Railway Freight Demand Forecasting Based on Multiple Factors: Grey Relational Analysis and Deep Autoencoder Neural Networks
نویسندگان
چکیده
The construction of high-speed rail lines in China has drastically improved the freight capacity conventional railways. However, due to recent national energy policy adjustments, volumes, consisting mostly coal, ore, and other minerals, have declined. As a result, corresponding changes supply demand goods transportation led gradual transformation railway market from seller’s buyer’s market. It is important carry out systematic analysis precise forecast for transport. traditional time series forecasting models often lack precision during drastic fluctuations demand, while deep learning-based may interpretability. This study combines grey relational (GRA) neural networks (DNN) offer more interpretable approach predicting demand. GRA used obtain explanatory variables associated with which improves intelligibility DNN prediction. high-dimension predictor variable can make training on challenging. Inspired by autoencoders (DAE), we add layer an encoder GRA-DNN model compress aggregate input. Case studies conducted Chinese 2000 2018 show that proven GRA-DAE-NN easy interpret. Comparative experiments prediction ARIMA, SVR, FC-LSTM, DNN, FNN, GRNN further validate performance model. accuracy 97.79%, higher than models. Among main variables, oil, grain production, locomotives, vehicles significant impact trend. ablation experiment verified effect selection improving predictions. method proposed this not only accurately predicts but also helps companies better understand key factors influencing changes.
منابع مشابه
Australia's long-term electricity demand forecasting using deep neural networks
Accurate prediction of long-term electricity demand has a significant role in demand side management and electricity network planning and operation. Demand over-estimation results in over-investment in network assets, driving up the electricity prices, while demand underestimation may lead to under-investment resulting in unreliable and insecure electricity. In this manuscript, we apply deep ne...
متن کاملForecasting freight demand at intermodal terminals using neural networks – an integrated framework
متن کامل
Regional Logistics Demand Forecasting: a Method Based on Improved Grey Neural Network
Regional logistics demand prediction directly affects regional economy development and logistics planning. Grey prediction, BP neural network, grey neural network and other methods have been widely used in the prediction of complex nonlinear logistics demand system. In this study, an improved grey neural network model was proposed based on these models. First, in this model, the grey influence ...
متن کاملShort-term and Medium-term Gas Demand Load Forecasting by Neural Networks
The ability of Artificial Neural Network (ANN) for estimating the natural gas demand load for the next day and month of the populated cities has shown to be a real concern. As the most applicable network, the ANN with multi-layer back propagation perceptrons is used to approximate functions. Throughout the current work, the daily effective temperature is determined, and then the weather data w...
متن کاملrodbar dam slope stability analysis using neural networks
در این تحقیق شبکه عصبی مصنوعی برای پیش بینی مقادیر ضریب اطمینان و فاکتور ایمنی بحرانی سدهای خاکی ناهمگن ضمن در نظر گرفتن تاثیر نیروی اینرسی زلزله ارائه شده است. ورودی های مدل شامل ارتفاع سد و زاویه شیب بالا دست، ضریب زلزله، ارتفاع آب، پارامترهای مقاومتی هسته و پوسته و خروجی های آن شامل ضریب اطمینان می شود. مهمترین پارامتر مورد نظر در تحلیل پایداری شیب، بدست آوردن فاکتور ایمنی است. در این تحقیق ...
ذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Sustainability
سال: 2023
ISSN: ['2071-1050']
DOI: https://doi.org/10.3390/su15129652