Matter Modeling Stack Exchange is a question and answer site for materials modelers and data scientists. It only takes a minute to sign up.
Sign up to join this community
I heard that machine learning techniques on materials use a large quantity of data to make predictions of a variety of features; for instance, a crystal structure. Data collected from empirical or high-level calculations could be used to correct DFT calculations for materials at, presumably, lower computational cost.
Basically, I would like to know what are the current advances made in machine learning methods applied to molecular systems or the design of materials.
Here is state of the art research:
Smith J.S. et al, Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning, July 2019 Nat. Commun. 2019, 10 (1), No. 2903, PMID: 31263102
Computational modeling of chemical and biological systems at atomic resolution is a crucial tool in the chemist's toolset. The use of computer simulations requires a balance between cost and accuracy: quantum-mechanical methods provide high accuracy but are computationally expensive and scale poorly to large systems, while classical force fields are cheap and scalable, but lack transferability to new systems. Machine learning can be used to achieve the best of both approaches. Here we train a general-purpose neural network potential that approaches CCSD(T)/CBS accuracy on benchmarks for reaction thermochemistry, isomerization, and drug-like molecular torsions. This is achieved by training a network to DFT data then using transfer learning techniques to retrain on a dataset of gold standard QM calculations (CCSD(T)/CBS) that optimally spans chemical space. The resulting potential is broadly applicable to materials science, biology, and chemistry, and billions of times faster than CCSD(T)/CBS calculations.
Here's a nice review paper:
Dereinger, V.L. et. al., Machine Learning Interatomic Potentials as Emerging Tools for Materials Science, Nov 2019 Adv. Mater. 2019, 31 (46), 1902765, PMID: 31486179
Atomic-scale modeling and understanding of materials have made remarkable progress, but they are still fundamentally limited by the large computational cost of explicit electronic-structure methods such as density-functional theory. This Progress Report shows how machine learning (ML) is currently enabling a new degree of realism in materials modeling: by "learning" electronic-structure data, ML-based interatomic potentials give access to atomistic simulations that reach similar accuracy levels but are orders of magnitude faster. A brief introduction to the new tools is given, and then, applications to some select problems in materials science are highlighted: phase-change materials for memory devices; nanoparticle catalysts; and carbon-based electrodes for chemical sensing, supercapacitors, and batteries. It is hoped that the present work will inspire the development and wider use of ML-based interatomic potentials in diverse areas of materials research.
And here's a nice overview:
Mater & Coote, Deep Learning in Chemistry, June, 2019 J. Chem. Inf. Model. 2019, 59 (6), 2545–2559
Machine learning enables computers to address problems by learning from data. Deep learning is a type of machine learning that uses a hierarchical recombination of features to extract pertinent information and then learn the patterns represented in the data. Over the last eight years, its abilities have increasingly been applied to a wide variety of chemical challenges, from improving computational chemistry to drug and materials design and even synthesis planning. This review aims to explain the concepts of deep learning to chemists from any background and follows this with an overview of the diverse applications demonstrated in the literature. We hope that this will empower the broader chemical community to engage with this burgeoning field and foster the growing movement of deep learning accelerated chemistry.
Machine learning (ML) is rapidly gaining its popularity in the field of materials science due to its exceptional ability to learn from data to guide experimentalists, thus reducing traditional trial and error loops coupled with human intuition; as well as to replace time consuming ab initio calculations. Of course, the foundation of ML is data (preferably large and of good quality). Currently, there are well organised and maintained experimental (ICSD, CSD, HTEM, etc.) and theoretical (MP, AFLOW, OQMD, etc.) databases that power ML models, but it is not uncommon that researchers collect their own databases by High-throughput Density Functional Theory calculations, High-throughput Experiments or screening the literature.
I have highlighted several cases below where ML is applied in materials research. However, this is not an exhaustive list, meaning there is many more applications, and growing.
I strongly recommend NPJ Computational Materials, which is a well received, specialised journal in this field. Following are two good review papers I came across.
You would also want to check out the tools below for high-throughput DFT calculations and analyses that are usually coupled with ML studies in computational materials science.
Finally, the true potential of Artificial Intelligence (AI) is yet to be explored in the field of materials science; and by the look of it, there is lot more opportunities. Some of you might have heard of Generative Adversarial Networks (GANs) that were recently used to generate realistic images of people that do not exist in the world! Check out StyleGAN by NVIDIA. Who knows if these GANs or other generative AI models will be used to generate new synthesizable compounds!
The use of a Markovian text generator can generate in silico combinatorial libraries in the form of SMILES strings. Invalid SMILES strings thereby generated can be culled with a simple Mathematica function. If your interested in ML in chemistry I would recommend becoming fluent in Mathematica and also read the following 80-page document: Machine Learning Methods in Chemistry
Good luck to you!
