Development of a data-driven lightning model for implementation in
Global Climate Models
Abstract
This study proposes a new global-scale lightning model, predicting
lightning rates from large-scale climatic variables. Using satellite
lightning records spanning a period of 29 years, we apply machine
learning methods to derive a functional relationship between lightning
and climate reanalysis data. In particular, we design a model tree,
representing different lightning regimes with separate single hidden
layer neural networks of low dimensionality. We apply multiple
complexity constraints in the model development stages, which makes the
lightning model straightforward to implement as a lightning scheme for
global climate models (GCMs). We demonstrate that, for years not used
for model training, our lightning model captures 70.6% of the daily
global spatio-temporal lightning variability, which corresponds to a
>42% relative improvement compared to well-established
lightning schemes. Similarly, the model correlates well with lightning
observations for the monthly climatology (r>0.92),
inter-annual variability (r>0.90), and latitudinal and
longitudinal distributions (r>0.86). Most notably, the
model brings a critical improvement in representing lightning magnitude
and variability in the three tropical lightning chimney regions: central
Africa, the Amazon, and the Maritime Continent. We implement the
lightning model in the Community Earth System Model to verify its
stability and performance as a GCM component, and we provide detailed
implementation guidelines. As an intermediate approach between
high-dimensional machine learning models and first-order lightning
parameterizations, our model offers GCMs a straightforward and efficient
tool to improve lightning simulation, which is critical for representing
atmospheric chemistry and naturally-ignited wildfires.