5 July 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

A 1900-year-old stele was discovered in Turkey’s ancient city of Parion

5 August 2021

5 August 2021

A 1,900-year-old grave stele was found during excavations in Parion, an important ancient port city, near Kemer village in the...

Archaeologists Uncovered Rich Viking Women’s Graves in Norway

23 December 2024

23 December 2024

Archaeologists have discovered a wealth of Viking Age history on a treasure trove at Skumsnes farm in Fitjar, Norway’s west...

Iraqis Disliked El Nouri Mosque’s Restoration Plan

18 April 2021

18 April 2021

UNESCO recently announced that the El Nouri mosque, which was bombed by ISIL(The Islamic State of Iraq and the Levant),...

Archaeologists discovered how wine was cooled in Roman legions on the Danube

15 September 2023

15 September 2023

Lead archaeologist Piotr Dyczek, a professor at the Center for Research on Antiquities of Southeastern Europe at the University of...

First Female Viking Grave Discovered In Swedish Mountains

21 August 2022

21 August 2022

A mountain hiker in Jämtland, in central Sweden, on his way camping in Kalffällen, made a surprising discovery. The discovery...

A rare 3,300-year-old bronze helmet reaching the present from the Hittite Empire era

17 July 2022

17 July 2022

The 3,300-year-old bronze helmet, which was unearthed during the 2002 excavations in Şapinuva, one of the important cult centers of...

Ukraine says Russian forces stole Scythian treasures from Melitopol Museum

11 May 2022

11 May 2022

Invading Russian troops have stolen items of ancient Scythian gold and other historical and cultural valuables that were stored in...

4750-year-old Megalithic Stone Plaza Discovered in the High Andes of Peru

15 February 2024

15 February 2024

Two anthropology professors from the University of Wyoming have discovered a prehistoric plaza high in the Andes, known as Callacpuma...

Baptismal font from the Ottonian period discovered: Oldest evidence of a quatrefoil-shaped basin north of the Alps

19 March 2024

19 March 2024

The site of a font of the medieval Ottonian dynasty, from the tenth century, has been discovered in the crypt...

Archaeologists Find Rare Ancient African Figurines in Christian Graves in Negev Desert

2 June 2025

2 June 2025

Researchers have uncovered five miniature figurines, including intricately carved African heads, in 1,500-year-old graves in Israel’s Negev Desert. These rare...

13,000-year-old Clovis campsite discovered in Michigan

10 September 2021

10 September 2021

In St. Joseph County, independent researcher Thomas Talbot and University of Michigan scholars uncovered a 13,000-year-old Clovis campsite, which is...

An artificial intelligence “Ithaca” that will improve our understanding of ancient history

11 March 2022

11 March 2022

A deep neural network trained to restore ancient Greek texts can do so with 72% accuracy when used by historians,...

Scientists Use Artificial İntelligence to Study Ancient Australian Rock Art

1 April 2021

1 April 2021

Rock art is the oldest surviving human art form. Throughout Australia, petroglyphs are part of the life and customs of...

‘Theodoric the Great’ villa mosaic found near Verona in Italy

17 April 2022

17 April 2022

A section of the ancient Roman mosaic flooring from the 5th century AD villa of Ostrogoth king Theodoric the Great...

Roman Canal and Road Uncovered in The Netherlands near UNESCO heritage sites

30 July 2021

30 July 2021

Dutch archaeologists that a canal and gravel road thought to have been built and used by the Roman military have...