Sections
Text Area

Research & Publications

 

Research

Left Column
Image
Image
ai4cell
Right Column
Text Area

1.    AI for Whole-Cell Simulations: 


AI-driven whole-cell simulations represent a paradigm shift in biological discovery, unlocking unprecedented power to model cellular complexity at molecular resolution. By integrating machine learning with biophysical principles, AI transcends traditional computational limits—predicting protein folding in milliseconds instead of months, simulating metabolic networks in dynamic microenvironments, and forecasting emergent cellular behaviors impossible to capture experimentally. This synergy enables virtual experiments on rare cell types, disease states, or drug interactions at minimal cost. AI for whole cells will revolutionize our capacity to decode life’s machinery—making the invisible visible, the untestable testable, and transforming biology from observation to prediction.

Left Column
Image
Image
ai4sustainability
Right Column
Text Area

2.    AI for Sustainability: 
 

AI-driven sustainability provides a unique chance to incorporate the power of fundamental laws in physics, chemistry, and earth sciences into deep learning architectures. By integrating theoretical modeling, computational simulations, generative models, and AI agents, our mission is to bridge the gap between isolated applications and the complex, equilibrium, non-equilibrium, and multiscale dynamics of physical, chemical, and climate systems, from modeling mass transport in aqueous solutions and at solid-state interfaces to understanding the carbon cycle and the dynamics of climate change. This fusion allows us to construct "Digital Twins" of physical and environmental processes that respect scientific constraints while enabling the predictive design and optimization of sustainable systems and solutions, which finally leads to a green chemistry and carbon-neutral future.

Left Column
Image
Image
ai4innovation
Right Column
Text Area

3.    AI for Innovation, Firm Competitiveness and Regional Growth: 


AI-driven economics research is catalyzing a revolution in innovation, firm competitiveness, and regional growth, turning data into strategic advantage and systemic resilience. By integrating machine learning with economic theory, AI transcends traditional constraints—optimizing operations in real-time, forecasting market shifts with unprecedented granularity, and uncovering hidden opportunities through predictive innovation ecosystems. This integration enables businesses to accelerate innovation, adapt swiftly to market fluctuations, and secure a competitive advantage in turbulent landscapes.  At the regional scale, AI maps talent-capital-technology clusters, simulates policy impacts (e.g., tax incentives, infrastructure investments, trade war shocks), and tracks economic spillovers to foster inclusive startup cultures and attract high-impact investments. By transforming economic complexity into actionable strategy, AI shifts firms from reactive adaptation to proactive disruption and empowers regions to ignite sustainable, broad-based prosperity—turning unpredictability into opportunity. AI becomes a springboard for inclusive economic dissemination, guaranteeing prosperity extends beyond conventional hubs to diverse regions, turning conventional economics research into strategic advantage and reshaping economic theory into tangible actions.

 

Text Area

Selected Publications

(Updated as of 10 Feb, 2026)

Text Area

2026

Benchmarking foundation potential against quantum chemistry methods for predicting molecular redox potentials    

In arXiv [physics.chem-ph]
Chen, Y., Cheng, L., Jing, Y., & Zhong, P.
DOI: 10.48550/arXiv.2510.24063 

 

2025

Diffusion Monte Carlo study of the structure and spectroscopy of H3 

The Journal of Physical Chemistry. A, 129(47), 10928–10939
Jacobson, G. M., Webb, A. W., Cheng, L., & McCoy, A. B.
DOI: 10.1021/acs.jpca.5c06590

SimPoly: Simulation of polymers with machine learning force fields derived from first principles   

In arXiv [physics.chem-ph]
Simm, G. N. C., Hélie, J., Schulz, H., Chen, Y., Simeon, G., Kuzina, A., Martinez-Baez, E., Gasparotto, P., Tocci, G., Chen, C., Li, Y., Cheng, L., Wang, Z., Nguyen, B. H., Smith, J. A., & Sun, L. 
DOI: 10.48550/arXiv.2510.13696

Unravelling the evolution of nickel-catalyzed C–O bond activation with data-driven strategies   

Organic Chemistry Frontiers: An International Journal of Organic Chemistry, 13(1), 182–193
Zhu, J., Wang, Y., Rava, I., Chen, S., Zou, Z., Huang, Y., Lin, Z., & Su, H. 
DOI: Zhu, J., Wang, Y., Rava, I., Chen, S., Zou, Z., Huang, Y., Lin, Z., & Su, H. (2026). . . https://doi.org/10.1039/d5qo00947b

