← Back to all news
arXiv Machine Learning By Weixiang Hong, Hongting Du, Jiayue Tang, Ruifeng Tan, Yangjian Quan, Jia Li, Jiaqiang Huang

Prototype-guided transfer of sparse literature knowledge for electrolyte additive discovery

Read the original on arXiv Machine Learning →

ProtoMI is a literature‑driven framework that learns structural priors from 126 reported boron‑containing electrolyte additives and applies them to screen 179,977 unlabeled candidates. Using graph contrastive learning, it identifies seven interpretable prototypes and adapts them through semi‑supervised contrastive learning, achieving enrichment factors of 9.2–45.6 while evaluating less than 2% of the candidate space. The method led to the discovery of four commercially accessible additives, including TNDB, which improves high‑temperature LiFePO4||graphite cycling by 34.93% and forms protective interphases that suppress solvent decomposition and Fe deposition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 27

A Hierarchical Synergistic Deep Learning Framework Integrating Composition, Structure, and Ionic Transport for Solid-State Electrolyte Discovery

The paper presents a hierarchical deep‑learning framework that integrates compositional, structural, and transport models to screen solid‑state electrolytes. Four modules—L‑G‑DCNN, DenseGNN, MatterSim, and DeePMD—coordinate to evaluate thermodynamics, multi‑property performance, and kinetic transport, outperforming existing methods. Applied to over 30 million candidates, the workflow identifies 97 high‑performance materials, mainly halides, and links Li⁺ jump‑network connectivity to ionic conductivity while highlighting limits for oxide electrolytes.

By Hongwei Du, Dingyang Lv, Baole Wei, Yongheng Li, Feng Yu, Ziheng Lu, Siqi Shi, Hong Wang
benchmarks
More like this →
arXiv AI
Sep 12

A Density-Matrix Framework for Electronic-Structure Analysis of Electrolytes for Lithium Batteries

The paper introduces EMolStudio, a density‑matrix‑centered AI platform that predicts and analyzes electronic structure for electrolyte molecules in lithium batteries. It integrates molecular functionalization, explicit Li⁺ first‑shell assembly, density‑matrix prediction, and electronic‑structure parsing, enabling systematic study of 163,655 functionalized molecules and 22,500 first‑shell clusters across four lithium salts. The analysis reveals that functional groups and anion identity distinctly influence frontier orbital energies, electrostatic potential, and Li⁺‑donor contacts, with LiTDI anchoring the highest occupied orbital on the anion.

By Mingkang Liu, Huize Yu, Lei Shen
More like this →
arXiv Machine Learning
Jul 3

An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility

arXiv:2607. 02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both.

By Sampreeti Bhattacharya, Arkaprava Roy
ragfine-tuning
More like this →