Road network data is critical information that used by government for development planning and by the services provider such as transportation and logistic company to deliver their services and prices calculations. Use of sentinel 2A satellite imagery data will solve the road map update cost issue since this data is free to use. The only problem on sentinel 2A is only about the medial spatial resolution that only able to detect 10 meters object. Using GPS data for the ground truth data will help to create the road masking data that can be used for the training. The result of the combination between these two data on Convolutional Neural Network are satisfied enough with accuracies score is 99% and soft dice error only 0.5%.

Keywords : Convolutional Neural Network (CNN), Sentinel, GPS, U-Net, Deep Learning.