Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference

Abstract

Realistic finite temperature simulations of matter are a formidable challenge for first principles methods. Long simulation times and large length scales are required, demanding years of compute time. Here we present an on-the-fly machine learning scheme that generates force fields automatically during molecular dynamics simulations. This opens up the required time and length scales, while retaining the distinctive chemical precision of first principles methods and minimizing the need for human intervention. The method is widely applicable to multi-element complex systems. We demonstrate its predictive power on the entropy driven phase transitions of hybrid perovskites, which have never been accurately described in simulations. Using machine learned potentials, isothermal-isobaric simulations give direct insight into the underlying microscopic mechanisms. Finally, we relate the phase transition temperatures of different perovskites to the radii of the involved species, and we determine the order of the transitions in Landau theory.

References in corpus (9)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• How van der Waals interactions determine the unique properties of water
• Rotational Dynamics of Organic Cations in CH3NH3PbI3 Perovskite
• Assessing density functionals using many body theory for hybrid perovskites
• Room temperature dynamic correlation between methylammonium molecules in lead-iodine based perovskites: An ab-initio molecular dynamics perspective
• The Finite Temperature Structure of the MAPbI3 Perovskite: Comparing Density Functional Approximations and Force Fields to Experiment

Cited by in corpus (98)

• On-the-fly machine learning force field generation: Application to melting points
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• De novo exploration and self-guided learning of potential-energy surfaces
• A practical guide to machine learning interatomic potentials -- Status and future
• Quantum Machine Learning for Chemistry and Physics
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• How to validate machine-learned interatomic potentials
• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• Uncertainty estimation for molecular dynamics and sampling
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• First principles simulations of dense hydrogen
• Sparse Gaussian Process Potentials: Application to Lithium Diffusivity in Superionic Conducting Solid Electrolytes
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• Phase transitions in inorganic halide perovskites from machine learning potentials
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Anharmonic lattice dynamics in large thermodynamic ensembles with machine-learning force fields: CsPbBr${}_3$ a phonon-liquid with Cs rattlers
• Efficient Modelling of Ion Structure and Dynamics in Inorganic Metal Halide Perovskites
• A reactive neural network framework for water-loaded acidic zeolites
• $\alpha$-$\beta$ phase transition of zirconium predicted by on-the-fly machine-learned force field
• Self-learning Hybrid Monte Carlo: A First-principles Approach
• Efficiency, Accuracy, and Transferability of Machine Learning Potentials: Application to Dislocations and Cracks in Iron
• Structural Dynamics Descriptors for Metal Halide Perovskites
• Layer-by-layer phase transformation in Ti${}_3$O${}_5$ revealed by machine learning molecular dynamics simulations
• Controlled defect production in monolayer MoS2 via electron irradiation at ultralow accelerating voltages
• Progress and Challenges in Ab Initio Simulations of Quantum Nuclei in Weakly Bonded Systems
• Revealing the free energy landscape of halide perovskites: Metastability and transition characters in CsPbBr${}_3$ and MAPbI${}_3$
• Exploring librational pathways with on-the-fly machine-learning force fields: Methylammonium molecules in MAPbX${}_3$ (X=I, Br, Cl) perovskites
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Enabling robust offline active learning for machine learning potentials using simple physics-based priors
• The importance of nuclear quantum effects for NMR crystallography
• Size-Dependent Nucleation in Crystal Phase Transition from Machine Learning Metadynamics
• Same and interconvertible high-pressure ice phases
• Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations
• Long-range order imposed by short-range interactions in methylammonium lead iodide: Comparing point-dipole models to machine-learning force fields
• Temperature-Dependent Chirality in Halide Perovskites
• Machine learning density functionals from the random-phase approximation
