Ping Zhang
6 Papers
14 Citations
Ping Zhang is an academic researcher. The author has contributed to research in topics: Computer science & Similarity (geometry). The author has an hindex of 3, co-authored 6 publications. Previous affiliations of Ping Zhang include Massachusetts Institute of Technology.
Chat about Author
Papers
Multi-fidelity prediction of molecular optical peaks with deep learning
TL;DR: In this paper , a directed message passing neural network (D-MPNN) was used to represent both dye molecules and solvents for predictions of molecular absorption peaks in solution, which can be integrated with active learning, generative modeling, and experimental workflows to enable the more rapid design of molecules with targeted optical properties.
56
•Posted Content
Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential.
TL;DR: In this paper, a neural network based on diabatic states is proposed to accelerate the simulation of photoisomerization of azobenzene derivatives, which can be used for virtual screening of photoactive compounds.
Excited state non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
TL;DR: In this article , a diabatic artificial neural network (DANN) was proposed to accelerate reactive simulations for azobenzene derivatives to accelerate the detection of photowitches with desired photophysical properties.
•Posted Content
Graph theory-based structural analysis on density anomaly of silica glass
TL;DR: In this paper, the topological differences between structural arrangements from molecular dynamics trajectories using a graph-theoretical approach, such that structural differences in silica glasses that exhibit density anomaly can be captured.
5
Tunable CHA/AEI Zeolite Intergrowths with A Priori Biselective Organic Structure‐Directing Agents: Controlling Enrichment and Implications for Selective Catalytic Reduction of NOx
TL;DR: In this paper , a novel ab initio methodology based on high-throughput simulations has permitted designing unique biselective organic structuredirecting agents (OSDAs) that allow the efficient synthesis of CHA/AEI zeolite intergrowth materials with controlled phase compositions.
2