Thermodynamics-Informed Machine Learning of Organic Electrode Material Solubility in Nonaqueous Electrolytes.

Organic electrode materials (OEMs) based on abundant elements, such as C, N, O, and S, represent a promising class of sustainable alternatives to traditional transition-metal-based cathodes. However, discovery of new OEMs remains slow and resource-intensive because the design process is dominated by empirical trial-and-error. Although recent machine-learning approaches have accelerated the identification of redox-active compounds, the prediction of OEM solubility─a critical property governing cycle life─remains a major bottleneck. Here, we developed a physics-informed model for predicting OEM solubility using solvation energies (ΔGsolv) and sublimation (ΔGsub) energetics derived from a curated set of 44 redox-active organic compounds. While the DFT-calculated ΔGsolv and sublimation enthalpies (ΔHsub) correlate well with experimental measurements, the computed sublimation entropies (ΔSsub) exhibit large systematic errors, thereby limiting the overall predictive accuracy based on first-principles thermodynamics alone. To overcome this limitation, we integrated the physically meaningful computed descriptors into our recently developed symbolic regression framework, SyMANTIC, which learns a corrective model for solubility prediction in nonaqueous electrolytes. Despite the modest data set size, the resulting hybrid model shows good predictive performance under cross-validation and on held-out test compounds, illustrating that this framework can recover compact, chemically meaningful structure-property relationships and offers a new path toward rational design of low-solubility OEMs with reduced reliance on trial-and-error experimentation.