Forecasting the Ambient Solar Wind With a Physics-Informed Learned Inner Boundary: Part I-Differentiable Inverse Reconstruction From Solar Images
The solar-wind speed at the inner boundary of heliospheric models is not observed; near-Earth monitors record the wind only after nonlinear propagation. We pose the reconstruction of an effective boundary speed at $21.5\,R_\odot$ as an inverse problem and train a map from solar observations to that boundary by differentiating through a reduced heliospheric transport solver from 21.5$\,R_\odot$ to measurement locations near the L1 Lagrangian point. Screening 42 candidate features from SDO/AIA 193~Å images and SDO/HMI magnetograms identifies coronal-hole area, its proximity to the ecliptic and its darkness as the most informative; the reference model adds their recent history, the expansion factor of GONG-based potential-field models and the speed observed one rotation earlier. In five-fold chronological cross-validation over solar cycle 24, the reconstruction outperforms 27-day recurrence and a linear regression on the screened features at a fixed lead (ROC area for wind above 600~km~s$^{-1}$: 0.879 versus 0.802 and 0.850) with a predicted-to-observed standard-deviation ratio of 0.81, at the cost of a $+26$~km~s$^{-1}$ bias from its tail-weighted loss. A factorial comparison shows that the skill comes from training through a speed-dependent propagation: a fixed lag degrades the score by 8.6~km~s$^{-1}$, stream interaction adds little, and a linear map, or a model with one coefficient per physical quantity, matches the neural network. About 57\% of the variance of the hourly speed is not determined by these inputs, and the remaining error is common to all model classes: better reconstructions need more informative inputs rather than more flexible models. Forecasting and probabilistic prediction are addressed in Parts II and III.