19 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

Marble inlay floors found in a Sunken Roman villa in Baia, the Las Vegas of the ancient world

9 April 2023

9 April 2023

Expansion of research activities in the Terme del Lacus area in the sunken Baia park, known as the ‘Las Vegas’...

The 3,200-year-old perfume of Tapputi, the first female chemist in history, came to life again

24 July 2022

24 July 2022

One of the scent formulas written in Akkadian on clay tablets by Tapputi, known as the world’s first female perfumer...

3,200-Year-Old Temple Mural of Spider God in Peru

25 March 2021

25 March 2021

Archaeologists in northern Peru have discovered a 3200-year-old mural. The mural was painted on the side of an ancient adobe...

Archaeologists Uncover Early Bronze Age Ceremonial Complex in Murayghat, Jordan

4 August 2025

4 August 2025

Archaeologists have uncovered striking evidence of an ancient ceremonial complex in Murayghat, Jordan, that could rewrite what we know about...

Göbeklitepe Monolith will be Exhibited in the United Nations

15 May 2021

15 May 2021

A copy of one of the famous ruins of Göbeklitepe, known as the oldest temple in the world, will be...

Evil-Wisher Well: Ancient curse tablets 2,500-year-old found in a well in Athens

14 July 2022

14 July 2022

30 ancient curse tablets were found at the bottom of a 2500-year-old well in ancient Athens. In 2020, Archaeologists from...

2,000-Year-Old Hellenistic Tomb Discovered Under Collapsed Port Road in Northern Cyprus

24 June 2025

24 June 2025

A routine alert about a collapsed road at Gazimağusa Port in Northern Cyprus has led to a remarkable archaeological breakthrough....

The mythical hero of Troy and Rome Aeneas’s peerless mosaic discovered in Türkiye

11 May 2023

11 May 2023

A large mosaic depicting the legendary Trojan hero Aeneas, the protagonist of Virgil’s epic poem “The Aeneid” and the ancestor...

The Life of the Maya Ambassador Found in El Palmar was not Easy

18 March 2021

18 March 2021

El Palmar is a small plaza compound in Mexico near the borders of Belize and Guatemala. Archaeologists Kenichiro Tsukamoto and...

A new Indo-European Language discovered in the Hittite capital Hattusa

21 September 2023

21 September 2023

The Çorum Provincial Directorate of Culture and Tourism announced in a written statement that a new Indo-European language was discovered...

Archaeologists find an Anglo-Saxon church at Stoke Mandeville excavation site

13 September 2021

13 September 2021

Archaeologists working on the HS2 project found the remains of an Anglo-Saxon church during their excavations at the former St...

The Sedgeford Anglo-Saxon malting complex may be the largest ever discovered in the UK

23 July 2023

23 July 2023

As archaeological excavations resume on a hill in Sedgeford, near Hunstanton, a seaside town in Norfolk, England, now more evidence...

A 2,500-year-old celestial map carved on the surface of a circular stone found in Italy

25 December 2023

25 December 2023

Two circular stones measuring 50 centimeters in diameter have been discovered in Castelliere di Rupinpiccolo, an ancient hilltop fortress in...

Four-face ivory dice found at Keezhadi excavation site in India

18 February 2022

18 February 2022

The Tamil Nadu Archaeological department along with the Archaeological Survey of India has unearthed rectangular ivory dice,  in the excavation...

Ancient Egyptian silos and administrative buildings uncovered at Kom Ombo in Egypt’s Aswan

6 March 2022

6 March 2022

The Egyptian-Austrian archaeological mission working in the Temple of Kom Ombo in Egypt’s southern province of Aswan unearthed an administrative...