23 September 2023 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

Banner
Related Post

The largest embalming cache ever found in Egypt unearthed at Abusir

10 February 2022

10 February 2022

Archaeologists from the Czech Institute for Egyptian Science have discovered a cache of artifacts related to the practice of Egyptian...

A first-of-its-kind Ayyanar stone idol found in Vellore, India

25 June 2022

25 June 2022

An Ayyanar stone idol, the first of its kind in Vellore, was discovered at Thandalai Krishnapuram (TK Puram) in Tamil...

A 7,500-year-old settlement has been discovered in Turkey’s Domuztepe Mound

11 September 2021

11 September 2021

During the most recent excavations at Domuztepe Mound in the Türkoğlu district of southern Turkey’s Kahramanmaraş province, a settlement and...

New ancient ape from Türkiye challenges the story of human origins

2 September 2023

2 September 2023

A recently discovered fossilized ape from a site in Turkey that is 8.7 million years old is inspiring scientists to...

Contemporaneous with ancient Egypt and Mesopotamia the Indus Valley Civilization city of ‘Mohenjo Daro’: Skilled urban planners with a reverence for the control of water

10 September 2022

10 September 2022

The Indus River Valley (or Harappan) civilization (3300-1300 BCE) lasted 2,000 years and spanned northeast Afghanistan to Pakistan and northwest...

Evidence of textile manufacture dating back millennia was found in an area famous for the Witney Blanket

12 June 2023

12 June 2023

Archaeological excavations at the site of Oxfordshire County Council’s project to build the A40 Science Transit Park and Ride at...

Archaeologists find 4 Umayyad epigraphs in the ancient city Knidos

24 May 2022

24 May 2022

Archaeological excavations in the ancient city of Knidos connected to Datça District of Muğla province in western Turkey have unearthed...

When the waters receded, the mounds of Pulur Sakyol and Yeniköy, bearing the traces of Kura-Aras Culture, came to light

8 December 2021

8 December 2021

The important cultural areas of Pulur Sakyol and Yeniköy mounds, which bear the traces of Kura-Aras Culture, represented by kurgans...

5,500-year-old Menhir discovered in Portugal

28 August 2023

28 August 2023

A 5,500-year-old (that is around 3500 BC) menhir has been discovered in the town of São Brás de Alportel in...

Archaeologists in Peru discover a mummy tied with 800-year-old ropes

28 November 2021

28 November 2021

On Peru’s central coast, archaeologists discovered a mummy estimated to be at least 800 years old. The mummy’s body was...

An exciting discovery in Hattusa, the capital of the Hittites

11 September 2022

11 September 2022

It is aimed to reach new information about the traditions of the Hittite civilization with 249 new hieroglyphs discovered in...

The 890-million-year-old sponge fossil may be the oldest animal yet discovered

1 August 2021

1 August 2021

890-million-year-old fossil sponges found in the “Little Dal” limestones of northwest Canada may be the oldest animal ever found. According...

A 2,000-year-old ancient “mirror” throws light on aristocratic life in China

17 May 2022

17 May 2022

Archeologists in Beijing have successfully reconstructed a 2,000-year-ago dressing mirror once cherished by the high nobility during the Han Dynasty....

Archaeologists unearth mosaic floors in the ruins of a building they believe is the lost Church of the Apostles

23 October 2021

23 October 2021

In the historical village of Bethsaida on the edge of the Sea of Galilee, archaeologists discovered mosaic floors in the...

7500-year-old cursed city of Iran

17 March 2023

17 March 2023

Sialk Hills, located in the southwestern part of Kashan city in Iran, was known among the locals as a ‘cursed...

Comments
Leave a Reply

Your email address will not be published. Required fields are marked *