• Tracing Ion Migration in Halide Perovskites with Machine Learned Force Fields
• Measuring transferability issues in machine-learning force fields: The example of Gold-Iron interactions with linearized potentials
• Mixing I and Br in Inorganic Perovskites: Atomistic Insights from Reactive Molecular Dynamics Simulations
• Lattice thermal conductivity of ZrSe2 based on the anharmonic phonon approach and on-the-fly machine learning force fields
• Ring Polymer Molecular Dynamics and Active Learning of Moment Tensor Potential for Gas-Phase Barrierless Reactions: Application to S + H2
• Hydrogen diffusion in the lower mantle revealed by machine learning potentials
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Phase transitions of LaMnO${}_3$ and SrRuO${}_3$ from DFT + U based machine learning force fields simulations
• Electronic Structure and Vibrational Stability of Copper-substituted Lead Apatite (LK-99)
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• Engineering Topological Phases Guided by Statistical and Machine Learning Methods
• Machine learning potentials for complex aqueous systems made simple
• Revealing the Low Temperature Phase of FAPbI${}_3$ using A Machine-Learned Potential
• Gaussian Process Regression Adaptive Density-Guided Approach: Towards Calculations of Potential Energy Surfaces for Larger Molecules
• Weighted Active Space Protocol for Multireference Machine-Learned Potentials
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• Coexistence of Superconductivity and Superionicity in Li${}_2$MgH${}_{16}$
• Locally Spontaneous Dynamic Oxygen Migration on Biphenylene: A DFT Study
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Quantum Delocalization Enables Water Dissociation on Ru(0001)
• Efficient dataset generation for machine learning perovskite alloys
• Active-learning-based efficient prediction of ab-initio atomic energy: a case study on a Fe random grain boundary model with millions of atoms
• Role of long-range dipolar interactions in the simulation of the properties of polar crystals using effective atomic potentials
• Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
• Why Superconducting Ta Qubits Have Fewer Tunneling Two-Level Systems at the Air-Oxide Interface Than Nb Qubits
• Accelerating structure search using atomistic graph-based classifiers
• Large-scale cooperative sulfur vacancy dynamics in two-dimensional MoS2 from machine learning interatomic potentials
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• Structure and thermodynamics of defects in Na-feldspar from a neural network potential
• Water structuring at stacked graphene interfaces unveiled by machine-learning molecular dynamics
• A machine learning approach to predict L-edge x-ray absorption spectra of light transition metal ion compounds
• Intermediates of Forming Transition Metal Dichalcogenide Heterostructures Revealed by Machine Learning Simulations
• Semiconducting Electrides Derived From Sodalite: A First-principles Study
• Evidence of Molecular Hydrogen in the N-doped LuH3 System: a Possible Path to Superconductivity?
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• Surface Reconstructions in Thin-Films of Magnetic Topological Insulator MnBi${}_2$Te${}_4$
• Temperature-transferable tight-binding model using a hybrid-orbital basis
• Self-learning path integral hybrid Monte Carlo with mixed ab initio and machine learning potentials for modeling nuclear quantum effects in water
• Anharmonicity and Coulomb pseudopotential effects on superconductivity in YH${}_6$ and YH${}_9$
• Oxygen-deficiency-driven phase segregation enables enhanced hole transport in amorphous tellurium oxides
• Impact of Metal Cation on Chiral Properties of 2D Halide Perovskites
• A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Kinetically Arrested Twin-Domain State in Formamidinium Lead Iodide
• A molecular rotor driven by an electric field on graphene
• Active learning potentials for first-principles phase diagrams using replica-exchange nested sampling
• Barrierless Water Dissociation on Rare-Earth Sesquioxide Surfaces from First Principles
• Elastic properties of amorphous LiTaCl${}_6$ solid-state electrolyte
• Atomistic mechanisms of phase transitions in all-temperature barocaloric material KPF${}_6$
• A Reparameterized Density Functional Tight-Binding Method for Engineering phase-stable CsPbX\textsubscript{3} Perovskites
• Deep machine learning potentials for multicomponent metallic melts: development, predictability and compositional transferability
• Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics
• Thermal transport and phase transitions of zirconia by on-the-fly machine-learned interatomic potentials