skip to main content


Title: Artificial intelligence-enhanced quantum chemical method with broad applicability
Abstract High-level quantum mechanical (QM) calculations are indispensable for accurate explanation of natural phenomena on the atomistic level. Their staggering computational cost, however, poses great limitations, which luckily can be lifted to a great extent by exploiting advances in artificial intelligence (AI). Here we introduce the general-purpose, highly transferable artificial intelligence–quantum mechanical method 1 (AIQM1). It approaches the accuracy of the gold-standard coupled cluster QM method with high computational speed of the approximate low-level semiempirical QM methods for the neutral, closed-shell species in the ground state. AIQM1 can provide accurate ground-state energies for diverse organic compounds as well as geometries for even challenging systems such as large conjugated compounds (fullerene C 60 ) close to experiment. This opens an opportunity to investigate chemical compounds with previously unattainable speed and accuracy as we demonstrate by determining geometries of polyyne molecules—the task difficult for both experiment and theory. Noteworthy, our method’s accuracy is also good for ions and excited-state properties, although the neural network part of AIQM1 was never fitted to these properties.  more » « less
Award ID(s):
2041108
NSF-PAR ID:
10319555
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Nature Communications
Volume:
12
Issue:
1
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Reliable simulations of molecules in condensed phase require the combination of an accurate quantum mechanical method for the core region, and a realistic model to describe the interaction with the environment. Additionally, this combination should not significantly increase the computational cost of the calculation compared to the corresponding in vacuo case. In this review, we describe the combination of methods based on coupled cluster (CC) theory with polarizable classical models for the environment. We use the polarizable continuum model (PCM) of solvation to discuss the equations, but we also show how the same theoretical framework can be extended to polarizable force fields. The theory is developed within the perturbation theory energy and singles‐T density (PTES) scheme, where the environmental response is computed with the CC single excitation amplitudes as an approximation for the full one‐particle reduced density. The CC‐PTES combination provides the best compromise between accuracy and computational effort for CC calculations in condensed phase, because it includes the response of the environment to the correlation density at the same computational cost of in vacuo CC. We discuss a number of numerical applications for ground and excited state properties, based on the implementation of CC‐PTES with single and double excitations (CCSD‐PTES), which show the reliability and computational efficiency of the method in reproducing experimental or full‐CC data.

    This article is characterized under:

    Electronic Structure Theory > Ab Initio Electronic Structure Methods

    Electronic Structure Theory > Combined QM/MM Methods

    Software > Quantum Chemistry

     
    more » « less
  2. null (Ed.)
    The Interface force field (IFF) enables accurate simulations of bulk and interfacial properties of compounds and multiphase materials. However, the simulation of reactions and mechanical properties up to failure remains challenging and expensive. Here we introduce the Reactive Interface Force Field (IFF-R) to analyze bond breaking and failure of complex materials using molecular dynamics simulations. IFF-R uses a Morse potential instead of a harmonic potential as typically employed in molecular dynamics force fields to describe the bond energy, which can render any desired bond reactive by specification of the curve shape of the potential energy and the bond dissociation energy. This facile extension of IFF and other force fields that utilize a harmonic bond energy term allows the description of bond breaking without loss in functionality, accuracy, and speed. The method enables quantitative, on-the-fly computations of bond breaking and stress-strain curves up to failure in any material. We illustrate accurate predictions of mechanical behavior for a variety of material systems, including metals (iron), ceramics (carbon nanotubes), polymers (polyacrylonitrile and cellulose I\b{eta}), and include sample parameters for common bonds based on using experimental and high-level (MP2) quantum mechanical reference data. Computed structures, surface energies, elastic moduli, and tensile strengths are in excellent agreement with available experimental data. Non-reactive properties are shown to be essentially identical to IFF values. Computations are approximately 50 times faster than using ReaxFF and require only a single set of parameters. Compatibility of IFF and IFF-R with biomolecular force fields allows the quantitative analysis of the mechanics of proteins, DNA, and other biological molecules. 
    more » « less
  3. Abstract

    Information about the spatial distribution of species lies at the heart of many important questions in ecology. Logistical limitations and collection biases, however, limit the availability of such data at ecologically relevant scales. Remotely sensed information can alleviate some of these concerns, but presents challenges associated with accurate species identification and limited availability of field data for validation, especially in high diversity ecosystems such as tropical forests.

    Recent advances in machine learning offer a promising and cost‐efficient approach for gathering a large amount of species distribution data from aerial photographs. Here, we propose a novel machine learning framework, artificial perceptual learning (APL), to tackle the problem of weakly supervised pixel‐level mapping of tree species in forests. Challenges arise from limited availability of ground labels for tree species, lack of precise segmentation of tree canopies and misalignment between visible canopies in the aerial images and stem locations associated with ground labels. The proposed APL framework addresses these challenges by constructing a workflow using state‐of‐the‐art machine learning algorithms.

    We develop and illustrate the proposed framework by implementing a fine‐grain mapping of three species, the palmPrestoea acuminataand the tree speciesCecropia schreberianaandManilkara bidentata, over a 5,000‐ha area of El Yunque National Forest in Puerto Rico. These large‐scale maps are based on unlabelled high‐resolution aerial images of unsegmented tree canopies. Misaligned ground‐based labels, available for <1% of these images, serve as the only weak supervision. APL performance is evaluated using ground‐based labels and high‐quality human segmentation using Amazon Mechanical Turk, and compared to a basic workflow that relies solely on labelled images.

