Search for: All records

Machine learning potentials (MLPs) are poised to combine the accuracy of ab initio predictions with the computational efficiency of classical molecular dynamics (MD) simulation. While great progress has been made over the last two decades in developing MLPs, there is still much to be done to evaluate their model transferability and facilitate their development. In this work, we construct two deep potential (DP) models for liquid water near graphene surfaces, Model S and Model F, with the latter having more training data. A concurrent learning algorithm (DP-GEN) is adopted to explore the configurational space beyond the scope of conventional ab initio MD simulation. By examining the performance of Model S, we find that an accurate prediction of atomic force does not imply an accurate prediction of system energy. The deviation from the relative atomic force alone is insufficient to assess the accuracy of the DP models. Based on the performance of Model F, we propose that the relative magnitude of the model deviation and the corresponding root-mean-square error of the original test dataset, including energy and atomic force, can serve as an indicator for evaluating the accuracy of the model prediction for a given structure, which is particularly applicable for large systems where density functional theory calculations are infeasible. In addition to the prediction accuracy of the model described above, we also briefly discuss simulation stability and its relationship to the former. Both are important aspects in assessing the transferability of the MLP model.

 

Modeling electric double layer (EDL) capacitance with physics-informed Gaussian process regression (PhysGPR) avoids unphysical predictions that might be encountered in conventional machine learning methods.

 

Porous carbons are the active materials of choice for supercapacitor applications because of their power capability, long-term cycle stability, and wide operating temperatures. However, the development of carbon active materials with improved physicochemical and electrochemical properties is generally carried out via time-consuming and cost-ineffective experimental processes. In this regard, machine-learning technology provides a data-driven approach to examine previously reported research works to find the critical features for developing ideal carbon materials for supercapacitors. Here, we report the design of a machine-learning-derived activation strategy that uses sodium amide and cross-linked polymer precursors to synthesize highly porous carbons (i.e., with specific surface areas > 4000 m²/g). Tuning the pore size and oxygen content of the carbonaceous materials, we report a highly porous carbon-base electrode with 0.7 mg/cm²of electrode mass loading that exhibits a high specific capacitance of 610 F/g in 1 M H₂SO₄. This result approaches the specific capacitance of a porous carbon electrode predicted by the machine learning approach. We also investigate the charge storage mechanism and electrolyte transport properties via step potential electrochemical spectroscopy and quasielastic neutron scattering measurements.

 

MXenes are 2D materials with great potential in various applications. However, the degradation of MXenes in humid environments has become a main obstacle in their practical use. Here we combine deep neural networks and an active learning scheme to develop a neural network potential (NNP) for aqueous MXene systems with ab initio precision but low cost. The oxidation behaviors of super large aqueous MXene systems are investigated systematically at nanosecond timescales for the first time. The oxidation process of MXenes is clearly displayed at the atomic level. Free protons and oxides greatly inhibit subsequent oxidation reactions, leading to the degree of oxidation of MXenes to exponentially decay with time, which is consistent with the oxidation rate of MXenes measured experimentally. Importantly, this computational study represents the first exploration of the kinetic process of oxidation of super‐sized aqueous MXene systems. It opens a promising avenue for the future development of effective protection strategies aimed at controlling the stability of MXenes.

 

A statistical emulator can be used as a surrogate of complex physics-based calculations to drastically reduce the computational cost. Its successful implementation hinges on an accurate representation of the nonlinear response surface with a high-dimensional input space. Conventional “space-filling” designs, including random sampling and Latin hypercube sampling, become inefficient as the dimensionality of the input variables increases, and the predictive accuracy of the emulator can degrade substantially for a test input distant from the training input set. To address this fundamental challenge, we develop a reliable emulator for predicting complex functionals by active learning with error control (ALEC). The algorithm is applicable to infinite-dimensional mapping with high-fidelity predictions and a controlled predictive error. The computational efficiency has been demonstrated by emulating the classical density functional theory (cDFT) calculations, a statistical-mechanical method widely used in modeling the equilibrium properties of complex molecular systems. We show that ALEC is much more accurate than conventional emulators based on the Gaussian processes with “space-filling” designs and alternative active learning methods. In addition, it is computationally more efficient than direct cDFT calculations. ALEC can be a reliable building block for emulating expensive functionals owing to its minimal computational cost, controllable predictive error, and fully automatic features. 

Efficient separation of C₂H₄/C₂H₆mixtures is of paramount importance in the petrochemical industry. Nanoporous materials, especially metal-organic frameworks (MOFs), may serve the purpose owing to their tailorable structures and pore geometries. In this work, we propose a computational framework for high-throughput screening and inverse design of high-performance MOFs for adsorption and membrane processes. High-throughput screening of the computational-ready, experimental (CoRE 2019) MOF database leads to materials with exceptionally high ethane-selective adsorption selectivity (LUDLAZ: 7.68) and ethene-selective membrane selectivity (EBINUA02: 2167.3). Moreover, the inverse design enables the exploration of broader chemical space and identification of MOF structures with even higher membrane selectivity and permeability. In addition, a relative membrane performance score (rMPS) has been formulated to evaluate the overall membrane performance relative to the Robeson boundary. The computational framework offers guidelines for the design of MOFs and is generically applicable to materials discovery for gas storage and separation.

 

Molecular design of redox-active materials with higher solubility and greater redox potential windows is instrumental in enhancing the performance of redox flow batteries Here we propose a computational procedure for a systematic evaluation of organic redox-active species by combining machine learning, quantum-mechanical, and classical density functional theory calculations. 1,517 small quinone molecules were generated from the building blocks of benzoquinone, naphthoquinone, and anthraquinone with different substituent groups. The physics-based methods were used to predict HOMO-LUMO gaps and solvation free energies that account for the redox potential differences and aqueous solubility, respectively. The high-throughput calculations were augmented with the quantitative structure-property relationship analyses and machine learning/graph network modeling to evaluate the materials’ overall behavior. The computational procedure was able to reproduce high-performance cathode electrolyte materials consistent with experimental observations and identify new electrolytes for RFBs by screening 100,000 di-substituted quinone molecules, the largest library of redox-active quinone molecules ever investigated. The efficient computational platform may facilitate a better understanding of the structure-function relationship of quinone molecules and advance the design and application of all-organic active materials for RFBs.

 

Gaussian process (GP) emulator has been used as a surrogate model for predicting force field and molecular potential, to overcome the computational bottleneck of ab initio molecular dynamics simulation. Integrating both atomic force and energy in predictions was found to be more accurate than using energy alone, yet it requires O(( NM) 3 ) computational operations for computing the likelihood function and making predictions, where N is the number of atoms and M is the number of simulated configurations in the training sample due to the inversion of a large covariance matrix. The high computational cost limits its applications to the simulation of small molecules. The computational challenge of using both gradient information and function values in GPs was recently noticed in machine learning communities, whereas conventional approximation methods may not work well. Here, we introduce a new approach, the atomized force field model, that integrates both force and energy in the emulator with many fewer computational operations. The drastic reduction in computation is achieved by utilizing the naturally sparse covariance structure that satisfies the constraints of the energy conservation and permutation symmetry of atoms. The efficient machine learning algorithm extends the limits of its applications on larger molecules under the same computational budget, with nearly no loss of predictive accuracy. Furthermore, our approach contains an uncertainty assessment of predictions of atomic forces and energies, useful for developing a sequential design over the chemical input space.