Quantum Neural Networks: A Path to Lower Emissions Through Fuel Consumption Prediction in Shipping
So Fong Chien, Julien J. M. Hermans, Austin A. Kana, Charilaos C. Zarakovitis, Stathis Zavvos, H. S. Lim
Abstract
This paper proposes Quantum Neural Networks (QNNs) as a data-driven approach for predicting fuel consumption. We utilize various layer architecture designs available in the Torchquantum framework, including both entangled and non-entangled circuit designs. In general, QNNs can achieve comparable Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) with signifi-cantly fewer trainable parameters. Neither pure QNNs nor hybrid QNN models exhibit the underfitting tendencies seen in classical neural networks (CNNs). Notably, one of the most significant findings of this work is that hybridizing or "dressing" the quantum circuit leads to substantial improvements in RMSE and MAPE for pure QNNs. These promising results suggest potential optimizations for reducing emissions in green shipping.
BibTeX
@inproceedings{icassp2025_quantumneuralnet,
title = {Quantum Neural Networks: A Path to Lower Emissions Through Fuel Consumption Prediction in Shipping},
author = {So Fong Chien and Julien J. M. Hermans and Austin A. Kana and Charilaos C. Zarakovitis and Stathis Zavvos and H. S. Lim},
booktitle = {ICASSP 2025},
year = {2025}
}