Researchers have developed a process using Machine Learning (ML) methods to find rock art in remote, hard-to-access areas of Australia. The study, co-led by Dr. Andrea Jalandoni, a digital archaeologist from Griffith University's Center for Social and Cultural Research, was published in the Aug. 2022 issue of the Journal of Archaeological Science. In the study, university researchers trained a ML model to detect whether painted rock art was present in an image by feeding it hundreds of images of rock art found in Kakadu National Park. The model achieved an impressive 89% success rate. Dr. Jalandoni told the Australian Associated Press, "Our machine learning model picks up whether an area photographed potentially contains previously undiscovered rock art, scientists can then go in and verify if there is rock art present and do more research."

After the success of last year's session on Machine Learning (ML) and the fruitful discussion that followed, it became apparent that there is plenty of interest in the application of these methods in archaeology. This interest might be partly ascribed to advances made in Deep Learning-in particular Convolution Neural Networks-across various disciplines. Applications using these methods now show high performance and in some cases exceed humans on challenging tasks ranging from computer vision to natural language processing. In digital archaeology we have seen and foresee applications of these techniques including automated object detection in remote sensing data, artefact image classification, use-wear analysis, text mining, paleography, predictive modelling, 3D shape analysis and recognition, and typology development. This session aims to: 1) offer a space for comparing methods, algorithms, code, APIs and workflows; 2) discuss the problems related to their application and; 3) offer insights into best practices including sources of error and validation methods.

In what's being hailed as a "major breakthrough" in Maya archaeology, researchers have identified the ruins of more than 60,000 houses, palaces, elevated highways, and other human-made features that have been hidden for centuries under the jungles of northern Guatemala. Laser scans revealed more than 60,000 previously unknown Maya structures that were part of a vast network of cities, fortifications, farms, and highways. Using a revolutionary technology known as LiDAR (short for "Light Detection And Ranging"), scholars digitally removed the tree canopy from aerial images of the now-unpopulated landscape, revealing the ruins of a sprawling pre-Columbian civilization that was far more complex and interconnected than most Maya specialists had supposed. "The LiDAR images make it clear that this entire region was a settlement system whose scale and population density had been grossly underestimated," said Thomas Garrison, an Ithaca College archaeologist and National Geographic Explorer who specializes in using digital technology for archaeological research. Garrison is part of a consortium of researchers who are participating in the project, which was spearheaded by the PACUNAM Foundation, a Guatemalan nonprofit that fosters scientific research, sustainable development, and cultural heritage preservation.