YLYou Li

You Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


You Li has a total of 28 co-authors. Here are the top co-authors by number of shared publications:

  • Hui Li

    State Key Laboratory of Supramolecular Structure and Materials, Institute of Theoretical Chemistry, College of Chemistry, Jilin University, Changchun, China

    8 shared publications
  • Yu Zhai

    Beijing National Laboratory For Molecular Sciences, Institute of Theoretical and Computational Chemistry, College of Chemistry and Molecular Engineering, Peking University, Beijing, China

    4 shared publications
  • Jitai Yang

    State Key Laboratory of Supramolecular Structure and Materials, Institute of Theoretical Chemistry, College of Chemistry, Jilin University, Changchun, China

    3 shared publications
  • Hui Li

    Jilin University 2519 Jiefang Road

    2 shared publications
  • Jia Nie

    Jilin University 2519 Jiefang Road

    2 shared publications
  • Xiao-Long Zhang

    The Laboratory of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering

    2 shared publications

Latest Publications

  • A Physics-Constrained Synergetic Active- and Transfer-Learning Framework for Constructing a Spectroscopically Accurate Full-Dimensional Potential Energy Surface of H2O–N2 Complex

    by Jia Nie, You Li, Zhixia Wang, Xiaolong Zhang, Hui Li

    High-resolution spectroscopy of weakly bound molecular complexes requires theoretical predictions with uncertainties below 0.1 cm–1. Achieving this level of accuracy places stringent demands on the underlying full-dimensional potential energy surfaces (PESs). However, constructing such PESs remains challenging because flexible configuration space requires dense sampling and the ab initio energies used for fitting must meet spectroscopic accuracy requirements. Here, we develop a physics-constrained synergetic active- and transfer-learning framework (SynATL) that combines uncertainty-driven active learning, high-level refinement via transfer learning, and an explicit long-range representation to construct spectroscopically accurate full-dimensional PESs. SynATL was used to construct a full-dimensional PES of the H2O–N2 complex at the post-CCSD(T) level, achieving a weighted root-mean-square error (RMSE) of 0.815 cm–1 on the test set and sub-cm–1 RMSEs in the spectroscopically relevant low-energy and attractive regions. Applied to rovibrational calculations of H2O–N2 and D2O–N2, the resulting PES reproduces microwave transitions with a root-mean-square deviation (RMSD) of 1.6 × 10–4 cm–1, about 80% lower than previous theoretical values, and gives 10–3 cm–1 level band-specific RMSDs for 235 assigned infrared lines across the H2O–N2 bending/overtone and D2O–N2 stretching/bending bands. SynATL therefore provides an efficient and transferable framework for full-dimensional PESs for quantitative spectroscopy of weakly bound complexes.

  • Constructing Spectroscopic-Accuracy Potential Energy Surfaces beyond CCSD(T) via Active and Transfer Learning: A Case Study of H 2 O–Ne

    by Huan Wang, Jia Nie, You Li, Zhi-Xia Wang, Xiao-Long Zhang, Yu-Rong Hu, Hui Li

    High-resolution rovibrational spectroscopy and quantum dynamics are highly sensitive to the accuracy of the potential energy surfaces (PESs). Although machine learning (ML) models have shown great PES fitting capability, achieving spectroscopic accuracy commonly requires 10 000 or more points, thereby limiting the use of high-level quantum chemical methods. Here, we present a two-step ML framework to significantly reduce data requirements. First, an uncertainty-driven active learning (AL) strategy is employed to construct a robust baseline neural network PES at the CCSD(T) level. Then, a constrained transfer learning (TL) approach is used to improve the quality of the baseline PES beyond CCSD(T). In our test of the H2O-Ne system, only 601 and 59 points are required for the AL and TL stages, respectively. The resulting TL PES achieves improved agreement with experiment. For the |101⟩∑e(000,0) ← |000⟩∑e(101,0) transition band, the root-mean-square error (RMSE) is reduced from 0.156 cm-1 for the baseline PES to 0.022 cm-1 for the TL PES. This work establishes a transferable and efficient framework for constructing high-accuracy potential energy surfaces for weakly bound molecular complexes.

  • Using Weighted and Chopped Rectangular Collocation Methods with Tensor-Product Contracted Bases To Compute Vibrational Spectra: Avoiding Quadrature

    by You Li, Tucker Carrington

    Product contracted (PC) bases are efficient for computing (ro-)vibrational spectra of molecules. However, to account for coupling between subsystems, all previous PC methods require computing integrals by quadrature. The cost of the quadrature is significant and increases with the dimensionality of the molecule. In this paper, we propose a weighted and chopped rectangular collocation (WC–RC) method that obviates quadrature. We use Christoffel weights and Christoffel–Fekete (CF) collocation points. They are known to be near-optimal for weighted least-squares fitting. Matrix chopping increases the accuracy of energy levels. An additional chopping makes it possible to symmetry adapt (SA) the calculation. With the WC–RC method, we achieve sub-0.1 cm–1 accuracy for both 9-D CH2NH and 6-D HF dimer using many fewer points than required when quadrature is used.


