Scholarlink

A hybrid forecasting framework combining a Genetic Algorithm-optimized Backpropagation neural network (GA-BP) with an ARIMA time series model is proposed to predict ship-based carbon emissions in inland waterways. The GA-BP model forecasts key influencing factors such as average sailing speed, berthing time, maneuvering time, and cruising time, while the ARIMA model predicts future vessel traffic volumes. AIS data collected from the Suzhou section of the Beijing–Hangzhou Grand Canal between 2018 and 2023 is used for training and validation. The integrated approach effectively captures both nonlinear interactions and temporal dynamics in ship operations. Forecasts for the period 2024–2035 show a steady rise in carbon emissions, with an average annual growth rate of 13.62%, emphasizing the influence of demand growth, regulatory policies, and technological development. These results provide a valuable reference for policymakers and practitioners aiming to reduce emissions and promote sustainable development in inland waterway transport.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Ship Carbon Emissions in Canal Waterways Based on GA-BP + ARIMA

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Xinnan Zhao,
  • Ding Li,
  • Cheng Cheng,
  • Zhengchun Sun,
  • Sudong Xu

摘要

A hybrid forecasting framework combining a Genetic Algorithm-optimized Backpropagation neural network (GA-BP) with an ARIMA time series model is proposed to predict ship-based carbon emissions in inland waterways. The GA-BP model forecasts key influencing factors such as average sailing speed, berthing time, maneuvering time, and cruising time, while the ARIMA model predicts future vessel traffic volumes. AIS data collected from the Suzhou section of the Beijing–Hangzhou Grand Canal between 2018 and 2023 is used for training and validation. The integrated approach effectively captures both nonlinear interactions and temporal dynamics in ship operations. Forecasts for the period 2024–2035 show a steady rise in carbon emissions, with an average annual growth rate of 13.62%, emphasizing the influence of demand growth, regulatory policies, and technological development. These results provide a valuable reference for policymakers and practitioners aiming to reduce emissions and promote sustainable development in inland waterway transport.