Quantifying wildfire drivers and predictability in boreal peatlands using a two-step error-correcting machine learning framework in TeFire v1.0

Journal Article · 21 February 2024 · Geoscientific Model Development (Online)

DOI: https://doi.org/10.5194/gmd-17-1525-2024 · OSTI ID:2310414

Tang, Rongyun ^[1]; Jin, Mingzhou  ^[2]; Mao, Jiafu  ^[3]; Ricciuto, Daniel M.  ^[3]; Chen, Anping  ^[4]; Zhang, Yulong ^[2]

---

1. Univ. of Tennessee, Knoxville, TN (United States); Univ. of Arkansas, Fayetteville, AR (United States)
2. Univ. of Tennessee, Knoxville, TN (United States)
3. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Climate Change Science Institute
4. Colorado State Univ., Fort Collins, CO (United States)

Wildfires are becoming an increasing challenge to the sustainability of boreal peatland (BP) ecosystems and can alter the stability of boreal carbon storage. However, predicting the occurrence of rare and extreme BP fires proves to be challenging, and gaining a quantitative understanding of the factors, both natural and anthropogenic, inducing BP fires remains elusive. Here, we quantified the predictability of BP fires and their primary controlling factors from 1997 to 2015 using a two-step correcting machine learning (ML) framework that combines multiple ML classifiers, regression models, and an error-correcting technique. We found that (1) the adopted oversampling algorithm effectively addressed the unbalanced data and improved the recall rate by 26.88 %–48.62 % when using multiple datasets, and the error-correcting technique tackled the overestimation of fire sizes during fire seasons; (2) nonparametric models outperformed parametric models in predicting fire occurrences, and the random forest machine learning model performed the best, with the area under the receiver operating characteristic curve ranging from 0.83 to 0.93 across multiple fire datasets; and (3) four sets of factor-control simulations consistently indicated the dominant role of temperature, air dryness, and climate extreme (i.e., frost) for boreal peatland fires, overriding the effects of precipitation, wind speed, and human activities. Our findings demonstrate the efficiency and accuracy of ML techniques in predicting rare and extreme fire events and disentangle the primary factors determining BP fires, which are critical for predicting future fire risks under climate change.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Biological and Environmental Research (BER). Earth & Environmental Systems Science (EESS); USDOE
• Grant/Contract Number: AC05-00OR22725
• OSTI ID: 2310414
• Alternate ID(s): OSTI ID: 2317730
• Journal Information: Geoscientific Model Development (Online), Vol. 17, Issue 4; ISSN 1991-9603
• Publisher: Copernicus Publications, EGUCopyright Statement
• Country of Publication: United States
• Language: English