18 September 2025 The Future is the Product of the Past

Scientists discover 4 new Nazca Geoglyphs using AI deep learning

Scientists from Japan used AI deep learning to discover new geoglyphs in the Arid Peruvian coastal plain, in the northern part of Peru’s Nazca Pampa.

The research has been ongoing since 2004 by a team from Yamagata University, led by Professor Makato Sakai. Yamagata University has been conducting geoglyph distribution surveys using satellite imagery, aerial photography, airborne scanning LiDAR, and drone photography to investigate the vast area of the Nazca Pampa covering more than 390 km2.

The Nazca Lines are thought to have been made over centuries, starting around 100 BC by the Nazca people of modern-day Peru. They were first studied in detail in the 1940s, and by the time they were designated a UNESCO World Heritage Site in 1994, around 30 were identified. They’re remarkably well-preserved considering their age, helped by the desert’s dry climate and winds that sweep away the sand but are being obscured by floods and human activity.

Archaeologists discovered 142 new designs in the desert over the course of ten years by manually identifying them using aerial photography and on-site surveying. Then, in collaboration with IBM Japan researchers, they used machine learning to search the data for designs that had been missed in previous studies.

Geoglyphs can be categorized into three main types: figurative, geometric, and lineal. (A) “Line-type figurative geoglyphs” were made by removing black stones in a linear pattern exposing the white sand underneath. (B to E) “Relief-type figurative geoglyphs” are often located on slopes and comprise a combination of black stone and white sand surfaces.
Geoglyphs can be categorized into three main types: figurative, geometric, and lineal. (A) “Line-type figurative geoglyphs” were made by removing black stones in a linear pattern exposing the white sand underneath. (B to E) “Relief-type figurative geoglyphs” are often located on slopes and comprise a combination of black stone and white sand surfaces.

In order to create a thorough survey of the area in 2016, the researchers used aerial photography with a ground resolution of 0.1 m per pixel. The team has identified numerous geoglyphs over time, but because the process takes a long time, they have turned to AI deep learning to analyze the images much more quickly.

A study published in the Journal of Archaeological Science revealed the discovery of four new Nazca geoglyphs using this new method by developing a labeling approach for training data that identifies a similar partial pattern between the known and new geoglyphs.

The four new geoglyphs depict a humanoid figure, a pair of legs, a fish, and a bird. The humanoid geoglyph is shown holding a club in his/her right hand and measures 5 metres in length. The fish geoglyph, shown with a wide-open mouth measures 19 metres, while the bird geoglyph measures 17 metres and the pair of legs 78 metres.

Four new Nasca geoglyphs identified by Deep Learning. (A) A humanoid, relief-type. (B) A pair of legs, line-type. (C) A fish, relief-type. (D) A bird, line-type. (B to D) are presented to the public for the first time in this paper.
Four new Nasca geoglyphs identified by Deep Learning. (A) A humanoid, relief-type. (B) A pair of legs, line-type. (C) A fish, relief-type. (D) A bird, line-type. (B to D) are presented to the public for the first time in this paper. Science Direct

“We have developed a DL pipeline that addresses the challenges that frequently arise in the task of archaeological image object detection,” the study’s authors write. Our method enables the discovery of previously unattainable targets by enabling DL to learn representations of images with better generalization and performance. Additionally, by speeding up the research process, our approach advances archaeology by introducing a novel paradigm that combines field research and AI, resulting in more effective and efficient investigations.

These results serve as yet another illustration of how machine learning can be useful to scientists, particularly when tackling tasks involving sizable datasets. Just like humans, algorithms can be taught to sift through specific types of data looking for patterns and anomalies. Although creating these tools can be challenging, once trained, such algorithms are tireless and consistent.

Cover Photo: Yamagata University / IBM Japan

https://doi.org/10.1016/j.jas.2023.105777

Related Articles

2nd-Century Statue Head Discovered at Fethiye Castle

22 August 2024

22 August 2024

Türkiye’s coastal town of Fethiye, which is famous for its natural beauties and historical sites, found an 1800-year-old statue head...

Poland’s largest megalithic cemetery discovered

3 March 2021

3 March 2021

Archaeologists excavated in Poland discovered a large megalithic complex, including dozens of tombs dating back 5,500 years. The site was...

Britain’s Hidden Treasures: The Pieces of Rare Iron Age Helmet Found at Snettisham

19 January 2025

19 January 2025

Thanks to advanced scientific testing, the copper alloy fragments unearthed at Snettisham, Norfolk, at one of Britain’s most significant archaeological...

A Christian monastery, possibly pre-dating Islam, found in UAE

6 November 2022

6 November 2022

A Christian monastery has been discovered on the island of Siniyah off the coast of the United Arab Emirates (UAE),...

Between Shamans, Gods and Spirits: A Journey into Bulgaria’s Mysterious Central Asian Origins

2 July 2025

2 July 2025

Long before modern borders were drawn, ancient spiritual traditions — led by shamans and rooted in communion with the unseen...

Rare 400-year-old Bronze Trumpets Discovered on a shipwreck in Croatia

12 July 2024

12 July 2024

Croatian underwater archaeologists have made an extraordinary discovery off the southern coast of Istria near Cape Kamenjak. They have unearthed...

The 4,500-year-old Wisconsin canoe was built around the same time that Stonehenge was being constructed

31 May 2024

31 May 2024

Historians from Wisconsin have reported the amazing finding of at least eleven prehistoric canoes in Lake Mendota, which is close...

New discoveries in Göbeklitepe and Karahantepe: A Human statue with a realistic facial expression found in Karahantepe

30 September 2023

30 September 2023

New finds were discovered in Göbeklitepe and Karahantepe. At around 12,000 years old, Göbekli Tepe is the world’s oldest megalithic...

The oldest evidence of human cannibalism as a funerary practice in Europe

7 October 2023

7 October 2023

According to a new study, cannibalism was a common funerary practice in northern Europe around 15,000 years ago, with people...

300 Year Old “Exceptional” Prosthesis made of Gold and Copper and wool Discovered in Poland

14 April 2024

14 April 2024

Something novel has been discovered by Polish archaeologists working on the excavation of the Church of St. Francis of Assisi...

Rare Arabic inscription discovered during Malta housing project works

3 May 2023

3 May 2023

A rare Arabic inscription, possibly dating back to medieval times, was discovered at the site of a social housing project...

Archaeologists deciphered the Sabaean inscription on a clay jar finds link between King Solomon and the Queen of Sheba

3 April 2023

3 April 2023

Archaeologists deciphered a partially preserved inscription that was found on the neck of a large jar dated back to the...

Researchers sequenced the DNA 1,600-year-old sheep mummy from an ancient Iranian salt mine, Chehrabad

16 July 2021

16 July 2021

A multinational team of geneticists and archaeologists sequenced the DNA from a 1,600-year-old sheep mummy discovered from Chehrabad, a salt...

Discovery Shedding Light on the Mysteries of Anatolia: 3500-year-old Double-Headed Eagle Seal

21 October 2024

21 October 2024

A grain silo and two different seal impressions, one of which is a double-headed eagle, were found during the excavation...

Unique work of Minoan art, the Pylos Combat Agate must be the David of the Prehistoric era

21 November 2021

21 November 2021

Found in a Greek tomb dating back 3,500 years, the artifact is so well designed that it looks as lively...