Optimizing Green Hydrogen Production: An AI-Based Approach

Caceres Ortuzar, Cristobal Alberto (2025) Optimizing Green Hydrogen Production: An AI-Based Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

In this paper, Artificial Intelligence (AI) is used to enhance the effectiveness and sustainability of green hydrogen production with renewable energy sources. Using Python, the dataset consisting of 2,535 records obtained from Kaggle and pre-processed for this project was analyzed in a Jupyter Notebook according to the CRISP-DM methodology (Schröer et al., 2021). We tested three regressions models Random Forest, Support Vector Regression (SVR), and Gradient Boosting with the best performance obtained by a random forest tuned with Bayesian hyperparameters that resulted in the lowest MAE and RMSE and highest R² score. SHAP analysis provided an explanation for the selected model of hydrogen production, and it identified the top indicative parameters (Ahmed at el., 2024; Wei et al., 2025). The research indicates that AI-based modeling provides efficient methods to design green hydrogen systems which enhance operational efficiency and reduce energy waste and costs in the domain and thus supports SDG 7 Affordable and Clean Energy and SDG 13 Climate Action (Seeger et al., 2025; Jamali et al., 2025), offering a transferable model with environmental values exceeding economic benefits for other renewable hydrogen technologies at large scales.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HC Economic History and Conditions > Natural resources > Power resources > Energy consumption H Social Sciences > HC Economic History and Conditions > Natural resources > Power resources
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	24 Jun 2026 11:08
Last Modified:	24 Jun 2026 11:08
URI:	https://norma.ncirl.ie/id/eprint/9397

Actions (login required)

View Item