mlsanityData to 14 Oct 2026

The Open DAC 2025 Dataset for Sorbent Discovery in Direct Air Capture

arXiv 2508.03162 ↗First posted 5 Aug 2025cond-mat.mtrl-sci cs.LG physics.chem-phcited by 7

Not on the map. Why?

Abstract (arXiv)

Identifying useful sorbent materials for direct air capture (DAC) from humid air remains a challenge. We present the Open DAC 2025 (ODAC25) dataset, a significant expansion and improvement upon ODAC23 (Sriram et al., ACS Central Science, 10 (2024) 923), comprising nearly 60 million DFT single-point calculations for CO2, H2O, N2, and O2 adsorption in 15,000 MOFs. ODAC25 introduces chemical and configurational diversity through functionalized MOFs, high-energy GCMC-derived placements, and synthetically generated frameworks. ODAC25 also significantly improves upon the accuracy of DFT calculations and the treatment of flexible MOFs in ODAC23. Along with the dataset, we release new state-of-the-art machine-learned interatomic potentials trained on ODAC25 and evaluate them on adsorption energy and Henry's law coefficient predictions.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 13 of its 106 references that are in the map. First posted on arXiv 5 Aug 2025.

Builds on

13 of 106 references.

References · 13

  1. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  2. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  3. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  4. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  5. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 204
  6. 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNscited by 117
  7. 2025UMA: A Family of Universal Models for Atomscited by 105
  8. 2022The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalystscited by 95
  9. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 84
  10. 2022GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasetscited by 61
  11. 2022Towards Training Billion Parameter Graph Neural Networks for Atomic Simulationscited by 25
  12. 2015AiiDA: Automated Interactive Infrastructure and Database for Computational Sciencecited by 20
1 more
  1. 2023The Open DAC 2023 Dataset and Challenges for Sorbent Discovery in Direct Air Capturecited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026SimMOF: AI agent for Automated MOF Simulationscited by 5
  2. 2025Generalization of Long-Range Machine Learning Potentials in Complex Chemical Spacescited by 2
  3. 2026Distribution-Free Robust Predict-Then-Optimize in Function Spacescited by 0
  4. 2026Practical Deep Heteroskedastic Regressioncited by 0
  5. 2026Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentialscited by 0
  6. 2026Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruningcited by 0
  7. 2026Reweighting free energy profiles between universal machine learning interatomic potentials for fast consensus buildingcited by 0