Integrating Automated Annotation of Magnetic Prospection Data into GIS Workflows in Archaeology (demo paper).

Archaeological excavations play a major role in gaining knowledge about prehistoric landscapes and ways of living. However, archaeological excavations are destructive acts and very resource intensive, so they cannot be performed in every area of interest. Therefore prospection methods have been developed, where feedbacks of e.g. lidar, radar or magnetic sensors are utilized to get an overview of the distribution, extent and complexity of underground structures in larger areas. After automated pre-processing of the sensor data arrays (and images) of these, grid data is provided as an input for exploration, analysis and annotation using geographic information system tools like QGIS. Annotating the images has been a fully manual task, performed by domain scientists. In this work we demonstrate a tool that supports domain scientists through automated annotation prediction. The implementation is integrated in the prevalent scientific workflow using available input and required output formats. The implementation is based on a pre-trained Rotated Retina Net. The manually annotated data of underground house remains from one of three archaeological sites is then used to pre-process and augment a feasible amount of training data for this specific task. One challenge was that global normalization of pixel values in the images did not yield useful results, because of modern infrastructure (such as utility pipes) distorting the magnetic feedback. A separated portion of the annotated data has been used for a quantitative evaluation of model performance. The system has also been applied to two additional, formerly unseen and non-annotated datasets where predicted annotations were found to be valuable for domain scientists. The system's output data can be used in GIS tools to edit annotations by experts, explore the sites, identify promising excavation sites and perform e.g. cluster analysis on house sizes and other features.