A chemistry-informed deep learning network for mitigating the stratospheric OH data gap.

The hydroxyl (OH) radical is a key species in stratospheric chemistry, driving ozone loss and the coupling of other chemical families. However, global OH observations are very sparse, with a critical gap in satellite-based observations since 2009. Although alternative chemical methods attempt to mitigate such gaps, they have limitations. Here, we present DRCAT, a chemistry-informed deep learning network to predict stratospheric OH profiles using coincident satellite observations of chemically related species. Trained on only 2 years of data, DRCAT provides reconstruction of a continuous and reliable global stratospheric OH dataset from late 2004 to the present. Results show that DRCAT outperforms both a chemical transport model and an observation-constrained steady-state approximation. Moreover, DRCAT successfully predicts anomalous OH enhancements after the 2022 Hunga volcanic eruption, showing generalizability to extreme conditions outside of the training regime. DRCAT thus provides a robust pathway to fill OH observational voids. Beyond OH, this work offers a scalable framework for similar reconstruction of other key short-lived species.