Towards the Habitable Worlds Observatory: Retrieval of Reflection Spectra from Evolving Earth Analogues using 1D CNNs
The Habitable Worlds Observatory (HWO) will characterize Earth-like exoplanets from low-resolution reflected-light spectra. To assess how atmospheric evolution shapes what can be recovered, we trained a convolutional neural network on 109,945 spectra generated with the Planetary Spectrum Generator for Archean, Proterozoic, and Modern atmospheres under LUVOIR-B and HabEx/SS observing assumptions, separating the contributions of observational noise and model variability. We find that recovery depends jointly on abundance and spectral structure. Across eras, O$_2$ recovery weakens in Proterozoic atmospheres and CH$_4$ becomes reliable only when abundant, while an isolated UV band yields robust Modern O$_3$ recovery ($R^2\simeq0.98$) despite poor Modern CH$_4$ recovery ($R^2=0.32$-$0.35$). Without being supplied feature locations, the network assigns $58$-$71\%$ of total attribution to visible wavelengths, while the ultraviolet remains decisive for O$_3$ and the near-infrared for CH$_4$ and CO$_2$. Aggregate retrieval leverage declines beyond approximately $1.7\,μ$m, supporting a practical long-wavelength boundary in this setup. These wavelength dependencies also shape detectability. At baseline noise, $83$-$85\%$ of Modern O$_2$ cases satisfy a $3σ$ criterion, while Proterozoic O$_2$ remains below $50\%$ when noise is halved and Modern CH$_4$ remains below $3σ$ as observational noise approaches zero because model uncertainty caps its significance. Together, these results imply molecule-specific priorities for HWO trade studies. Low-abundance O$_2$ retains considerable leverage from improved observational quality while motivating better inference, whereas at the 1,000-hour benchmark O$_3$ and Modern CH$_4$ show predominantly model-associated uncertainty in these networks, motivating broader training coverage and improved uncertainty calibration.