LandTalk.AI - Your Landscape Talks To You
Based on our latest research (see below) we now launched a QGIS Plugin to experiment with ChatGPT and Google Gemini on QGIS maps. Details and download available from our repository:
https://github.com/juergenlandauer/LandTalk.AI
I will present how visual language models (VLM) can revolutionize Landscape Archaeology at CAA 2025 in Athens in May:
https://2025.caaconference.org/
The data and source code & instructions are available from www.github.com/juergenlandauer/caa2025
For presentation slides click here.


If you have an exciting idea about how archaeological data and Artificial Intelligence can help you in your resarch, do not hesitate to contact me or send me your proposal.
I might be interested to assist you as part of my nonprofit work. Usually no cost involved :-)
A contact form is available at the end of this page (see below).

Our paper Archaeological Site Detection: Latest Results from a Deep Learning Based Europe Wide Hillfort Search just got published in the Journal of Computer Applications in Archaeology.
We show how large landscapes, here covering a total area of 180,000 km², can be analyzed with AI in LiDAR
Our paper on finding ancient Khmer sites
in Cambodia using Deep Learning and
satellite imgery just got published in PLOS One:
Beyond the Greater Angkor Region: Automatic large-scale mapping of Angkorian period reservoirs in satellite imagery using deep learning

I am glad to report that our article on finding human traces from Doggerland in seismic data has been published in MDPI Heritage:
Many thanks to my co-authors Andrew Iain Fraser, Vince Gaffney, and Elizabeth Zieschang!