Prediction of H2–CNT Interaction Energies on a Chiral (2,1) Carbon Nanotube Using Multilayer Perceptrons

Accurate estimation of molecule–nanotube interaction energies is critical for the computational screening of carbon-based materials for hydrogen storage; however, density functional theory (DFT) calculations remain computationally expensive for extensive configurational sampling. In this work, we develop a multilayer perceptron (MLP) surrogate model to predict H2–CNT interaction energies, represented by Eads, for H2 interactions with a chiral (2,1) carbon nanotube. A curated dataset comprising 696 configurations was generated using DMol3 (BIOVIA Materials Studio), varying intermolecular distance, molecular orientation, and interaction site across three regions: internal cavity, edges, and external surface. The proposed MLP architecture (64–32–1) incorporates GELU activation functions, L2 regularization, and dropout to improve generalization. The model achieves coefficients of determination in the range R2 = 0.90–0.96 across all interaction regions, with particularly strong performance at the nanotube edges (R2 = 0.9358, MSE = 0.046 eV2), as well as on the external surface (R2 = 0.9625, MSE = 0.574 eV2) and within the internal cavity (R2 = 0.9051, MSE = 1.506 eV2). The original Eads distribution had a mean of 4.0955 eV and a sample standard deviation of 4.3189 eV. The elevated energy values observed in the internal cavity (up to 12 eV) are consistent with steric repulsion induced by geometric confinement rather than predictive artifacts. The trained MLP showed close agreement with DFT-derived trends, enabling exploration of interaction-energy landscapes spanning both attractive and repulsive regimes. These results indicate that MLP-based models trained on diverse configurational datasets provide a computationally efficient alternative for screening carbon nanostructures in hydrogen storage applications, without substantially compromising accuracy relative to first-principles methods.