    Receiver operating characteristic (ROC) curves and Intersection over Union (IoU) metrics demonstrate that APL substantially outperforms the basic workflow and attains human‐level cognitive economy, with 50‐fold time savings. For the palm andC. schreberiana, the APL framework has high pixelwise accuracy and IoU with reference to human segmentations. ForM.bidentata, APL predictions are congruent with ground‐based labels. Our approach shows great potential for leveraging existing data from global forest plot networks coupled with aerial imagery to map tree species at ecologically meaningful spatial scales.

     
    more » « less
  4. BACKGROUND Electromagnetic (EM) waves underpin modern society in profound ways. They are used to carry information, enabling broadcast radio and television, mobile telecommunications, and ubiquitous access to data networks through Wi-Fi and form the backbone of our modern broadband internet through optical fibers. In fundamental physics, EM waves serve as an invaluable tool to probe objects from cosmic to atomic scales. For example, the Laser Interferometer Gravitational-Wave Observatory and atomic clocks, which are some of the most precise human-made instruments in the world, rely on EM waves to reach unprecedented accuracies. This has motivated decades of research to develop coherent EM sources over broad spectral ranges with impressive results: Frequencies in the range of tens of gigahertz (radio and microwave regimes) can readily be generated by electronic oscillators. Resonant tunneling diodes enable the generation of millimeter (mm) and terahertz (THz) waves, which span from tens of gigahertz to a few terahertz. At even higher frequencies, up to the petahertz level, which are usually defined as optical frequencies, coherent waves can be generated by solid-state and gas lasers. However, these approaches often suffer from narrow spectral bandwidths, because they usually rely on well-defined energy states of specific materials, which results in a rather limited spectral coverage. To overcome this limitation, nonlinear frequency-mixing strategies have been developed. These approaches shift the complexity from the EM source to nonresonant-based material effects. Particularly in the optical regime, a wealth of materials exist that support effects that are suitable for frequency mixing. Over the past two decades, the idea of manipulating these materials to form guiding structures (waveguides) has provided improvements in efficiency, miniaturization, and production scale and cost and has been widely implemented for diverse applications. ADVANCES Lithium niobate, a crystal that was first grown in 1949, is a particularly attractive photonic material for frequency mixing because of its favorable material properties. Bulk lithium niobate crystals and weakly confining waveguides have been used for decades for accessing different parts of the EM spectrum, from gigahertz to petahertz frequencies. Now, this material is experiencing renewed interest owing to the commercial availability of thin-film lithium niobate (TFLN). This integrated photonic material platform enables tight mode confinement, which results in frequency-mixing efficiency improvements by orders of magnitude while at the same time offering additional degrees of freedom for engineering the optical properties by using approaches such as dispersion engineering. Importantly, the large refractive index contrast of TFLN enables, for the first time, the realization of lithium niobate–based photonic integrated circuits on a wafer scale. OUTLOOK The broad spectral coverage, ultralow power requirements, and flexibilities of lithium niobate photonics in EM wave generation provides a large toolset to explore new device functionalities. Furthermore, the adoption of lithium niobate–integrated photonics in foundries is a promising approach to miniaturize essential bench-top optical systems using wafer scale production. Heterogeneous integration of active materials with lithium niobate has the potential to create integrated photonic circuits with rich functionalities. Applications such as high-speed communications, scalable quantum computing, artificial intelligence and neuromorphic computing, and compact optical clocks for satellites and precision sensing are expected to particularly benefit from these advances and provide a wealth of opportunities for commercial exploration. Also, bulk crystals and weakly confining waveguides in lithium niobate are expected to keep playing a crucial role in the near future because of their advantages in high-power and loss-sensitive quantum optics applications. As such, lithium niobate photonics holds great promise for unlocking the EM spectrum and reshaping information technologies for our society in the future. Lithium niobate spectral coverage. The EM spectral range and processes for generating EM frequencies when using lithium niobate (LN) for frequency mixing. AO, acousto-optic; AOM, acousto-optic modulation; χ (2) , second-order nonlinearity; χ (3) , third-order nonlinearity; EO, electro-optic; EOM, electro-optic modulation; HHG, high-harmonic generation; IR, infrared; OFC, optical frequency comb; OPO, optical paramedic oscillator; OR, optical rectification; SCG, supercontinuum generation; SHG, second-harmonic generation; UV, ultraviolet. 
    more » « less
  5. We describe a strategy of integrating quantum mechanical (QM), hybrid quantum mechanical/molecular mechanical (QM/MM) and MM simulations to analyze the physical properties of a solid/water interface. This protocol involves using a correlated ab initio (CCSD(T)) method to first calibrate Density Functional Theory (DFT) as the QM approach, which is then used in QM/MM simulations to compute relevant free energy quantities at the solid/water interface using a mean-field approximation of Yang et al. that decouples QM and MM thermal fluctuations; gas-phase QM/MM and periodic DFT calculations are used to determine the proper QM size in the QM/MM simulations. Finally, the QM/MM free energy results are compared with those obtained from MM simulations to directly calibrate the force field model for the solid/water interface. This protocol is illustrated by examining the orientations of an alkyl amine ligand at the gold/water interface, since the ligand conformation is expected to impact the chemical properties ( e.g. , charge) of the solid surface. DFT/MM and MM simulations using the INTERFACE force field lead to consistent results, suggesting that the effective gold/ligand interactions can be adequately described by a van der Waals model, while electrostatic and induction effects are largely quenched by solvation. The observed differences among periodic DFT, QM/MM and MM simulations, nevertheless, suggest that explicitly including electronic polarization and potentially charge transfer in the MM model can be important to the quantitative accuracy. The strategy of integrating multiple computational methods to cross-validate each other for complex interfaces is applicable to many problems that involve both inorganic/metallic and organic/biomolecular components, such as functionalized nanoparticles. 
    more » « less