Recently, many network-wide traffic prediction studies based on various deep-learning methods are published. The field is very active, and the relevant papers are getting many attractions and citations. After reading and reviewing many related papers, I have many doubts and cannot help asking the following six questions. 

1. Is the proposed model innovative? 

2. Is the heterogeneity of road segments considered? 

3. Is the unevenness of traffic conditions considered? 

4. Is the competitive method sufficiently tuned? 

5. Is the result significant? 

6. Is the newly proposed model reproducible?

全文链接 https://www.researchgate.net/publication/336015615_Six_Questions_on_Network-wide_Traffic_Prediction