Atmospheric chemistry models—components in models that simulate air pollution and climate change—are computationally expensive. Previous studies have shown that machine‐learned atmospheric chemical solvers can be orders of magnitude faster than traditional integration methods but tend to suffer from numerical instability. Here, we present a modeling framework that reduces error accumulation compared to previous work while maintaining computational efficiency. Our approach is novel in that it (1) uses a recurrent training regime that results in extended (>1 week) simulations without exponential error accumulation and (2) can reversibly compress the number of modeled chemical species by >80% without further decreasing accuracy. We observe an ~260× speedup (~1,900× with specialized hardware) compared to the traditional solver. We use random initial conditions in training to promote general applicability across a wide range of atmospheric conditions. For ozone (concentrations ranging from 0–70 ppb), our model predictions over a 24‐hr simulation period match those of the reference solver with median error of 2.7 and <19 ppb error across 99% of simulations initialized with random noise. Error can be significantly higher in the remaining 1% of simulations, which include extreme concentration fluctuations simulated by the reference model. Results are similar for total particulate matter (median error of 16 and <32 μg/m³ across 99% of simulations with concentrations ranging from 0–150 μg/m³). Finally, we discuss practical implications of our modeling framework and next steps for improvements. The machine learning models described here are not yet replacements for traditional chemistry solvers but represent a step toward that goal.

中文翻译：

---

建立稳定的，通用的机器学习的大气化学系统模型

大气化学模型（模拟空气污染和气候变化的模型中的组件）在计算上非常昂贵。先前的研究表明，机器学习的大气化学求解器可以比传统的积分方法快几个数量级，但往往会出现数值不稳定的情况。在这里，我们提出了一个建模框架，与以前的工作相比，它减少了错误累积，同时保持了计算效率。我们的方法的新颖之处在于：1）使用循环训练方案，可以进行扩展的（> 1周）模拟，而不会出现指数误差累积，并且2）可以可逆地将建模化学物种的数量压缩> 80％，而不会进一步降低准确性。与传统的求解器相比，我们观察到了约260倍的加速（专用硬件约为1900倍）。我们在训练中使用随机的初始条件，以促进在广泛的大气条件下的普遍适用性。对于臭氧（浓度范围为0–70 ppb），我们在24小时模拟期内的模型预测与参考求解器的模型预测相符，在随机噪声初始化的99％模拟中，中值误差为2.7 ppb，误差小于19 ppb。在其余1％的模拟中，误差可能会更高，其中包括参考模型模拟的极端浓度波动。总颗粒物的结果相似（中值误差为16μg/ m 我们在24小时仿真期内的模型预测与参考求解器的模型预测相匹配，在随机噪声初始化的99％模拟中，中值误差为2.7 ppb，误差小于19 ppb。在其余1％的模拟中，误差可能会更高，其中包括参考模型模拟的极端浓度波动。总颗粒物的结果相似（中值误差为16μg/ m 我们在24小时仿真期内的模型预测与参考求解器的模型预测相匹配，在随机噪声初始化的99％模拟中，中值误差为2.7 ppb，误差小于19 ppb。在其余1％的模拟中，误差可能会更高，其中包括参考模型模拟的极端浓度波动。总颗粒物的结果相似（中值误差为16μg/ m在99％的模拟中浓度为³和<32μg/ m ³，浓度范围为0-150μg/ m ³）。最后，我们讨论了建模框架的实际含义以及下一步的改进步骤。这里描述的机器学习模型尚未替代传统的化学求解器，但代表了朝着这一目标迈出的一步。