Deep generative modeling of the canonical ensemble with differentiable thermal properties   

Physical Review Letters, 135(2), 027301
Li, S.-H., Zhang, Y.-W., & Pan, D. 
DOI: 10.1103/8wx7-kyx8 

An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking   

In arXiv [physics.chem-ph]
Foster, A., Schätzle, Z., Szabó, P. B., Cheng, L., Köhler, J., Cassella, G., Gao, N., Li, J., Noé, F., & Hermann, J.  
DOI: 10.48550/ARXIV.2506.19960 

Comparison of AI and NWP models in operational severe weather forecasting: A study on tropical cyclone predictions   

Journal of Geophysical Research: Machine Learning and Computation, 2(2)
Shi, Y., Hu, R., Wu, N., Zhang, H., Liu, X., Zeng, Z., Zhu, J., Han, P., Luo, C., Zhang, H., He, J., & Shi, X.  
DOI: 10.1029/2024jh000481 

Universality of dynamic flow structures in active viscoelastic liquids   

Journal of Fluid Mechanics, 1007(R7)
Feng, Z., Qian, T., & Zhang, R. 
DOI: 10.1017/jfm.2025.177

Machine learning approaches for developing potential surfaces: Applications to OH-(H2O)n (n = 1-3) complexes   

The Journal of Physical Chemistry. A, 129(12), 2958–2972
Jacobson, G. M., Cheng, L., Bhethanabotla, V. C., Sun, J., & McCoy, A. B. 
DOI: 10.1021/acs.jpca.4c08826

Highly accurate real-space electron densities with neural networks   

The Journal of Chemical Physics, 162(3)
Cheng, L., Szabó, P. B., Schätzle, Z., Kooi, D. P., Köhler, J., Giesbertz, K. J. H., Noé, F., Hermann, J., Gori-Giorgi, P., & Foster, A. 
DOI: 10.1063/5.0236919

 

2024

Unveiling hidden reaction kinetics of carbon dioxide in supercritical aqueous solutions   

Proceedings of the National Academy of Sciences of the United States of America, 122(1), e2406356121
Li, C., Yao, Y., & Pan, D.  
DOI: 110.1073/pnas.2406356121

Synthesis and stability of biomolecules in C-H-O-N fluids under Earth’s upper mantle conditions   

Journal of the American Chemical Society, 146(45), 31240–31250
Li, T., Stolte, N., Tao, R., Sverjensky, D. A., Daniel, I., & Pan, D. 
DOI: 10.1021/jacs.4c11680 

Predicting the urban stormwater drainage system state using the Graph-WaveNet   

Sustainable Cities and Society, 115(105877), 105877
Li, M., Shi, X., Lu, Z., & Kapelan, Z.  
DOI: 10.1016/j.scs.2024.105877

Escalating tropical cyclone precipitation extremes and landslide hazards in South China under Global Warming   

Npj Climate and Atmospheric Science, 7(1)
Shi, X., Liu, Y., Chen, J., Chen, H., Wang, Y., Lu, Z., Wang, R.-Q., Fung, J. C.-H., & Ng, C. W. W.   
DOI: 10.1038/s41612-024-00654-w

Quantum approximate optimization via learning-based adaptive optimization   

Communications Physics, 7(1)
Cheng, L., Chen, Y.-Q., Zhang, S.-X., & Zhang, S.   
DOI: 10.1038/s42005-024-01577-x

Moiré effect enables versatile design of topological defects in nematic liquid crystals   

Nature Communications, 15(1), 1655
Wang, X., Jiang, J., Chen, J., Asilehan, Z., Tang, W., Peng, C., & Zhang, R. 
DOI: 10.1038/s41467-024-45529-z

Chiral active particles are sensitive reporters to environmental geometry   

Nature Communications, 15(1), 1406
Chan, C. W., Wu, D., Qiao, K., Fong, K. L., Yang, Z., Han, Y., & Zhang, R. 
DOI: 10.1038/s41467-024-45531-5

Symmetry breaking of self-propelled topological defects in thin-film active chiral nematics   

Physical Review Letters, 132(3), 038301
Wang, W., Ren, H., & Zhang, R.  
DOI: 10.1103/PhysRevLett.132.038301

 

2023

The impact of large language models on scientific discovery: A preliminary study using GPT-4   

In arXiv [cs.CL]
AI4Science, M. R., & Quantum, M. A.  
DOI: 10.48550/ARXIV.2311.07361

Can a machine learning–enabled numerical model help extend effective forecast range through consistently trained subgrid-scale models?   

