Quantifying the performance of machine learning models in materials discovery-Reference-Cited by-同舟云学术

Quantifying the performance of machine learning models in materials discovery

Published:2023 Issue:2 Volume:2 Page:327-338
ISSN:2635-098X
Container-title:Digital Discovery
language:en
Short-container-title:Digital Discovery

Author:

Borg Christopher K. H.¹,Muckley Eric S.¹,Nyby Clara¹,Saal James E.¹^ORCID,Ward Logan²^ORCID,Mehta Apurva³,Meredig Bryce¹^ORCID

Affiliation:

1. Citrine Informatics, Inc., Redwood City, CA, USA

2. Argonne National Laboratory, Lemont, IL, USA

3. SLAC National Accelerator Laboratory, Menlo Park, CA, USA

Abstract

In this work, we simulate a sequential learning (SL)-guided materials discovery process and demonstrate a decoupling between traditional model error metrics and model performance in guiding materials discoveries.

Funder

U.S. Department of Energy

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2023/DD/D2DD00113F

Reference50 articles.

1. Machine Learning in Materials Discovery: Confirmed Predictions and Their Underlying Approaches

2. Combinatorial screening for new materials in unconstrained composition space with machine learning

3. High-Throughput Machine-Learning-Driven Synthesis of Full-Heusler Compounds

4. Structural absorption by barbule microstructures of super black bird of paradise feathers

5. Materials informatics for the screening of multi-principal elements and high-entropy alloys

Cited by 16 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Machine learning in materials research: Developments over the last decade and challenges for the future;Current Opinion in Solid State and Materials Science;2024-12

2. Accelerating Materials Discovery for Polymer Solar Cells: Data-Driven Insights Enabled by Natural Language Processing;Chemistry of Materials;2024-08-06

3. High-Throughput Screening of Li Solid-State Electrolytes with Bond Valence Methods and Machine Learning;Chemistry of Materials;2024-08-05

4. Step Forward Cross Validation for Bioactivity Prediction: Out of Distribution Validation in Drug Discovery;2024-07-04

5. Optimizing FDM 3D printing parameters for improved tensile strength using the Takagi–Sugeno fuzzy neural network;Materials Today Communications;2024-03