Key points are not available for this paper at this time.
The aim of this study was to provide archaeological site identification, monitoring, and conservation through advanced imaging techniques. The research problem addressed the challenge of using modern technology to effectively identify and preserve archaeological sites. We employed various methods such as lidar, satellite imagery, UAV photogrammetry, GPR, and machine learning algorithms. We collected LiDAR data using an airborne scanner to capture fine-grained geological information. Satellite images from Digital Globe and Airbus provided detailed information, while UAVs equipped with photogrammetry sensors produced detailed 3D images. The subsurface features were mapped using downward radar surveys. Machine learning algorithms, including support vector machines and neural networks, were used to process the data for feature recognition and classification. We evaluated algorithm performance using statistical tools like accuracy assessments and error rates. The results demonstrated significant advancements in site detection accuracy. Algorithm D achieved the highest accuracy of 93.567%, with low false positive (2.456%) and false negative (3.978%) rates, highlighting its effectiveness in identifying archaeological features. Integration of multi-sensor data improved spatial resolution and feature recognition across diverse landscapes. The research contributes to the field by demonstrating the potential of advanced imaging in archaeology, facilitating more accurate and effective site identification and conservation.
Collins O. Molua (Sat,) studied this question.