Artificial Intelligence for the Earth Systems, 2(1), 1–31
Qu, Y., & Shi, X. 
DOI: 10.1175/aies-d-22-0050.1 

 

2022

Molecular-orbital-based machine learning for open-shell and multi-reference systems with kernel addition Gaussian process regression   

The Journal of Chemical Physics, 157(15), 154105
Cheng, L., Sun, J., Deustua, J. E., Bhethanabotla, V. C., & Miller, T. F., 3rd.  
DOI: 10.1063/5.0110886

Nanoconfinement facilitates reactions of carbon dioxide in supercritical water   

Nature Communications, 13(1), 5932
Stolte, N., Hou, R., & Pan, D.  
DOI: 10.1038/s41467-022-33696-w

Molecular dipole moment learning via rotationally equivariant derivative kernels in molecular-orbital-based machine learning   

The Journal of Chemical Physics, 157(10), 104109
Sun, J., Cheng, L., & Miller, T. F., 3rd. 
DOI: 10.1063/5.0101280 

Accurate molecular-orbital-based machine learning energies via unsupervised clustering of chemical space   

Journal of Chemical Theory and Computation, 18(8), 4826–4835
Cheng, L., Sun, J., & Miller, T. F., 3rd. (2022) 
DOI: 10.1021/acs.jctc.2c00396

Fast near ab initio potential energy surfaces using machine learning   

The Journal of Physical Chemistry. A, 126(25), 4013–4024
Lu, F., Cheng, L., DiRisio, R. J., Finney, J. M., Boyer, M. A., Moonkaen, P., Sun, J., Lee, S. J. R., Deustua, J. E., Miller, T. F., 3rd, & McCoy, A. B. 
DOI: 10.1021/acs.jpca.2c02243

ODBO: Bayesian optimization with search space prescreening for directed protein evolution   

In arXiv [q-bio.BM]
Cheng, L., Yang, Z., Hsieh, C., Liao, B., & Zhang, S. 
DOI: 10.48550/ARXIV.2205.09548

 

2021

Molecular energy learning using alternative blackbox matrix-matrix multiplication algorithm for exact Gaussian Process   

Paper presented at the NeurIPS 2021 AI for Science Workshop
Sun, J., Cheng, L., & Miller, T. F., III  
DOI: --

Spatiotemporal control of liquid crystal structure and dynamics through activity patterning   

Nature Materials, 20(6), 875–882
Zhang, R., Redford, S. A., Ruijgrok, P. V., Kumar, N., Mozaffari, A., Zemsky, S., Dinner, A. R., Vitelli, V., Bryant, Z., Gardel, M. L., & de Pablo, J. J.   
DOI: 10.1038/s41563-020-00901-4

Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states   

The Journal of Chemical Physics, 154(6), 064108
Husch, T., Sun, J., Cheng, L., Lee, S. J. R., & Miller, T. F., 3rd 
DOI: 10.1063/5.0032362 

 

2020

Enabling smart dynamical downscaling of extreme precipitation events with machine learning   

Geophysical Research Letters, 47(19)
Shi, X.  
DOI: 10.1029/2020gl090309

 

2019

Regression clustering for improved accuracy and training costs with molecular-orbital-based machine learning   

Journal of Chemical Theory and Computation, 15(12), 6668–6677
Cheng, L., Kovachki, N. B., Welborn, M., & Miller, T. F., 3rd.  
DOI: 10.1021/acs.jctc.9b00884

A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules   

The Journal of Chemical Physics, 150(13), 131103
Cheng, L., Welborn, M., Christensen, A. S., & Miller, T. F., 3rd. 
DOI: 10.1063/1.5088393 

 

2018

Transferability in machine learning for electronic structure via the molecular orbital basis   

Journal of Chemical Theory and Computation, 14(9), 4772–4779
Welborn, M., Cheng, L., & Miller, T. F., 3rd. 
DOI: 10.1021/acs.jctc.8b00636