TY - JOUR
T1 - Travel Time Prediction and Explanation with Spatio-Temporal Features: A Comparative Study
AU - Ahmed, Irfan
AU - Weerasingha Dewage, Indika P.K.
AU - Reshadat, Vahideh
AU - Kayes, A.S.M.
AU - van den Heuvel, Willem-Jan A.M.
AU - Tamburri, Damien Andrew
PY - 2022/1/1
Y1 - 2022/1/1
N2 - Travel time information is used as input or auxiliary data for tasks such as dynamic navigation, infrastructure planning, congestion control, and accident detection. Various data-driven Travel Time Prediction (TTP) methods have been proposed in recent years. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm. The existing studies that empirically compare different TTP models only use a few models with specific features. Moreover, there is a lack of research on explaining TTPs made by black-box models. Such explanations can help to tune and apply TTP methods successfully. To fill these gaps in the current TTP literature, using three data sets, we compare three types of TTP methods (ensemble tree-based learning, deep neural networks, and hybrid models) and ten different prediction algorithms overall. Furthermore, we apply XAI (Explainable Artificial Intelligence) methods (SHAP and LIME) to understand and interpret models’ predictions. The prediction accuracy and reliability for all models are evaluated and compared. We observed that the ensemble learning methods, i.e., XGBoost and LightGBM, are the best performing models over the three data sets, and XAI methods can adequately explain how various spatial and temporal features influence travel time.
AB - Travel time information is used as input or auxiliary data for tasks such as dynamic navigation, infrastructure planning, congestion control, and accident detection. Various data-driven Travel Time Prediction (TTP) methods have been proposed in recent years. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm. The existing studies that empirically compare different TTP models only use a few models with specific features. Moreover, there is a lack of research on explaining TTPs made by black-box models. Such explanations can help to tune and apply TTP methods successfully. To fill these gaps in the current TTP literature, using three data sets, we compare three types of TTP methods (ensemble tree-based learning, deep neural networks, and hybrid models) and ten different prediction algorithms overall. Furthermore, we apply XAI (Explainable Artificial Intelligence) methods (SHAP and LIME) to understand and interpret models’ predictions. The prediction accuracy and reliability for all models are evaluated and compared. We observed that the ensemble learning methods, i.e., XGBoost and LightGBM, are the best performing models over the three data sets, and XAI methods can adequately explain how various spatial and temporal features influence travel time.
KW - Explainable AI
KW - Hybrid models
KW - LSTM
KW - LightGBM
KW - SHAP and LIME
KW - Spatio-temporal
KW - Travel time prediction
KW - XAI
KW - XGBoost
UR - http://www.scopus.com/inward/record.url?scp=85121822454&partnerID=8YFLogxK
U2 - 10.3390/electronics11010106
DO - 10.3390/electronics11010106
M3 - Article
SN - 2079-9292
VL - 11
JO - Electronics
JF - Electronics
IS - 1
M1 - 106
ER -