The recent application of artificial intelligence (AI) in archaeology has been nothing short of revolutionary, particularly in the discovery of ancient geoglyphs in the Nazca Desert of Peru. This cutting-edge technology has not only accelerated the pace of discovery but also opened new avenues for understanding these enigmatic structures. The story of how AI cracked one of archaeology's biggest mysteries is a testament to the power of innovation and collaboration between different fields.
The Nazca Desert's Silent Art
On the high plateau of the Nazca Desert, a landscape seemingly devoid of life, lies a silent artwork etched into the earth. These are the Nazca Lines, a collection of geoglyphs that have fascinated archaeologists and historians for decades. The challenge has always been to map and understand these ancient creations, which are often barely visible from the ground. For most of the past century, archaeologists relied on planes, cameras, and long days on foot to slowly identify and document these figures.
AI's Role in Unveiling the Nazca Secrets
The turning point came when a team led by archaeologist Masato Sakai from Yamagata University partnered with data scientists at IBM Research. They developed an AI system designed to recognize the visual fingerprints of earthworks, a task that has traditionally been done by human specialists. The model was trained on everyday photographs and then fine-tuned on a few hundred known Nazca figures, a challenging task given the limited data.
What made this project unique was the way the team stretched the data. They chopped each confirmed figure into many overlapping tiles, turning every geoglyph into a stack of training samples. This approach allowed the model to generate a continuous geoglyph probability map with a resolution of five meters, highlighting areas where geoglyphs might exist.
The AI-Assisted Survey
The AI-assisted survey generated 47,410 candidate patches that could contain previously unknown Nazca geoglyphs. These patches were then screened by human specialists using high-resolution imagery from aircraft and drone surveys. The experts narrowed down the candidates to 1,309 high-potential sites, which were then visited by the team on foot.
During six months of walking surveys, the team confirmed 303 new figurative Nazca geoglyphs, plus 42 additional geometric designs that had never been recorded before. This brings the total number of known Nazca geoglyphs to 683. The new finds include relief-type geoglyphs, which are made by piling or removing stones to create subtle contrasts, and line-type geoglyphs, which are larger and shaped as long straight segments and wide trapezoids.
The AI's Impact on Discovery
The study, published in the Proceedings of the National Academy of Sciences, quantifies how quickly the new workflow speeds up discovery. From the 1940s to the early 2000s, surveys added figurative Nazca geoglyphs at a rate of about 1.5 per year. With the rise of high-resolution imagery after 2004, that rate climbed to about 18.7 per year. The AI-assisted survey achieved roughly a sixteen-fold acceleration beyond even that improved pace.
The Broader Implications
For Sakai and his colleagues, the key benefit is not that software replaces fieldwork but that it directs it. The model still points to 968 high-potential sites that have yet to be checked, and statistical estimates suggest that at least 248 additional AI-proposed figures are likely to be genuine. The project has also become a reference case for AI archaeology and drone-based surveys worldwide, offering a method that other teams can adapt for different kinds of faint archaeological features.
Personal Reflection
What makes this story particularly fascinating is the way AI has been able to complement human expertise. The collaboration between archaeologists and data scientists has not only accelerated the pace of discovery but also opened new avenues for understanding these ancient structures. It raises a deeper question about the role of technology in archaeology and the potential for AI to transform our understanding of the past.
Looking Ahead
As AI continues to evolve, its role in archaeology is likely to become even more significant. The Nazca project is just the beginning, and we can expect to see more innovative applications of AI in the field. From enhancing the accuracy of surveys to providing new insights into the cultural significance of ancient sites, AI is poised to revolutionize our understanding of the past. In my opinion, this is a development that will not only benefit archaeologists but also the broader public, as it will help us better appreciate and preserve our shared cultural heritage.
