Michael Stephen Chen

All Publications

• Data-Efficient Machine Learning Potentials from Transfer Learning of Periodic Correlated Electronic Structure Methods: Liquid Water at AFQMC, CCSD, and CCSD(T) Accuracy. Journal of chemical theory and computation Chen, M. S., Lee, J., Ye, H. Z., Berkelbach, T. C., Reichman, D. R., Markland, T. E. 2023

  Abstract

  Obtaining the atomistic structure and dynamics of disordered condensed-phase systems from first-principles remains one of the forefront challenges of chemical theory. Here we exploit recent advances in periodic electronic structure and provide a data-efficient approach to obtain machine-learned condensed-phase potential energy surfaces using AFQMC, CCSD, and CCSD(T) from a very small number (≤200) of energies by leveraging a transfer learning scheme starting from lower-tier electronic structure methods. We demonstrate the effectiveness of this approach for liquid water by performing both classical and path integral molecular dynamics simulations on these machine-learned potential energy surfaces. By doing this, we uncover the interplay of dynamical electron correlation and nuclear quantum effects across the entire liquid range of water while providing a general strategy for efficiently utilizing periodic correlated electronic structure methods to explore disordered condensed-phase systems.

  View details for DOI 10.1021/acs.jctc.2c01203

  View details for PubMedID 36730728

• Optically Induced Anisotropy in Time-Resolved Scattering: Imaging Molecular-Scale Structure and Dynamics in Disordered Media with Experiment and Theory. Physical review letters Montoya-Castillo, A., Chen, M. S., Raj, S. L., Jung, K. A., Kjaer, K. S., Morawietz, T., Gaffney, K. J., van Driel, T. B., Markland, T. E. 2022; 129 (5): 056001

  Abstract

  Time-resolved scattering experiments enable imaging of materials at the molecular scale with femtosecond time resolution. However, in disordered media they provide access to just one radial dimension thus limiting the study of orientational structure and dynamics. Here we introduce a rigorous and practical theoretical framework for predicting and interpreting experiments combining optically induced anisotropy and time-resolved scattering. Using impulsive nuclear Raman and ultrafast x-ray scattering experiments of chloroform and simulations, we demonstrate that this framework can accurately predict and elucidate both the spatial and temporal features of these experiments.

  View details for DOI 10.1103/PhysRevLett.129.056001

  View details for PubMedID 35960558

• A framework for automated structure elucidation from routine NMR spectra. Chemical science Huang, Z., Chen, M. S., Woroch, C. P., Markland, T. E., Kanan, M. W. 2021; 12 (46): 15329-15338

  Abstract

  Methods to automate structure elucidation that can be applied broadly across chemical structure space have the potential to greatly accelerate chemical discovery. NMR spectroscopy is the most widely used and arguably the most powerful method for elucidating structures of organic molecules. Here we introduce a machine learning (ML) framework that provides a quantitative probabilistic ranking of the most likely structural connectivity of an unknown compound when given routine, experimental one dimensional 1H and/or 13C NMR spectra. In particular, our ML-based algorithm takes input NMR spectra and (i) predicts the presence of specific substructures out of hundreds of substructures it has learned to identify; (ii) annotates the spectrum to label peaks with predicted substructures; and (iii) uses the substructures to construct candidate constitutional isomers and assign to them a probabilistic ranking. Using experimental spectra and molecular formulae for molecules containing up to 10 non-hydrogen atoms, the correct constitutional isomer was the highest-ranking prediction made by our model in 67.4% of the cases and one of the top-ten predictions in 95.8% of the cases. This advance will aid in solving the structure of unknown compounds, and thus further the development of automated structure elucidation tools that could enable the creation of fully autonomous reaction discovery platforms.