  • Applying the active learning strategy to the construction of full-dimensional neural network potential energy surfaces: Critical tests in H2O–He spectroscopic calculation

    by You Li, Xiao-Long Zhang, Hui Li

    An uncertainty-driven active learning strategy was employed to achieve efficient point sampling for full-dimension potential energy surface constructions. Model uncertainty is defined as the weighted square energy difference between two neural network models, and the local maximums of uncertainty would be added to the training set by two criteria. A two-step sampling procedure was introduced to reduce the computational costs of expansive double-precision neural network training. A reference potential energy surface (PES) of the 6-D H2O–He system was constructed first by the MLRNet model with a weighted Root-Mean-Square-Error (RMSE) of 0.028 cm−1. The full-dimension long-range function was fitted by a pruned basis expansion method. The current sampling method is reliable for the long-range switched fundamental invariant neural network (LS-FI-NN) to construct spectroscopically accurate PES, where the single precision model achieves a test set RMSE of 0.3253 cm−1 with 472 fitting points and the double precision model is 0.0710 cm−1 with only 613 points. In comparison, the MLRNet requires 652 points to reach a similar accuracy. However, the MLRNet, with fewer parameters, shows lower training errors across all sampling cycles and lower test errors in the first few cycles, indicating its potential with an appropriate sampling procedure. The spectroscopic calculations were performed to validate the accuracy of PESs. The energy levels of the double precision LS-FI-NN showed great agreement with the reference PES’s results, with only 0.0161 and 0.0044 cm−1 average errors for vibrational levels and the band origin shifts.


  • Open Access

    Employing the active learning strategy to construct full-dimensional intermolecular potential energy surfaces within spectroscopic accuracy

    by You Li, Xiao-Long Zhang, Hui Li

    In this work, we employed an uncertainty-driven active learning strategy to achieve highly efficient point sampling for full-dimension potential energy surface constructions. The model uncertainty is defined as the weighted square energy difference between two neural network (NN) models trained with the same dataset, and the local maximums of uncertainty would be added into the training set by two criteria. A two-step sampling procedure was introduced to reduce the computational costs of expansive double-precision neural network training. The 6-D H$_2$O-He system was chosen as the test system. A reference PES was constructed firstly by the newly developed MLRNet model with a weighted RMSE of 0.028 cm$^{-1}$, where the full-dimension long-range function was fitted by a pruned basis expansion method. Our tests demonstrate that it is also reliable for the long-range switched fundamental invariant neural network (LS-FI-NN) to construct spectroscopically accurate PES, however, it is less inefficient for the newly developed MLRNet model. For the first single-precision sampling, the LS-FI-NN only requires 472 fitting points to achieve a weighted-RMSE of 0.3253 cm$^{-1}$ for 47945 test points. In comparison, the MLRNet requires 652 points to reach a similar accuracy. Notably, the MLRNet demonstrated lower training errors across all sampling cycles and lower test errors in the first few cycles with less trainable parameters, which indicates its potential with an appropriate sampling procedure. For the second double-precision sampling, the LS-FI-NN achieved a test RMSD of 0.0710 cm$^{-1}$ with only 613 points, while the MLRNet can't converge to a given threshold for tens of iterations. The spectroscopic calculations were performed to further validate the accuracy of these PESs. The energy levels of the double precision LS-FI-NN showed great agreement with the reference PES's results, with only 0.0161 cm$^{-1}$ and 0.0044 cm$^{-1}$ average errors for vibrational levels and the band origin shifts.

  • Open Access

    Revealing the Ultrafast Energy Transfer Pathways in Energetic Materials: Time-Dependent and Quantum State-Resolved

    by Jia Liu, Jitai Yang, Gangbei Zhu, Jiarui Li, You Li, Yu Zhai, Huajie Song, Yanqiang Yang, Hui Li

    Intramolecular vibrational energy transfer is gaining tremendous attention as a regulator of condensed-phase behavior and reactions. In polyatomic molecules, this transfer is an ultrafast process involving multiple modes with numerous quantum states. The inherent complexity and rapid evolution of these processes pose significant challenges to experimental observation, and the high computational costs make full quantum mechanical calculations impractical with current technology. In the intramolecular energy transfer process, whether the doorway modes are intermediaries for transferring energy from lattice phonons to high-frequency intramolecular vibrational modes has been a controversial issue. However, the broad range of doorway modes complicates the experimental identification of a specific doorway in the transfer process corresponding to a specific end point. Here, for the first time, we utilize a combination of vibrational projection, statistical analysis, and the local quantum vibrational embedding (LQVE) method to elucidate the ultrafast energy transfer pathways that upconvert energy from lattice phonons to intramolecular modes in the typical energetic material β-HMX. This approach enables us to resolve the coupled vibrational mode groups, identify the most probable energy transfer pathways corresponding to the different final modes, and clearly confirm that the doorway region is a mandatory pathway for energy transfer. The LQVE method's time-dependent and quantum state-resolved advantages are leveraged to reveal the microscopic mechanism of the energy transfer process. The time scale of these processes is determined at about 1 ps, and the first theoretical two-dimensional infrared spectroscopy evidence is provided, which is confirmed by the experimental results. These findings deliver important insights into the fundamental mechanisms of ultrafast energy transfer in energetic materials, providing theoretical support for controlling explosive behavior and designing new explosives. The methodologies developed in this work can be extended to other condensed phase materials and used to evaluate the coupling between multiple vibrational modes.


