Search for: All records

Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivari- ance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel super- computers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by com- bining the Allegro model with sharpness aware minimization (SAM) for enhanc- ing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and “smooth”) model was shown to elongate the time-to-failure tfailure, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of time- to-failure on the problem size, t_failure = N^−0.14 (N is the number of atoms) compared to the SOTA Allegro model (t_failure ∝ N^−0.29), i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalabil- ity and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia to lay a foundation of the green ammonia technology for sustainability. 

Computing landscape is evolving rapidly. Exascale computers have arrived, which can perform 10^18 mathematical operations per second. At the same time, quantum supremacy has been demonstrated, where quantum computers have outperformed these fastest supercomputers for certain problems. Meanwhile, artificial intelligence (AI) is transforming every aspect of science and engineering. A highly anticipated application of the emerging nexus of exascale computing, quantum computing and AI is computational design of new materials with desired functionalities, which has been the elusive goal of the federal materials genome initiative. The rapid change in computing landscape resulting from these developments has not been matched by pedagogical developments needed to train the next generation of materials engineering cyberworkforce. This gap in curricula across colleges and universities offers a unique opportunity to create educational tools, enabling a decentralized training of cyberworkforce. 

Machine learning represents a milestone in data-driven research, including material informatics, robotics, and computer-aided drug discovery. With the continuously growing virtual and synthetically available chemical space, efficient and robust quantitative structure–activity relationship (QSAR) methods are required to uncover molecules with desired properties. Herein, we propose variable-length-array SMILES-based (VLA-SMILES) structural descriptors that expand conventional SMILES descriptors widely used in machine learning. This structural representation extends the family of numerically coded SMILES, particularly binary SMILES, to expedite the discovery of new deep learning QSAR models with high predictive ability. VLA-SMILES descriptors were shown to speed up the training of QSAR models based on multilayer perceptron (MLP) with optimized backpropagation (ATransformedBP), resilient propagation (iRPROP‒), and Adam optimization learning algorithms featuring rational train–test splitting, while improving the predictive ability toward the more compute-intensive binary SMILES representation format. All the tested MLPs under the same length-array-based SMILES descriptors showed similar predictive ability and convergence rate of training in combination with the considered learning procedures. Validation with the Kennard–Stone train–test splitting based on the structural descriptor similarity metrics was found more effective than the partitioning with the ranking by activity based on biological activity values metrics for the entire set of VLA-SMILES featured QSAR. Robustness and the predictive ability of MLP models based on VLA-SMILES were assessed via the method of QSAR parametric model validation. In addition, the method of the statistical H0 hypothesis testing of the linear regression between real and observed activities based on the F2,n−2 -criteria was used for predictability estimation among VLA-SMILES featured QSAR-MLPs (with n being the volume of the testing set). Both approaches of QSAR parametric model validation and statistical hypothesis testing were found to correlate when used for the quantitative evaluation of predictabilities of the designed QSAR models with VLA-SMILES descriptors. 

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which ami-no-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predict-ing contacts with a wide range of distances (commonly classified into short-, me-dium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the Pro-teinNet dataset show improved accuracy for contacts of all ranges using the pro-posed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction. 

Metal-fullerene compounds are characterized by significant electron transfer to the fullerene cage, giving rise to an electric dipole moment. We use the method of electrostatic beam deflection to verify whether such reactions take place within superfluid helium nanodroplets between an embedded C 60 molecule and either alkali (heliophobic) or rare-earth (heliophilic) atoms. The two cases lead to distinctly different outcomes: C 60 Na n ( n = 1–4) display no discernable dipole moment, while C 60 Yb is strongly polar. This suggests that the fullerene and small alkali clusters fail to form a charge-transfer bond in the helium matrix despite their strong van der Waals attraction. The C 60 Yb dipole moment, on the other hand, is in agreement with the value expected for an ionic complex. 

We present sharpness-aware minimization (SAM) for fluid dynamics which can efficiently learn the plausible dynamics of liquid splashes. Due to its ability to achieve robust and generalizing solutions, SAM efficiently converges to a parameter set that predicts plausible dynamics of elusive liquid splashes. Our training scheme requires 6 times smaller number of epochs to converge and, 4 times shorter wall-clock time. Our result shows that sharpness of loss function has a close connection to the plausibility of fluid dynamics and suggests further applicability of SAM to machine learning based fluid simulation.