The development of fast ionic conductors to improve the performance of electrochemical devices relies on expensive high-throughput(HT)density functional theory(DFT)calculations of transport properties.Machine learning...The development of fast ionic conductors to improve the performance of electrochemical devices relies on expensive high-throughput(HT)density functional theory(DFT)calculations of transport properties.Machine learning(ML)can accelerate HT workflows but requires high-quality data to ensure accurate predictions from trained models.In this study,we introduce the LiTraj dataset,which comprises 13,000 percolation and 122,000 migration barriers,and 1700 migration trajectories,calculated for Li-ion in diverse crystal structures using empirical force fields and DFT,respectively.With LiTraj,we demonstrate that classicalMLmodels and graph neural networks(GNNs)for structureto-property prediction of percolation and migration barriers can distinguish between“fast”and“poor”ionic conductors.Furthermore,we evaluate the capability of GNN-based universal ML interatomic potentials(uMLIPs)to identify optimal Li-ion migration trajectories.Fine-tuned uMLIPs achieve near-DFT accuracy in predicting migration barriers,significantly accelerating HT screenings of new ionic conductors.展开更多
Numerous observations and simulations have revealed that climate warming is not uniform across the Earth,especially during the boreal winter[1].One striking phenomenon is Arctic amplification(AA),which shows the Arcti...Numerous observations and simulations have revealed that climate warming is not uniform across the Earth,especially during the boreal winter[1].One striking phenomenon is Arctic amplification(AA),which shows the Arctic is warming much faster than the global mean[2,3].This is evident in the reanalysis dataset,which indicates that,as shown in Fig.1a,the trend of winter surface air temperature at 2 m(SAT)averaged around the Arctic(65°-90°N)is 0.72 K 10a^(-1)。展开更多
基金the financial support of Russian Science Foundation project No.24-73-10204.
文摘The development of fast ionic conductors to improve the performance of electrochemical devices relies on expensive high-throughput(HT)density functional theory(DFT)calculations of transport properties.Machine learning(ML)can accelerate HT workflows but requires high-quality data to ensure accurate predictions from trained models.In this study,we introduce the LiTraj dataset,which comprises 13,000 percolation and 122,000 migration barriers,and 1700 migration trajectories,calculated for Li-ion in diverse crystal structures using empirical force fields and DFT,respectively.With LiTraj,we demonstrate that classicalMLmodels and graph neural networks(GNNs)for structureto-property prediction of percolation and migration barriers can distinguish between“fast”and“poor”ionic conductors.Furthermore,we evaluate the capability of GNN-based universal ML interatomic potentials(uMLIPs)to identify optimal Li-ion migration trajectories.Fine-tuned uMLIPs achieve near-DFT accuracy in predicting migration barriers,significantly accelerating HT screenings of new ionic conductors.
基金supported by the National Natural Science Foundation of China(42288101 and 42105053).
文摘Numerous observations and simulations have revealed that climate warming is not uniform across the Earth,especially during the boreal winter[1].One striking phenomenon is Arctic amplification(AA),which shows the Arctic is warming much faster than the global mean[2,3].This is evident in the reanalysis dataset,which indicates that,as shown in Fig.1a,the trend of winter surface air temperature at 2 m(SAT)averaged around the Arctic(65°-90°N)is 0.72 K 10a^(-1)。
