TSECfire v1.0: Quantifying Wildfire Drivers and Predictability in Boreal Peatlands Using a Two-Step Error-Correcting Machine Learning Framework

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, a quantitative understanding of natural and anthropogenic influences on the changes in BP fires remains elusive. Here, we quantified the predictability of BP fires and their primary controlling factors from 1997 to 2016 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) non-parametric models outperformed parametric models in predicting fire occurrences, and the machine learning model of Random Forest performed the best with the area under the Receiver Operating Characteristic curve ranging from 0.83 to 0.93 across multiple fire data sets, 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 BP fire prediction and disentangle the primary factors determining BP fires, which are critical for predicting future fire risks under climate change.