Closed-Loop Electrolyte Design for Lithium-Mediated Ammonia Synthesis
Abstract
Novel methods for producing ammonia, a large-scale industrial chemical, are necessary for reducing the environmental impact of its production. Lithium-mediated electrochemical nitrogen reduction is one attractive alternative method for producing ammonia. In this work, we experimentally tested several classes of proton donors for activity in the lithium-mediated approach. From these data, an interpretable data-driven classification model is constructed to distinguish between active and inactive proton donors; solvatochromic Kamlet–Taft parameters emerged to be the key descriptors for predicting nitrogen reduction activity. A deep learning model is trained to predict these parameters using experimental data from the literature. The combination of the classification and deep learning models provides a predictive mapping from proton donor structure to activity for nitrogen reduction. We demonstrate that the two-model approach is superior to a purely mechanistic or a data-driven approach in accuracy and experimental data efficiency.
Additional Information
© 2021 The Authors. Published by American Chemical Society. Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0). Received 20 September 2021. Published online 2 December 2021. Published in issue 22 December 2021. We thank Matt Wolski of Daramic for providing us with polyporous separator samples. This material is based upon work supported by the National Science Foundation under Grant No. 1944007. Funding for this research was provided by the Abdul Latif Jameel World Water and Food Systems Lab (J-WAFS) at MIT. N.L. acknowledges support by the National Science Foundation Graduate Research Fellowship under Grant No. 1122374. D.K. and V.V. gratefully acknowledge funding support from the National Science Foundation under Award CBET-1554273. D.K. and V.V. thank Dr. Bharath Ramsundar for useful discussions and feedback about the computational models and the deep-learning methodology. V.V. acknowledges support from the Scott Institute for Energy Innovation at Carnegie Mellon University. D.K. acknowledges discussions with Victor Venturi regarding the deep-learning model implementation. Author Contributions. D.K. and N.L. contributed equally. Conceptualization: N.L. and K.M. Methodology - Experimental: N.L. Methodology - Modeling: D.K. and V.V. Investigation: N.L. and M.L.G. Formal analysis: D.K. and V.V. Data curation: D.K. Writing - Original Draft: N.L. and D.K. Writing - Review and Editing: N.L., D.K., K.M., and V.V. Supervision: K.M. and V.V. The authors declare the following competing financial interest(s): D.K., V.V., N.L., and K.M. are inventors on a provisional patent application, 63/066841, related to hydrogen donors for lithium-mediated ammonia synthesis.Attached Files
Published - acscentsci.1c01151.pdf
Supplemental Material - oc1c01151_si_001.pdf
Files
Name | Size | Download all |
---|---|---|
md5:c55be0c0f73423e2ff31df8e9b39c476
|
2.0 MB | Preview Download |
md5:0bf312069b4c9e3154c2269b43aa9b38
|
9.3 MB | Preview Download |
Additional details
- PMCID
- PMC8704027
- Eprint ID
- 114606
- Resolver ID
- CaltechAUTHORS:20220505-565053000
- CBET-1944007
- NSF
- Massachusetts Institute of Technology (MIT)
- DGE-1122374
- NSF Graduate Research Fellowship
- CBET-1554273
- NSF
- Carnegie Mellon University
- Created
-
2022-05-06Created from EPrint's datestamp field
- Updated
-
2022-05-06Created from EPrint's last_modified field