Change Detection in Road Networks During Conflicts: A Deep Learning Framework with Aerial Photography
Open Access
- 28 September 2025
- journal article
- Published by Northern Technical University in NTU Journal of Engineering and Technology
- Vol. 4 (3)
Abstract
Monitoring transformations in road infrastructure is critical for disaster response and recovery in conflict regions. However, manual analysis of road damage is time-consuming and limited in scale, while the speed of changes requires near real-time monitoring. This paper presents a deep learning framework using Hybrid Spectral Networks (HybridSN) for change detection in road networks during conflicts, applied to the city of Old Mosul, Iraq. The HybridSN model achieved high accuracy in road detection, with recall of 0.990 in 2014 and 0.982 in 2022. Change detection analysis revealed a substantial reduction of 13,249.83 m in total road length from 20,186.93 m in 2014 to 6,937.10 m in 2022, indicating widespread damage. The quantitative results demonstrate the capabilities of the proposed approach in assessing road network changes through conflict.Keywords
This publication has 21 references indexed in Scilit:
- Recognition and extraction of high-resolution satellite remote sensing image buildings based on deep learningNeural Computing and Applications, 2021
- Speckle filtering impact on land use/land cover classification area using the combination of Sentinel-1A and Sentinel-2B (a case study of Kirkuk city, Iraq)Arabian Journal of Geosciences, 2021
- Multiscale Residual Convolution Neural Network and Sector Descriptor-Based Road Detection MethodIEEE Access, 2019
- UNESCO’s project to ‘Revive the Spirit of Mosul’: Iraqi and Syrian opinion on heritage reconstruction after the Islamic StateInternational Journal of Heritage Studies, 2019
- Multi-scale object detection in remote sensing imagery with convolutional neural networksISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imageryRemote Sensing of Environment, 2018
- Building-A-Nets: Robust Building Extraction From High-Resolution Remote Sensing Images With Adversarial NetworksIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018
- A new difference image creation method based on deep neural networks for change detection in remote-sensing imagesInternational Journal of Remote Sensing, 2017
- Road detection using Deep Neural Network in high spatial resolution images2017
- Classification of Quickbird imagery over urban area using convolutional neural network2017