2026-10-07T08:56:31Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34033427 2026-09-30T15:20:02Z category_1 category_4 category_146 category_915 category_873 category_734 category_931 portal_63 item_type_6 month_year_09_2026

Predicting Adsorbate-Solvent Interaction Energies in Zeolite Pores Using Convolutional Neural Networks with Attention Mechanisms Jiexin Shi (20684372) Xiuting Chen (234331) Rachel B. Getman (1582147) Biophysics Biochemistry Space Science Physical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified solvation interaction energies represented chemical domain phase heterogeneous catalysis multiscale modeling workflow mean absolute error feature channels relevant feature attributions reveals determining reaction thermodynamics density functional theory averaged solvation energies confined nanoporous environments approaching dft accuracy solvent interaction energies proximal solvent structures spatial attention maps pore conditions considered model emphasizes adsorbate framework enables efficient diverse solvent configurations 3 </ sub predicting adsorbate model achieves individual configurations dft targets confined systems solvent branches zeolite pores using simulation systems within scalable pathway principles calculations physical intuition molecular dynamics interpretable prediction extensive first enhanced three critical role bonding interactions accurate prediction 08 ev 04 ev Solvent effects play a critical role in determining reaction thermodynamics and kinetics in liquid-phase heterogeneous catalysis, particularly in confined nanoporous environments such as zeolite pores. However, accurate prediction of solvation thermodynamics remains computationally prohibitive due to the need for extensive first-principles calculations on diverse solvent configurations. In this work, we present an attention-enhanced three-dimensional convolutional neural network (3D-CNN) framework to predict solvation interaction energies (Δ<i>E_int</i>) of adsorbates in Ti-faujasite (Ti-FAU) zeolite pores. Molecular dynamics (MD) snapshots of C₁–C₃ oxygenates in aqueous and water–methanol solvent environments are transformed into multichannel voxel grid representations that encode spatially resolved atomistic information. The 3D-CNN architecture incorporates separate adsorbate and solvent branches and employs convolutional block attention modules to dynamically prioritize spatial regions and feature channels relevant to adsorbate–solvent interactions. Trained on density functional theory (DFT)-derived interaction energies from a multiscale modeling workflow, the model achieves a mean absolute error of 0.08 eV for individual configurations and 0.04 eV for ensemble-averaged solvation energies, approaching DFT accuracy while substantially reducing computational cost. Cross-validation (CV) using simulation-system, solvent-composition, and pore-type splits demonstrates predictive performance on held-out systems within the represented chemical domain and across the solvent and pore conditions considered in this study. Analysis of spatial attention maps and feature attributions reveals that the model emphasizes adsorbate-proximal solvent structures and hydrogen-bonding interactions, consistent with physical intuition. This framework enables efficient and interpretable prediction of solvation interaction energies in confined systems and provides a scalable pathway for mapping structural information sampled from force-field-MD to DFT targets. 2026-09-30T00:00:00Z Text Journal contribution 10.1021/acs.jcim.6c02080.s001 https://figshare.com/articles/journal_contribution/Predicting_Adsorbate-Solvent_Interaction_Energies_in_Zeolite_Pores_Using_Convolutional_Neural_Networks_with_Attention_Mechanisms/34033427 CC BY-NC 4.0