Employing Artificial Intelligence in search for archaeological remains

Wouter Verschoof-van der Vaart has developed a way to use Deep Learning and geography software to rapidly and systematically map prehistoric barrows, Celtic fields, and medieval charcoal kilns. This innovative method has been tested on high-resolution elevation maps from the Veluwe, the Netherlands. It was recently presented in the ISPRS International Journal of Geo-Information.

Digitalisation of archaeological prospection

In order to put the effectiveness of the new technique, dubbed WODAN2.0, into context it was tested on the same data as used in the citizen science project Heritage Quest. One of the conclusions was that the performance of the technique, as of yet, does not reach or exceed human performance. However, the results do show that WODAN2.0 is capable to detect archaeological objects in this real-world situation of scarce remains in different types of terrain. WODAN2.0 is a step forward on the further digitalisation of archaeological prospection.

Read the article online.

/Public Release. View in full here.