Title: Predicting carbon emission and peaking time of waterborne freight transportation in China

Authors: Tingsong Wang; Mengyao Wang; Peiyue Cheng

Addresses: School of Management, Shanghai University, Shanghai, 200444, China ' School of Management, Shanghai University, Shanghai, 200444, China ' School of Management Science and Engineering, Shandong University of Finance and Economics, Shandong, 250014, China

Abstract: This study focuses on predicting carbon emissions from China's waterborne freight transport and identifying peak times. A bottom-up model based on freight turnover is developed. After comparing three models, the long short-term memory (LSTM) network is used to forecast emissions from 2021 to 2040, and the Mann-Kendall test is applied to detect peaks. Results show inland, coastal, and oceanic transport will peak in 2030, 2032, and 2029, with overall waterborne emissions peaking around 2030 and declining significantly (P < 0.05). Validation confirms LSTM outperforms seasonal autoregressive integrated moving average (SARIMA) and Extreme Gradient Boosting (XGBoost). Furthermore, the study suggests that the promotion of clean energy sources, such as LNG and hydrogen, along with optimisation of energy infrastructure, could expedite the low-carbon transformation of waterborne transport. This paper offers methodological support for precise carbon emission measurement and peak time determination, providing practical reference value for China's achievement of its dual carbon goals.

Keywords: waterborne freight transport; carbon emissions prediction; long short-term memory; LSTM model; Mann-Kendall trend test; peak carbon emissions time; China.

DOI: 10.1504/IJSTL.2026.153238

International Journal of Shipping and Transport Logistics, 2026 Vol.22 No.3, pp.303 - 326

Received: 13 Apr 2025
Accepted: 22 Jul 2025
Published online: 29 Apr 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article