As illustrated by the work of Ralph White, traditional methods of electrochemical engineering are based on human intelligence: Mathematical models encoding physical hypotheses are proposed, tested against experimental data and refined by fitting adjustable parameters. Artificial intelligence is beginning to challenge this paradigm, since predictions can be made directly from data without the need for models, but such knowledge is often not transferrable to new situations. This talk will present a hybrid approach of solving PDE-constrained inverse problems to derive new multiscale models, in the context of Li-ion batteries. Examples include learning models of reaction kinetics and surface heterogeneities from x-ray adsorption images of phase separation in lithium iron phosphate nanoparticles [1], x-ray diffraction spectra for fictitious phase separation in nickel-rich oxide porous electrodes [2], and optical videos of lithium plating on graphite particles [3].[1] H. Zhao, H. D. Deng, A. E. Cohen, J. Lim, Y. Li, D. Fraggedakis, B. Jiang, B. D. Storey, W. C. Chueh, R. D. Braatz, and M. Z. Bazant, Learning heterogeneous reaction kinetics from X-ray movies pixel-by-pixel, preprint, https://www.researchsquare.com/article/rs-2320040/v1[2] J. Park, H. Zhao, S. D. Kang, K. Lim, C.-C. Chen, Y.-S. Yu, R. D. Braatz, D. A. Shapiro, J. Hong, M. F. Toney, M. Z. Bazant, and W. C. Chueh, Fictitious Phase Separation in Li Layered Oxides Driven by Electro-Autocatalysis, Nature Materials 20, 991-999 (2021).[3] T. Gao, Y. Han, D. Fraggedakis, S. Das, T. Zhou, C.-N. Yeh, S. Xu, W. C. Chueh, J. Li, M. Z. Bazant, Interplay of lithium intercalation and plating on a single graphite particle, Joule 5, 1-22 (2021).