Explainable Deep Learning Model for Carbon Dioxide Estimation

• Published in: IEICE Transactions on Information and Systems Vol. E108.D; no. 9; pp. 1138 - 1141
• Main Authors: LEE, Chong-Hui, HUANG, Lin-Hao, QI, Fang-Bin, WANG, Wei-Juan, ZHANG, Xian-Ji, LI, Zhen
• Format: Journal Article
• Language: English
• Published: The Institute of Electronics, Information and Communication Engineers 01.09.2025; 一般社団法人 電子情報通信学会
• Subjects: Carbon dioxide estimation; deep learning; explainable neural network; fuel consumption
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.2024EDL8087

In recent years, environmental sustainability and the reduction of CO2 emissions have become significant research topics. To effectively reduce CO2 emissions, recent studies have used deep learning models to provide precise estimates, but these models often lack interpretability. In light of this, our study employs an explainable neural network to learn fuel consumption, which is then converted to CO2 emissions. The explainable neural network includes an explainable layer that can explain the importance of each input variable. Through this layer, the study can elucidate the impact of different speeds on fuel consumption and CO2 emissions. Validated with real fleet data, our study demonstrates an impressive mean absolute percentage error (MAPE) of only 3.3%, outperforming recent research methods.