Digital Discovery, 2024, Advance ArticleDOI: 10.1039/D3DD00216K, Paper Open Access   This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.Gang Seob Jung, Jong Youl Choi, Sangkeun Matthew LeeDeveloping an automated active learning framework for Neural Network Potentials, focusing on accurately simulating bond-breaking in
Digital Discovery, 2024, Advance ArticleDOI: 10.1039/D4DD00018H, Paper Open Access   This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.Robin Ruff, Patrick Reiser, Jan Stühmer, Pascal FriederichGraph neural networks (GNNs) have been applied to a large variety of applications in materials science and
Digital Discovery, 2024, Advance ArticleDOI: 10.1039/D4DD00020J, Communication Open Access   This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.Flaviu Cipcigan, Jonathan Booth, Rodrigo Neumann Barros Ferreira, Carine Ribeiro dos Santos, Mathias SteinerGFlowNets discover reticular materials with simulated CO2 working capacity outperforming all
Digital Discovery, 2024, Advance ArticleDOI: 10.1039/D3DD00200D, Paper Open Access   This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.Amer Marwan El-Samman, Incé Amina Husain, Mai Huynh, Stefano De Castro, Brooke Morton, Stijn De BaerdemackerThe embedding vectors from a Graph Neural Network trained
Digital Discovery, 2024, Advance ArticleDOI: 10.1039/D3DD00252G, Paper Open Access   This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.Paula Torren-Peraire, Alan Kai Hassen, Samuel Genheden, Jonas Verhoeven, Djork-Arné Clevert, Mike Preuss, Igor V. TetkoSynthesis planning relies on retrosynthesis models, yet this relationship
Researchers have developed a framework that uses machine learning to accelerate the search for new proton-conducting materials, that could potentially improve the efficiency of hydrogen fuel cells.
Antineutrinos generated in nuclear fission can be measured to remotely monitor the operation of nuclear reactors and verify that they are not being used to produce nuclear weapons, report scientists. Thanks to a newly developed method, it is now possible to estimate a reactor's operation
Fake plants are moving into the 21st century! Researchers developed literal 'power plants' -- tiny, leaf-shaped generators that create electricity from a blowing breeze or falling raindrops. The team tested the energy harvesters by incorporating them into artificial plants.
Researchers are tapping into idled electric vehicles to act as mobile generators and help power overworked and aging electricity grids. After analyzing energy demand on Alberta's power grid during rush hour, the research proposes an innovative way to replenish electrical grids with power generated from