16 June 2024 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

The colored skeletons of Çatalhöyük provide insight into the burial rituals of a fascinating society that lived 9000 years ago

18 March 2022

18 March 2022

New research provides new insights into how the inhabitants of the “oldest city in the world” in Çatalhöyük (Turkey) buried...

New mosaics unearthed in “Zeugma of the Black Sea”

3 October 2022

3 October 2022

New mosaics with various figures were unearthed during the ongoing excavations in the ancient city of Hadrianopolis, which is called...

Magical Roman Phallus Wind Chime Unearthed in Serbia

15 November 2023

15 November 2023

Archaeologists have unearthed a Roman phallus wind chime known as a tintinnabulum, during excavations at the ancient city of Viminacium...

Tombs of elite Wari craftsmen found in the royal necropolis in Castillo de Huarmey, Peru

12 September 2022

12 September 2022

A group of tombs of elite craftsmen of the Wari culture has been discovered at the archaeological site of Castillo...

A rare medieval Christogram Tattoo from Ghazali, Sudan

22 October 2023

22 October 2023

A Polish-Sudanese research team investigating the medieval African monastery of Ghazali discovered a rare medieval religious tattoo in a tomb...

A 12.000 -year-old temple was found during excavations in Boncuklu Tarla in southeastern Turkey

21 October 2021

21 October 2021

A temple thought to be 12 thousand years old was unearthed in Boncuklu Tarla in the Ilısu Neighborhood of Dargeçit...

Arkeologists decipher hieroglyphics of a vessel found in the archaeological rescue of the Mayan Train

16 May 2022

16 May 2022

Based on the analysis of eleven glyphic cartouches inscribed into a ceramic pot, discovered in October 2021 during archaeological rescue...

Oldest footprints of pre-humans identified in Crete

11 October 2021

11 October 2021

Six million-year-old fossilized footprints on the island show the human foot had begun to develop. The oldest known footprints of...

The ashes of 8,000 victims were found in two mass graves near the Soldau concentration camp in Poland

14 July 2022

14 July 2022

Polish authorities said they had unearthed two mass graves near the former Nazi concentration camp Soldau containing the ashes of...

“Land of the Thousand Temples” Kancheepuram in India

20 May 2021

20 May 2021

Kancheepuram, one of the most sacred and religious Hindu pilgrim centers in India is also called the ‘Land of the...

3000 years old wooden wishing well discovered in Germany

7 January 2023

7 January 2023

In the town of Germering, in the Germany state of Bavaria, archaeologists have unearthed the remains of a well-preserved Bronze...

The World’s Largest Pyramid Is Hidden Within a Hill in Mexico

8 October 2022

8 October 2022

The largest and tallest pyramids in the world are incredible feats of design, engineering, and construction. The Great Pyramid of...

Britain’s first Roman funerary bed is discovered in central London after 2,000 years

7 February 2024

7 February 2024

Archaeologists excavating a construction site in London have unearthed the first Roman “flat-packed” funerary furniture – a fully intact Roman...

16 New Ancient Rock Art Sites Discovered In Jalapão, Brazil

13 March 2024

13 March 2024

Archaeologists at Brazil’s National Institute of Historical and Artistic Heritage (Iphan) discovered 16 new archaeological sites while surveying a large...

Ancient Murals of Two-faced Figures Found in Peru

21 March 2023

21 March 2023

Archaeologists are reporting a number of fascinating discoveries as work on the excavations at Pañamarca progresses that are helping to...