Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation
This work addresses the problem of slow atmospheric chemistry simulations for environmental researchers, offering a significant speedup but requiring further error control for long-term simulations.
The paper tackles the computational expense of chemical transport models by using a neural network to emulate the CBM-Z gas-phase chemical mechanism, achieving a 250x speedup on CPU and up to 4250x on GPU with low error rates (median RMSE = 0.02 ppb).
Chemical transport models (CTMs), which simulate air pollution transport, transformation, and removal, are computationally expensive, largely because of the computational intensity of the chemical mechanisms: systems of coupled differential equations representing atmospheric chemistry. Here we investigate the potential for machine learning to reproduce the behavior of a chemical mechanism, yet with reduced computational expense. We create a 17-layer residual multi-target regression neural network to emulate the Carbon Bond Mechanism Z (CBM-Z) gas-phase chemical mechanism. We train the network to match CBM-Z predictions of changes in concentrations of 77 chemical species after one hour, given a range of chemical and meteorological input conditions, which it is able to do with root-mean-square error (RMSE) of less than 1.97 ppb (median RMSE = 0.02 ppb), while achieving a 250x computational speedup. An additional 17x speedup (total 4250x speedup) is achieved by running the neural network on a graphics-processing unit (GPU). The neural network is able to reproduce the emergent behavior of the chemical system over diurnal cycles using Euler integration, but additional work is needed to constrain the propagation of errors as simulation time progresses.