Connor Cremers, Chenghao Wan, Calvin H. Lin et al.
We present induction-heated resonant reactors, a new concept in electrified thermochemistry in which the reactor itself serves as a volumetric electromagnetic resonator heated through resonant wireless power transfer. We use the Swiss roll resonator as a model system and show that it can be designed to support uniform volumetric heating profiles and enhanced heat transfer characteristics, creating opportunities for process intensification in scaled systems. Compared to conventional (i.e., non-resonant) induction heating systems, resonant reactors can achieve exceptionally high system efficiencies through the combination of near-unity power-to-heat efficiencies and low thermal losses, both enabled by the utilization of resonant energy transfer. These concepts demonstrate how the integration of electromagnetic power transduction with thermochemical reaction engineering enables new opportunities for utilizing green electricity in sustainable chemical conversion.
Frank Hu, Michael S. Chen, Grant M. Rotskoff et al. · stanford
Rapid determination of molecular structures can greatly accelerate workflows across many chemical disciplines. However, elucidating structure using only one-dimensional (1D) NMR spectra, the most readily accessible data, remains an extremely challenging problem because of the combinatorial explosion of the number of possible molecules as the number of constituent atoms is increased. Here, we introduce a multitask machine learning framework that predicts the molecular structure (formula and connectivity) of an unknown compound solely based on its 1D 1H and/or 13C NMR spectra. First, we show how a transformer architecture can be constructed to efficiently solve the task, traditionally performed by chemists, of assembling large numbers of molecular fragments into molecular structures. Integrating this capability with a convolutional neural network (CNN), we build an end-to-end model for predicting structure from spectra that is fast and accurate. We demonstrate the effectiveness of this framework on molecules with up to 19 heavy (non-hydrogen) atoms, a size for which there are trillions of possible structures. Without relying on any prior chemical knowledge such as the molecular formula, we show that our approach predicts the exact molecule 69.6% of the time within the first 15 predictions, reducing the search space by up to 11 orders of magnitude.