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

TL;DR

The paper introduces ODAC25, a comprehensive dataset of nearly 60 million DFT calculations on MOFs for sorbent discovery in direct air capture, along with machine learning potentials for improved predictions.

Contribution

It presents the ODAC25 dataset with expanded chemical diversity and improved accuracy, and introduces new machine learning potentials trained on this dataset.

Findings

ODAC25 contains nearly 60 million calculations.

New machine learning potentials outperform previous models.

Enhanced dataset improves sorbent material discovery.

Abstract

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 CO$_2$, H$_2$O, N$_2$, and O$_2$ 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.