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 (5)

• 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
• 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

Cited by in corpus (76)

• On-the-fly machine learning force field generation: Application to melting points
• A practical guide to machine learning interatomic potentials -- Status and future
• Quantum Machine Learning for Chemistry and Physics
• 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
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• 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
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• A reactive neural network framework for water-loaded acidic zeolites
• 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
• 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
• 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
• 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
• 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
• Hydrogen diffusion in the lower mantle revealed by machine learning potentials
• Phase transitions of LaMnO${}_3$ and SrRuO${}_3$ from DFT + U based machine learning force fields simulations
• Generating candidates in global optimization algorithms using complementary energy landscapes
• 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
• Revealing the Low Temperature Phase of FAPbI${}_3$ using A Machine-Learned Potential
• Machine learning potentials for complex aqueous systems made simple
• 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
• Quantum Delocalization Enables Water Dissociation on Ru(0001)
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Locally Spontaneous Dynamic Oxygen Migration on Biphenylene: A DFT Study
• Coexistence of Superconductivity and Superionicity in Li${}_2$MgH${}_{16}$
• Efficient dataset generation for machine learning perovskite alloys
• Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
• Role of long-range dipolar interactions in the simulation of the properties of polar crystals using effective atomic potentials
• 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
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• Large-scale cooperative sulfur vacancy dynamics in two-dimensional MoS2 from machine learning interatomic potentials
• Structure and thermodynamics of defects in Na-feldspar from a neural network potential
• Semiconducting Electrides Derived From Sodalite: A First-principles Study
• Evidence of Molecular Hydrogen in the N-doped LuH3 System: a Possible Path to Superconductivity?
• 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
• Water structuring at stacked graphene interfaces unveiled by machine-learning molecular dynamics
• Temperature-transferable tight-binding model using a hybrid-orbital basis
• Towards Improved Quantum Machine Learning for Molecular Force Fields
• Surface Reconstructions in Thin-Films of Magnetic Topological Insulator MnBi${}_2$Te${}_4$
• Self-learning path integral hybrid Monte Carlo with mixed ab initio and machine learning potentials for modeling nuclear quantum effects in water
• Impact of Metal Cation on Chiral Properties of 2D Halide Perovskites
• Anharmonicity and Coulomb pseudopotential effects on superconductivity in YH${}_6$ and YH${}_9$
• Kinetically Arrested Twin-Domain State in Formamidinium Lead Iodide
• A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• A molecular rotor driven by an electric field on graphene
• Oxygen-deficiency-driven phase segregation enables enhanced hole transport in amorphous tellurium oxides
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures
• Atomistic mechanisms of phase transitions in all-temperature barocaloric material KPF${}_6$
• Smooth Overlap of Spin Orientations: Machine Learning Exchange Fields for Ab-initio Spin Dynamics
• Barrierless Water Dissociation on Rare-Earth Sesquioxide Surfaces from First Principles
• Elastic properties of amorphous LiTaCl${}_6$ solid-state electrolyte
• Thermal transport and phase transitions of zirconia by on-the-fly machine-learned interatomic potentials
• Deep machine learning potentials for multicomponent metallic melts: development, predictability and compositional transferability
• A Reparameterized Density Functional Tight-Binding Method for Engineering phase-stable CsPbX\textsubscript{3} Perovskites
• Active learning potentials for first-principles phase diagrams using replica-exchange nested sampling