Publications

📜 Gas adsorption meets deep learning: voxelizing the potential energy surface of metal-organic frameworks

Developing RetNet, a 3D convolutional neural network that takes as input a 3D energy image and predicts one or more gas adsorption properties.

RetNet Architecture

📜 Comparison of machine learning approaches for the identification of top-performing materials for hydrogen storage

Comparing ML approaches regarding their efficiency for identifying high-performing MOFs regarding hydrogen storage.

Self-consisent approach

📜 Comparison of Energy-Based Machine Learning Descriptors for Gas Adsorption

Comparing enery-based descriptors regarding their impact on the performance of ML models for predicting uptake of various gases in MOFs.

Feature importance


© Copyright 2024, Antonios P. Sarikas. All rights reserved.

Powered by Hydejack v9.1.6