ArcGIS tool and tutorial to convert the shapefiles into network format. The latest version of the tool is available at http://csun.uic.edu/codes/GISF2E.htmlUpdate: we now have added QGIS and python tools. To download them and learn more, visit http://csun.uic.edu/codes/GISF2E.htmlPlease cite: Karduni,A., Kermanshah, A., and Derrible, S., 2016, "A protocol to convert spatial polyline data to network formats and applications to world urban road networks", Scientific Data, 3:160046, Available at http://www.nature.com/articles/sdata201646

This is a tutorial on how to use GIP data for the ESRI ArcGIS Network Analyst.

Road networks serve as a fundamental layer in various applications ranging from basemap preparation, which is needed for navigation, to humanitarian aid, disaster management, and transportation planning. As a result, accurate and updated road network maps are not just beneficial, but often critical. Traditional methods of road mapping and updating are time-consuming and often involve manual fieldwork. However, with deep learning solutions, the process has become both more efficient and accurate. In this tutorial, you are a GIS analyst working at the City of Mississauga in Ontario and you have been tasked with developing an automated road extraction to update the city road network. You will start with generating training samples to identify and marking out roads within the imagery, which then serve as examples for the deep learning model to learn from. Then, you’ll use the ArcGIS API for Python to train a deep learning model and use the developed model in ArcGIS Pro for inferencing and extracting the city road network. Following the road extraction, you will apply a post-processing steps to connect segmented roads and create a smooth road network and then compare it to a reference road network layer.