ru
ru
Source
AI4X
DATE OF PUBLICATION
07/08/2025
Authors
Artem Dembitskiy Roman Eremin Innokentiy Humonen Semen Budennyy Stanislav Fedotov Dmitry Aksyonov
Share

Datasets for Benchmarking Machine Learning Models for Accelerated Search of Fast Ionic Conductors

GNN, uMLIP, Li-ion, benchmark, dataset

Abstract

Fast ionic conductors are essential for advancing electrochemical devices, such as batteries, gas sensors, and ceramic membranes [1]. Traditional searches for these materials rely on costly highthroughput (HT) density functional theory (DFT) calculations across diverse chemical and structural spaces. To accelerate technological advancement in this area, HT schemes must be optimized by replacing DFTwith accurate and fast surrogate models for rapid materials screening. Here, we benchmark existing machine learning (ML) models for HT search of Li-ion conductors.




DOWNLOAD pdf

Similar publications

AI4X
Data-driven assessment of thermodynamic stability and search for competing phases: Application to the 2D Material Defect dataset
Roman Eremin, Aliaksei Krautsou, Innokentiy Humonen, Artem Dembitskiy, Semen Budennyy
SOURCE
npj Computational Materials
Discovery of Chemically Modified Higher Tungsten Boride by Means of Hybrid GNN/DFT Approach
Nikita Matsokin, Roman Eremin, Anastasia Kuznetsova, Innokentiy Humonen, Aliaksei Krautsou, Vladimir Lazarev, Yuliya Vassilyeva, Alexander Pak, Semen Budennyy, Alexander Kvashnin, Andrei Osiptsov
SOURCE
npj Computational Materials
Benchmarking Machine Learning Models for Predicting Lithium Ion Migration
Artem Dembitskiy, Innokentiy Humonen, Roman Eremin, Dmitry Aksyonov, Stanislav Fedotov, Semen Budennyy
SOURCE
EPJ Data Science
Assessing the complexity of a path search optimization method based on clustering for a transport graph
Dmitrii Fedorov, Georgii Kontsevik, Roman Bashirov, Sergey Mityagin, Liubov Tupikina, Nikita Zakharenko, Semen Budennyy
SOURCE
Биохимическая физика
Влияние симметрии кристаллических структур в обучающей выборке на оценку энергии графовыми нейронными сетями на примере разупорядоченного CsPbI3
Aliaksei Krautsou, Innokentiy Humonen, Vladimir Lazarev, Roman Eremin, Semen Budennyy
SOURCE
Scientific Reports
Doping Position Estimation for FeRh-based alloys
Egor Rumiantsev, Kuzma Khrabrov, Artem Tsypin, Nikita Peresypkin, Radel Gimaev, Vladimir Zverev, Roman Eremin, Artur Kadurin
SOURCE
Doklady Mathematics
Eco4cast: Bridging predictive scheduling and cloud computing for reduction of carbon emissions for ML models training
Mikhail Tiutiulnikov, Vladimir Lazarev, Alexey Korovin, Nikita Zakharenko, I. Doroshchenko, Semen Budennyy
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again