Quantifying wildfire drivers and predictability in boreal peatlands using a two-step error-correcting machine learning framework in TeFire v1.0
Open Access
- 21 February 2024
- journal article
- research article
- Published by Copernicus GmbH in Geoscientific Model Development
- Vol. 17 (4) , 1525-1542
Abstract
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.Keywords
All Related Versions
Funding Information
- U.S. Department of Energy (DE-AC05-00OR22725)
This publication has 75 references indexed in Scilit:
- Peatland subsidence and carbon loss from drained temperate fensSoil Use and Management, 2011
- Global land-surface evaporation estimated from satellite-based observationsHydrology and Earth System Sciences, 2011
- The effects of water table draw‐down (as a surrogate for climate change) on the hydrology of a fen peatland, CanadaHydrological Processes, 2006
- Future Area Burned in CanadaClimatic Change, 2005
- IMPACTS OF LARGE‐SCALE ATMOSPHERIC–OCEAN VARIABILITY ON ALASKAN FIRE SEASON SEVERITYEcological Applications, 2005
- Uncertainty in estimating carbon emissions from boreal forest firesJournal of Geophysical Research: Atmospheres, 2004
- Use of Phospholipid Fatty Acids To Detect Previous Self-Heating Events in Stored PeatApplied and Environmental Microbiology, 2003
- Burned area mapping using multi-temporal moderate spatial resolution data—a bi-directional reflectance model-based expectation approachRemote Sensing of Environment, 2002
- Northern Peatlands: Role in the Carbon Cycle and Probable Responses to Climatic WarmingEcological Applications, 1991
- Modeling of smoldering combustion propagationProgress in Energy and Combustion Science, 1985