Abstract
Artificial Neural Networks (ANNs) are rapidly gaining popularity in transportation research in general and travel demand analysis in particular. While ANNs typically outperform conventional methods in terms of predictive performance, they suffer from limited explainability. That is, it is very difficult to assess whether or not particular predictions made by an ANN are based on intuitively reasonable relationships embedded in the model. As a result, it is difficult for analysts to gain trust in ANNs. In this paper, we show that often-used approaches using perturbation (sensitivity analysis) are ill-suited for gaining an understanding of the inner workings of ANNs. Subsequently, and this is the main contribution of this paper, we introduce to the domain of transportation an alternative method, inspired by recent progress in the field of computer vision. This method is based on a re-conceptualisation of the idea of ‘heat maps’ to explain the predictions of a trained ANN. To create a heat map, a prediction of an ANN is propagated backward in the ANN towards the input variables, using a technique called Layer-wise Relevance Propagation (LRP). The resulting heat map shows the contribution of each input value –for example the travel time of a certain mode– to a given travel mode choice prediction. By doing this, the LRP-based heat map reveals the rationale behind the prediction in a way that is understandable to human analysts. If the rationale makes sense to the analyst, the trust in the prediction, and, by extension, in the trained ANN as a whole, will increase. If the rationale does not make sense, the analyst may choose to adapt or re-train the ANN or decide not to use it at all. We show that by reconceptualising the LRP methodology towards the choice modelling and travel demand analysis contexts, it can be put to effective use in application domains well beyond the field of computer vision, for which it was originally developed.
Highlights
Artificial Neural Networks (ANNs) are emerging as an increasingly indispensable tool for many applications in the field of transportation
Without sufficient understanding of how and why the trained ANN makes a particular prediction, the use of ANNs in transportation research will mainly be confined to niche settings where prediction per formance is highly valued and model transparency is not of great importance; for justi fiable reasons, governments and transport planning agencies put a higher premium on model transparency, than on superior empirical prediction performance
Using a series of Monte Carlo experiments, this study re-conceptualises the use of heat maps, generated using a Layer-wise Rele vance Propagation method, to explain predictions of Artificial Neural Networks in the context of travel choice analysis
Summary
Artificial Neural Networks (ANNs) are emerging as an increasingly indispensable tool for many applications in the field of transportation. More spe cifically, the LRP method uses the topology of the ANN to assign a relevance score to each independent variable, highlighting the most relevant independent variables in the context of a particular prediction These resulted relevance scores are used to generate a heat map. We would like to emphasise once more that this research is motivated by the observation that ANNs are increasingly used for travel demand analysis and prediction This in our view presents a strong motivation to offer a method which reveals the rationale behind a trained ANN and as such allows for intuitive investigation of what made the model produce a prediction.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
