Table 1

Recent literature review on neural networks in delay prediction

LiteratureMethodInput dataCharacteristics
Huang, Spanninger, and Corman (2022) CLF-Net (3DCNN, LSTM, FCNN)Spatio-temporal features, timetable features (time-series), infrastructure (non-time-series)It is the first time that static, temporal, and spatio-temporal data are simultaneously considered in a hybrid model
Li et al. (2022) LLCF (CNN, two LSTM, FCNN)Considers the arrival routes of predicted trains and route conflicts with forward trainsThe detailed train arrival/departure routes are considered from a microscopic view in the proposed arrival delay prediction model
Heglund et al. (2020) STGCNA sequence of node features that are the arrival delay of trains passing through linksConsider the connections between elements in the rail network
Ding et al. (2021) MTGNNThe actual delay and infrastructure data of trains at previous stationsCombines graph learning, graph convolution, and temporal convolution modules to predict train arrival delays under different causes
Zhang et al. (2021) TSTGCN (SAtt, TAtt, GCN)Recent time series, daily time series, weekly time seriesPredict the total number of delayed trains in each railway station
Xu et al. (2022) DB-STGCN (STGCN, DBN)Timetable-related variables, delay pattern variables, infrastructure-related variables, and weather-related variablesConsider train delay patterns and dynamic interactions between train events, and study the dynamic causality of train delay propagation

Source(s): Author's own work

or Create an Account

Close Modal
Close Modal