Neural Network Emulator for Atmospheric Chemical ODE

TL;DR

This paper introduces ChemNNE, an attention-based neural network emulator that models atmospheric chemical ODEs efficiently, achieving high accuracy and speed through innovative embeddings, Fourier neural operators, and physics-informed training.

Contribution

The paper presents a novel neural network emulator for atmospheric chemistry that combines attention mechanisms, sinusoidal time embeddings, Fourier neural operators, and physics-informed losses.

Findings

Achieves state-of-the-art accuracy in chemical modeling.

Significantly faster computation compared to traditional methods.

Provides a large-scale dataset for training and evaluation.

Abstract

Modeling atmospheric chemistry is complex and computationally intense. Given the recent success of Deep neural networks in digital signal processing, we propose a Neural Network Emulator for fast chemical concentration modeling. We consider atmospheric chemistry as a time-dependent Ordinary Differential Equation. To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process. To efficiently simulate the chemical changes, we propose the sinusoidal time embedding to estimate the oscillating tendency over time. More importantly, we use the Fourier neural operator to model the ODE process for efficient computation. We also propose three physical-informed losses to supervise the training optimization. To evaluate our model, we propose a large-scale chemical dataset that can be used for neural network training and evaluation. The extensive experiments show that our approach achieves state-of-the-art performance in modeling accuracy and computational speed.