  View details for DOI 10.1039/d1sc04105c

  View details for PubMedID 34976353

  View details for PubMedCentralID PMC8635205

• AENET-LAMMPS and AENET-TINKER: Interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials JOURNAL OF CHEMICAL PHYSICS Chen, M. S., Morawietz, T., Mori, H., Markland, T. E., Artrith, N. 2021; 155 (7): 074801

  Abstract

  Machine-learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular dynamics and Monte Carlo simulations, an integration of the MLPs with sampling software is needed. Here, we develop two interfaces that link the atomic energy network (ænet) MLP package with the popular sampling packages TINKER and LAMMPS. The three packages, ænet, TINKER, and LAMMPS, are free and open-source software that enable, in combination, accurate simulations of large and complex systems with low computational cost that scales linearly with the number of atoms. Scaling tests show that the parallel efficiency of the ænet-TINKER interface is nearly optimal but is limited to shared-memory systems. The ænet-LAMMPS interface achieves excellent parallel efficiency on highly parallel distributed-memory systems and benefits from the highly optimized neighbor list implemented in LAMMPS. We demonstrate the utility of the two MLP interfaces for two relevant example applications: the investigation of diffusion phenomena in liquid water and the equilibration of nanostructured amorphous battery materials.

  View details for DOI 10.1063/5.0063880

  View details for Web of Science ID 000685163500002

  View details for PubMedID 34418919

• Exploiting Machine Learning to Efficiently Predict Multidimensional Optical Spectra in Complex Environments. The journal of physical chemistry letters Chen, M. S., Zuehlsdorff, T. J., Morawietz, T., Isborn, C. M., Markland, T. E. 2020: 7559–68

  Abstract

  The excited-state dynamics of chromophores in complex environments determine a range of vital biological and energy capture processes. Time-resolved, multidimensional optical spectroscopies provide a key tool to investigate these processes. Although theory has the potential to decode these spectra in terms of the electronic and atomistic dynamics, the need for large numbers of excited-state electronic structure calculations severely limits first-principles predictions of multidimensional optical spectra for chromophores in the condensed phase. Here, we leverage the locality of chromophore excitations to develop machine learning models to predict the excited-state energy gap of chromophores in complex environments for efficiently constructing linear and multidimensional optical spectra. By analyzing the performance of these models, which span a hierarchy of physical approximations, across a range of chromophore-environment interaction strengths, we provide strategies for the construction of machine learning models that greatly accelerate the calculation of multidimensional optical spectra from first principles.

  View details for DOI 10.1021/acs.jpclett.0c02168

  View details for PubMedID 32808797

• Molecular identification of polymers and anthropogenic particles extracted from oceanic water and fish stomach - A Raman micro-spectroscopy study ENVIRONMENTAL POLLUTION Ghosal, S., Chen, M., Wagner, J., Wang, Z., Wall, S. 2018; 233: 1113-1124

  Abstract

  Pacific Ocean trawl samples, stomach contents of laboratory-raised fish as well as fish from the subtropical gyres were analyzed by Raman micro-spectroscopy (RMS) to identify polymer residues and any detectable persistent organic pollutants (POP). The goal was to access specific molecular information at the individual particle level in order to identify polymer debris in the natural environment. The identification process was aided by a laboratory generated automated fluorescence removal algorithm. Pacific Ocean trawl samples of plastic debris associated with fish collection sites were analyzed to determine the types of polymers commonly present. Subsequently, stomach contents of fish from these locations were analyzed for ingested polymer debris. Extraction of polymer debris from fish stomach using KOH versus ultrapure water were evaluated to determine the optimal method of extraction. Pulsed ultrasonic extraction in ultrapure water was determined to be the method of choice for extraction with minimal chemical intrusion. The Pacific Ocean trawl samples yielded primarily polyethylene (PE) and polypropylene (PP) particles >1 mm, PE being the most prevalent type. Additional microplastic residues (1 mm - 10 μm) extracted by filtration, included a polystyrene (PS) particle in addition to PE and PP. Flame retardant, deca-BDE was tentatively identified on some of the PP trawl particles. Polymer residues were also extracted from the stomachs of Atlantic and Pacific Ocean fish. Two types of polymer related debris were identified in the Atlantic Ocean fish: (1) polymer fragments and (2) fragments with combined polymer and fatty acid signatures. In terms of polymer fragments, only PE and PP were detected in the fish stomachs from both locations. A variety of particles were extracted from oceanic fish as potential plastic pieces based on optical examination. However, subsequent RMS examination identified them as various non-plastic fragments, highlighting the importance of chemical analysis in distinguishing between polymer and non-polymer residues.

  View details for DOI 10.1016/j.envpol.2017.10.014

  View details for Web of Science ID 000424177000118

  View details for PubMedID 29037491