In this research, UAVs, GNSS, GIS, and machine learning are studied to enhance rural infrastructure resilience and better the assessment of the pavement condition. High-resolution UAVs can offer an effective way of gathering rich data about road-related situations in isolated places and distant highways. GNSS guarantees a high degree of accuracy in locating points, whereas GIS provides out the capability of analyzing space and mapping a network of roads. They trained machine-learned models (a Random Forest classifier) to forecast maintenance requirements on the basis of such factors as the Pavement Condition Index (PCI), traffic volume (AADT), and environmental elements, such as rainfall and rutting. The model had an almost perfect accuracy, precision and recall indicating that it is effective in determining road segments which need to be maintained. This system provides a resource allocation approach based on data-driven proactive maintenance, to enhance the decision-making process. Some improvements in the system in the future may involve adding real-time traffic data, weather prediction, and high-technology UAV systems to manage rural infrastructure to a better extent.
IRE Journals:
Malvern Munashe Dongo, Munashe Naphtali Mupa, Trymore Musariri, Frank Chingarandi "Optimizing UAV-Based Pavement and Roadway Assessment Techniques for Enhancing Rural Infrastructure Resilience in the United States" Iconic Research And Engineering Journals Volume 9 Issue 9 2026 Page 1225-1233 https://doi.org/10.64388/IREV9I9-1715203
IEEE:
Malvern Munashe Dongo, Munashe Naphtali Mupa, Trymore Musariri, Frank Chingarandi
"Optimizing UAV-Based Pavement and Roadway Assessment Techniques for Enhancing Rural Infrastructure Resilience in the United States" Iconic Research And Engineering Journals, 9(9) https://doi.org/10.64388/IREV9I9-1715203