A Framework for Quantifying Uncertainty in DFT Energy Corrections

Wang, Amanda; Kingsbury, Ryan; McDermott, Matthew J.; Horton, Matthew; Jain, Anubhav; Ong, Shyue Ping; Dwaraknath, Shyam; Persson, Kristin A.

doi:10.26434/chemrxiv.14593476

Cited by 9 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highlighted V-shaped region shows the area in which the average absolute error is greater than the energy to the known convex hull; this is the region where the model is most at risk of misclassifying structures. In most of this region, Wren’s accuracy is well below the threshold of 100 meV per atom considered to be the accuracy of semilocal DFT across diverse chemistries ( 66 ) and comparable to the threshold of ∼ 50 meV per atom characteristic of fitted correction schemes ( 67 – 69 ).…”

Section: Resultsmentioning

confidence: 95%

Rapid discovery of stable materials by coordinate-free coarse graining

et al. 2022

View full text Add to dashboard Cite

A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allowing the stability and functional properties of materials to be accurately predicted. However, most of these approaches use atomic coordinates as input and are thus bottlenecked by crystal structure identification when investigating previously unidentified materials. Our approach solves this bottleneck by coarse-graining the infinite search space of atomic coordinates into a combinatorially enumerable search space. The key idea is to use Wyckoff representations, coordinate-free sets of symmetry-related positions in a crystal, as the input to a machine learning model. Our model demonstrates exceptionally high precision in finding unknown theoretically stable materials, identifying 1569 materials that lie below the known convex hull of previously calculated materials from just 5675 ab initio calculations. Our approach opens up fundamental advances in computational materials discovery.

show abstract

Section: Resultsmentioning

confidence: 95%

Rapid discovery of stable materials by coordinate-free coarse graining

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The highlighted region shows the area in which the average absolute error is greater than the energy to the known convex hull -this is the region where the model is most at risk of miss-classifying structures. However, we see that in the majority of this region the model's accuracy is well below the 100 meV per atom threshold considered to be the accuracy of semi-local DFT across diverse chemistries [28] and comparable to the ∼ 50 meV per atom threshold characteristic of fitted correction schemes [29][30][31]. This high level of accuracy around the stability threshold leads to the model's impressive performance when identifying materials below the known convex hull.…”

Section: Selecting Stable Materials From Diverse Chemical Spacesmentioning

confidence: 84%

Rapid Discovery of Stable Materials by Coordinate-free Coarse Graining

Goodall¹,

Parackal²,

Faber³

et al. 2021

Preprint

View full text Add to dashboard Cite

A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allowing the stability and functional properties of materials to be accurately predicted. However, most of these approaches use atomic coordinates as input and are thus bottlenecked by crystal structure identification when investigating novel materials. Our approach solves this bottleneck by coarse-graining the infinite search space of atomic coordinates into a combinatorially enumerable search space. The key idea is to use Wyckoff representationscoordinate-free sets of symmetry-related positions in a crystal -as the input to a machine learning model. Our model demonstrates exceptionally high precision in discovering new stable materials, identifying 1,558 materials that lie below the known convex hull of previously calculated materials from just 5,675 ab-initio calculations. Our approach opens up fundamental advances in computational materials discovery.

show abstract

“…60 demonstrates that care has to be taken when using PBE for OER or similar reactions. While DFT correction schemes have been suggested to reduce these inaccuracies, 61 we shall still use PBE below, also for Gibbs free energies, because the method is fast and reliable enough to quantify trends in comparable situations, e.g. for screening of different materials or checking cluster vs. periodic models.…”

Section: Resultsmentioning

confidence: 99%