Search Results for « SchNet »

Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not restricted to a grid. Instead, their precise locations contain essential physical information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles. This includes rotationally invariant energy predictions and a smooth, differentiable potential energy surface. Our architecture achieves state-of-the-art performance for benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally, we introduce a more challenging benchmark with chemical and structural variations that suggests the path for further work.

OE62 data set + molecues generated with G-SchNet trained on the OE62 data set. Minimal tutorial for using the SchNet+H models and the adapted G-SchNet model individually and for creating new molecules with targeted properties. Includes the code from https://github.com/rhyan10/G-SchNetOE62 and https://github.com/schnarc/SchNarc/ used for this tutorial.

In recent years, deep learning has become a part of our everyday life and is revolutionizing quantum chemistry as well. In this work, we show how deep learning can be used to advance the research field of photochemistry by learning all important properties-multiple energies, forces, and different couplings-for photodynamics simulations. We simplify such simulations substantially by (i) a phase-free training skipping costly preprocessing of raw quantum chemistry data; (ii) rotationally covariant nonadiabatic couplings, which can either be trained or (iii) alternatively be approximated from only ML potentials, their gradients, and Hessians; and (iv) incorporating spin-orbit couplings. As the deep-learning method, we employ SchNet with its automatically determined representation of molecular structures and extend it for multiple electronic states. In combination with the molecular dynamics program SHARC, our approach termed SchNarc is tested on two polyatomic molecules and paves the way toward efficient photodynamics simulations of complex systems.

Quantum materials present significant challenges due to their inherent complexity in physical systems. With the rapid development of deep learning, it is accessible to make prediction of the complicated behaviors in quantum materials. This paper proposed a new neural network SchNet+ to better narrate the complexity of systems, which can not be easily solved by traditional mathematical equations.

Vision Foundation Model (VFM) such as the Segment Anything Model (SAM) and Contrastive Language-Image Pre-training Model (CLIP) has shown promising performance for segmentation and detection tasks. However, although SAM excels in fine-grained segmentation, it faces major challenges when applying it to semantic-aware segmentation. While CLIP exhibits a strong semantic understanding capability via aligning the global features of language and vision, it has deficiencies in fine-grained segmentation tasks. Human parsing requires to segment human bodies into constituent parts and involves both accurate fine-grained segmentation and high semantic understanding of each part. Based on traits of SAM and CLIP, we formulate high efficient modules to effectively integrate features of them to benefit human parsing. We propose a Semantic-Refinement Module to integrate semantic features of CLIP with SAM features to benefit parsing. Moreover, we formulate a high efficient Fine-tuning Module to adjust the pretrained SAM for human parsing that needs high semantic information and simultaneously demands spatial details, which significantly reduces the training time compared with full-time training and achieves notable performance. Extensive experiments demonstrate the effectiveness of our method on LIP, PPP, and CIHP databases.

Machine-learning force fields provide a promising route for accelerating molecular simulation by replacing expensive quantum-chemical calculations with differentiable models of molecular energies and atomic forces. However, learning accurate and energy-conserving forces remains challenging, especially when the model must capture both global energy trends and local potential-energy gradients from limited data. In this work, we propose a Hybrid Quantum SchNet architecture that integrates variational quantum circuit modules into the continuous-filter SchNet framework. Quantum modules are inserted into the filter generator, atom-wise update, and readout transformations, allowing quantum-enhanced feature mappings to contribute to distance-dependent interactions and atomic energy prediction while preserving the energy-gradient formulation of forces. The model is evaluated on eight MD17 molecular systems using 1000 training configurations per molecule. Compared with energy-only training, joint energy--force supervision substantially improves both energy and force prediction accuracy. Compared with energy-only training, joint energy--force supervision substantially improves both energy and force prediction accuracy. Averaged over the benchmark, the energy MAE decreases from 2.567 to 0.593 kcal mol$^{-1}$, while the force MAE decreases from 16.340 to 1.540 kcal mol$^{-1}$ Å$^{-1}$. Ablation experiments on ethanol further show that the performance of the hybrid model depends on the balance between quantum circuit width, circuit depth, and optimization stability. These results demonstrate that variational quantum circuits can be incorporated into neural force-field architectures and trained end-to-end to improve molecular energy and force prediction.

Data associated with the paper entitled On application of Deep Learning to simplified quantum-classical dynamics in electronically excited states Three TD-DFTB datasets (sX_10_force.db) have been produced using the Atomic Simulation Environment (ASE) coupled to deMon-Nano code for the linear response Time-Dependent Density Functional based Tight-Binding (TD-DFTB) calculations. Each dataset contains 10000 TD-DFTB electronic structure calculations for a given excited singlet state (S2/S3/S4) of a neutral phenanthrene molecule. Each database entry contains Cartesian atomic coordinates as well as potential energy and atomic forces for a given excited state at a given geometry. Since ASE has been used, all physical quantities are stored in the corresponding units (e.g. eV for energy or eV/Å for forces). The file format is SQLite as provided by the ASE; Three pre-trained Deep Learning models (best_model_sX) for a given excited singlet state have been produced using SchNetPack package, which implements the SchNet architecture for atomistic simulations. Each model has been trained using the corresponding TD-DFTB dataset from #1. The file format is binary as provided by the SchNetPack; 500_init_conditions.tar.gz contains 500 initial conditions (Cartesian coordinates and velocities), which can be used for Trajectory Surface Hopping (TSH) simulations with or without the pre-trained models from #2.