Volume 43: Energy Transitions toward Carbon Neutrality: Part VI

Evaluation of Explainable Deep Learning Models in Predicting Hydrogen Production Chiagoziem C. Ukwuoma, Dongsheng Cai, Chibueze D. Ukwuoma, Favour AB Ekong, Emmanuel S.A Gyarteng, Chidera O. Ukwuoma, Qi Huang



To meet the difficulties of the current energy environment, hydrogen has enormous potential as a clean and sustainable energy source. Utilizing hydrogen’s potential requires accurate hydrogen production prediction. Due to its capacity to identify intricate patterns in data, Machine learning alongside deep learning models has attracted considerable interest from a variety of industries, including the energy industry. These algorithms are inherently black boxes, which makes it difficult to comprehend and interpret their predictions, particularly in important sectors like hydrogen generation. First, this study conducted an extensive experiment using 4 machine learning regression models and a novel deep learning model based on Keras API for hydrogen production prediction based on the co-gasification of biomass and plastics datasets. Secondly, this study investigates the application of explainable AI models including Shapley Additive Explanation (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), and Explain Like I’m Five (ELi5) in predicting hydrogen production. We explore the significance of these models in providing insights into the underlying mechanisms and factors influencing hydrogen production processes hence improving our understanding of the relationships between input factors and hydrogen production outputs. This will allow for better-informed decision-making and process optimization in the energy industry. Our results demonstrate the interpretability and transparency of these models, highlighting their potential to raise the accuracy and dependability of forecasts of hydrogen generation. These models provide a useful resource for stakeholders to make informed decisions and enhance the use of hydrogen as a sustainable energy source by bridging the gap between predicted accuracy and interpretability.

Keywords machine learning, deep learning, explainable artificial intelligence, predicting hydrogen production, co-gasification

Copyright ©
Energy Proceedings