.1029/2024...
@climate-guy.bsky.social

Amirhossein Montazeri received three years of funding from the NASA FINESST program to model soil burn severity using satellite imagery and hashtag#MachineLearning:
lnkd.in/gJcUFegb

Yavar Pourmohammad received one year of funding from JFSP to develop a hashtag#MachineLearning model to infer the cause of wildfires that were recorded with an unknown cause using their attributes: lnkd.in/gJJraAqk

Here is my first post:

Congratulations to two brilliant PhD students at Boise State University for receiving awards from NASA - National Aeronautics and Space Administration and Joint Fire Science Program:

Looking forward to the great science and products that Yavar and Amirhossein will develop.