AI-based prediction of train-induced environmental vibration with limited measurements
Peer-Reviewed Publication
Updates every hour. Last Updated: 5-May-2026 18:16 ET (5-May-2026 22:16 GMT/UTC)
This study presents a transfer learning–based method for predicting train-induced environmental vibration. The method applies data fusion to combine physics-based numerical simulations and limited measurement data within a neural network. It reduces the heavy reliance of conventional machine learning–based models on scarce and costly field measurements while achieving improved prediction accuracy.
Topological phases are at the heart of many advances in photonics and materials science. In a recent eLight paper, researchers introduced the concept of multi-topological phases, a previously unknown class of topological phases that goes beyond conventional topological theory. Such multi-topological phases can host multiple sets of boundary states, associated with multiple topological invariants, arising from constrained inter-cell coupling in lattice systems. This discovery offers a novel design strategy for future topological materials.
A reserach team led by Guangfan Zheng and Qian Zhang at Northeast Normal University reported a visible light-mediated photoredox catalytic radical-polar cross-coupling strategy to achieve bifunctionalization of ipso- and para-positions in substituted aromatics. By utilizing the rapid coupling between sulfur dioxide and the dearomatized radical-type Meisenheimer intermediate, the Smiles rearrangement process was successfully delayed. Following radical ipso-cyclization, the inert C–N bond and the para-C–H bond were activated stepwise. This in-situ and para-bifunctionalization mode is complementary to the Catellani reaction, providing a novel strategy for precise multi-site modification of substituted aromatics. The article was published as an open access Research Article in CCS Chemistry, the flagship journal of the Chinese Chemical Society.
MIT chemists showed they can use nuclear magnetic resonance (NMR) to decipher the structure of the fuzzy coat that surrounds Tau proteins. The findings may aid efforts to develop drugs that interfere with Tau buildup in the brain.