Flow Prediction

Predict The flow of OD matrix using Gravity Model (GM) and Neural Network (NN) 

Relative Fields: Transportation Engineering, Traffic Engineering, Machine Learning, Neural Network with Pytorch

Project Overview

In this project, we aim to compare the performance of the Gravity Model (GM) with Neural Network (NN) and Graph Neural Network (GNN) in a specific context. By analyzing and evaluating these models, we seek to gain insights into their respective strengths, limitations, and potential applications.

We utilized datasets from Siouxfall, Anahiem, and Chicago to conduct our analysis. These datasets provide valuable real-world data that enables us to assess the performance and predictive capabilities of the GM, NN, and GNN models in different urban settings. By leveraging these datasets, we aim to draw meaningful conclusions and identify potential patterns or correlations between the models and the characteristics of the cities under consideration.

Project Steps :

  • code out the GM Model. We did this in 4 different approach. 1-exponentional  2-power  3-tanner  4-guess
  • The last approach (Guess) is made by me and is a new approach.
  • Model the NN and GN
  • connect all details to get the results all together.

Results of The Project

We are still work on the conclusion.

Coming Soon…

Code Sources :

This modeling is done by Pytorch.

Here you can fine all codes and results :

Last Changes:

Github-Transportation-FlowPrediction

Stable Version:

Github-Transportation-FlowPrediction

Scroll to Top