Predicting Fire Season Intensity in Maritime Southeast Asia with
Interpretable Models
Abstract
There have been many extreme fire seasons in Maritime Southeast Asia
(MSEA) over the last two decades, a trend which will likely continue, if
not accelerate, due to climate change. Fires, in turn, are a major
driver of atmospheric carbon monoxide (CO) variability, especially in
the Southern Hemisphere. Previous studies have explored the relationship
between climate variability and fire counts, burned area, and
atmospheric CO through regression models that use climate mode indices
as predictor variables. Here we model the connections between climate
variability and atmospheric CO at a level of complexity not yet studied
and make accurate predictions of atmospheric CO (a proxy for fire
intensity) at useful lead times. To do this, we develop a
regularization-based statistical modeling framework that can accommodate
multiple lags of a single climate index, which we show to be an
important feature in explaining CO. We use this framework to present
advancements over previous modeling efforts, such as the inclusion of
outgoing longwave radiation (OLR) anomalies, the use of weekly data, and
a stability analysis that adds weight to the scientific interpretation
of selected model terms. We find that the El Ni\ {n}o
Southern Oscillation (ENSO), the Dipole Mode Index (DMI), and OLR (as a
proxy for the Madden-Julian Oscillation) at various lead times are the
most significant predictors of atmospheric CO in MSEA. We further show
that the model gives accurate predictions of atmospheric CO at leads
times of up to 6 months, making it a useful tool for fire season
preparedness.