  • Machine Learning Approach Based on a Range-Corrected Deep Potential Model for Efficient Vibrational Frequency Computation

    by Jitai Yang, Yang Cong, You Li, Hui Li

    As an ensemble average result, vibrational spectrum simulation can be time-consuming with high accuracy methods. We present a machine learning approach based on the range-corrected deep potential (DPRc) model to improve the computing efficiency. The DPRc method divides the system into "probe region" and "solvent region"; "solvent-solvent" interactions are not counted in the neural network. We applied the approach to two systems: formic acid C═O stretching and MeCN C≡N stretching vibrational frequency shifts in water. All data sets were prepared using the quantum vibration perturbation approach. Effects of different region divisions, one-body correction, cut range, and training data size were tested. The model with a single-molecule "probe region" showed stable accuracy; it ran roughly 10 times faster than regular deep potential and reduced the training time by about four. The approach is efficient, easy to apply, and extendable to calculating various spectra.


  • MLRNet: Combining the Physics-Motivated Potential Models with Neural Networks for Intermolecular Potential Energy Surface Construction

    by You Li, Yu Zhai, Hui Li

    A physics-based machine learning model called MLRNet has been developed to construct the high-accuracy two-body intermolecular potential energy surface (IPES). The outputs of the neural network are integrated into the physically realistic Morse/long-range (MLR) function, which ensures that the MLRNet has meaningful extrapolation at both short and long ranges and solves the asymptotic problem in common neural network potential (NNP) models. The neural network representation of the MLR parameters is more flexible and more efficient than the polynomial expansion in the conventional mdMLR model, especially for systems containing nonrigid monomer(s). The present work illustrates the basic framework of the current MLRNet model, including (i) how to combine the physically meaningful MLR function with different possible NN structures, (ii) the preservation of permutation symmetry, and (iii) the predetermination of the long-range function uLR. We choose two realistic systems to demonstrate the performance of MLRNet: the three-dimensional IPES of CO2-He including the CO2 antisymmetric vibration Q3 and the six-dimensional IPES of the H2O-Ar system. In both cases, the fitting errors of the MLRNet are several times smaller than those of the conventional mdMLR model. Both short-range and long-range extrapolation tests were performed to illustrate the extrapolation ability of the MLRNet and its damping function version. Moreover, for the 6-D H2O-Ar system, the MLRNet only needs 1596 trainable parameters, which is almost equal to the number needed for the 5-D mdMLR model (1509) and half that needed for the PIP-NN model (3501) within similar accuracy, which illustrates the model efficiency in high-dimensional IPES fitting.


  • Open Access

    MLRNet: Combining physics-motivated potential model with neural network for intermolecular potential energy surface construction

    by You Li, Yu Zhai, Hui Li

    A physics-based machine learning model called MLRNet has been developed to construct the high-accuracy two-body intermolecular potential energy surface (IPES). The outputs of the neural network are integrated into the physically realistic Morse/Long Range (MLR) function, which ensures that the MLRNet has meaningful extrapolation at both short and long ranges and solves the asymptotic problem in common neural network potential (NNP) models. The neural network representation of the MLR parameters is more flexible and more efficient than the polynomials expansion in the conventional mdMLR model, especially for systems containing non-rigid monomer(s). The present work illustrates the basic framework of the current MLRNet model, including (i) how to combine the physically meaningful MLR function with different possible NN structures, (ii) the preservation of permutation symmetry, and (iii) the predetermination of the long-range function uLR. We choose two realistic systems to demonstrate the performance of MLRNet: the 3-dimensional IPES of CO2-He including CO2 anti-symmetric vibration Q3, and the 6-dimensional IPES of H2O-Ar system. In both cases, the fitting errors of the MLRNet are several times smaller than those of the conventional mdMLR model. Both the short-range and long-range extrapolation tests have been performed to illustrate the extrapolation ability of the MLRNet and its damping function version. Moreover, for the 6-D H2O-Ar system, the MLRNet only needs 1596 trainable parameters which are almost equal 5-D mdMLR model (1509) and half of the PIP-NN model (3501) with similar accuracy, which illustrates the model efficiency in high-dimensional IPES fitting.