Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 3, 2026International Journal of Hydrogen EnergyOpen Access

Predicting hydrogen storage in MOFs: Representation matters

View Full Paper
Ask AI
Bookmark
Share

Authors

ADAlexios P. DrososUniversity of CreteASAntonios P. SarikasUniversity of CreteGFGeorge E. FroudakisUniversity of Crete

Discussion

Loading...

Member takes

Implication

Randomized trial benchmarks three representations for hydrogen storage prediction in MOFs, highlighting the importance of representation choice.

Key Points

  • The research investigates how different structural representations influence the predictive performance of models in hydrogen storage in MOFs.
  • Benchmark three representations: geometric descriptors, energy voxels, and molecular point clouds.
  • Apply a unified protocol for comparing predictive accuracy and data efficiency.
  • Evaluate transferability of models to unseen MOF databases.
  • Energy voxels consistently outperform geometry-only approaches in predictive accuracy.
  • The performance gap widens as local interactions governing uptake become more significant.
  • Choice of representation significantly influences the learning capability of the model.

Cite This Study

Drosos et al. (2026) studied this question.

synapsesocial.com/papers/6a47545e5c29257aa2579f9ehttps://doi.org/10.1016/j.ijhydene.2026.156056
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks2024 · 118 citations
  2. 2Artificial Intelligence and High-Throughput Computational Workflows Empowering the Fast Screening of Metal–Organic Frameworks for Hydrogen Storage2024 · 25 citations
  3. 3Comparison of machine learning approaches for the identification of top-performing materials for hydrogen storage2023 · 7 citations
  4. 4Comparison of Energy-Based Machine Learning Descriptors for Gas Adsorption2023 · 15 citations
  5. 5Energy-based descriptors to rapidly predict hydrogen storage in metal–organic frameworks2018 · 321 citations