Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Enhanced Predictions for the Experimental Photophysical Data Using the Featurized Schnet-Bondstep Approach
Sheng-Hsuan Hung (National Taiwan Normal University), Zong-Rong Ye (National Taiwan Normal University), Chi‐Feng Cheng (National Taiwan Normal University), Berlin Chen (National Taiwan Normal University), Ming‐Kang Tsai (Fu Jen Catholic University, National Taiwan Normal University)
Résumé : An assessment of modifying the SchNET model for the predictions of experimental molecular photophysical properties, including absorption energy (Δ E abs ), emission energy (Δ E emi ), and photoluminescence quantum yield (PLQY), was reported. The solution environment was properly introduced outside the interaction layers of SchNET for not overly amplifying the solute–solvent interactions, particularly being supported by the changes of prediction errors between the presence and absence of the solvent effect. Two featurization schemes under the framework of the Schnet-bondstep approach, with featuring the concepts of reduced-atomic-number and reduced-atomic-neighbor, were demonstrated. These featurized models can consequently provide fine predictions for Δ E abs and Δ E emi with errors less than 0.1 eV. The corresponding predictions of PLQY were shown to be comparable to the previous graph convolution network model.