The results of the investigations by citizens are used in an innovative research project that investigates the potential of machine learning and automated detection in archaeology.
Within the scope of the Leiden University Data Science Reseach Programme and the Faculty of Archaeology, Wouter Verschoof-van der Vaart is conducting research into the use of Deep learning and Convolutional Neural Networks (CNNs), in order to develop a generic, flexible and robust automated detection method for archaeological objects in remotely sensed data.
The results of the Heritage Quest project will be used to enlarge the number of archaeological remains that can act as examples from which the computer can learn how to independently identify archaeological features like burial mounds. At the same time the archaeological features newly discovered by volunteers will be used to verify the output of the computer.
Read more: Deep learning in archaeology