3 March 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

Archaeologists Discovered Submerged Stoa Complex in Ancient Salamis, Greece

27 October 2023

27 October 2023

Archaeologists exploring the east coast of Salamis, the largest Greek island in the Saronic Gulf, discovered a large, long, and...

The largest stone coffin grave found so far at the Yoshinogari Ruins -3.2 meters

30 May 2023

30 May 2023

A grave with a stone coffin around 2.3 meters long and dating to the latter part of the Yayoi Period...

1300-year-old stone sculpture from the ancient Turkish era found in Kazakhstan

3 August 2021

3 August 2021

A 1,300-year-old stone sculpture from the early Turkish period was discovered in Kazakhstan’s south, around 250 kilometers (155 miles) from...

New Discoveries of Sanxingdui Ancient City to be Announced

19 March 2021

19 March 2021

Sanxingdui, which literally means “Stacks of Three Stars”, is a cultural relic of the Kingdom of Shu in ancient China....

4 Aztec child burials unearthed in Mexico and dated to the Early Colonial period may be indicators of Aztec resistance

6 July 2022

6 July 2022

During an archaeological rescue effort in Mexico City’s historic central district of La Lagunilla, the remains of an Aztec house...

Norwegian couple found a Viking Age Grave And Sword in their garden

3 July 2023

3 July 2023

While trying to expand their home, a Norwegian couple found a Viking Age grave and sword in their garden. It’s...

Israeli researchers create AI to translate ancient cuneiform Akkadian texts

4 May 2023

4 May 2023

Israeli experts have created a program to translate an ancient language that is difficult to decipher, allowing automatic and accurate...

A rare Ogham inscription found on Pictish stone in Scottish Kirkyard

8 November 2022

8 November 2022

A Pictish carved stone cross slab with a rare inscription in the early medieval ogham language has been discovered in...

1650-Year-Old Earthen Grills Unearthed in Assos Excavations

14 August 2021

14 August 2021

Excavations continue in Assos Ancient City, a rich settlement of the period, which is located within the borders of Behramkale...

Rock Ship of Masuda, Japan’s mysterious monolith

17 April 2023

17 April 2023

Located in the Takaichi District of Nara Prefecture, Japan, the village of Asuka is famous for its mysterious stones. The...

Researchers find the earliest record of aurora in old Chinese documents

15 April 2022

15 April 2022

Researchers have found the oldest known reference to a candidate aurora in a celestial event, described in an ancient Chinese...

Researchers may have found 3,000-year-old evidence of Yue (Amputation), one of the five punishments practiced in ancient China

4 May 2022

4 May 2022

According to the South China Morning Post, researchers in China believe a skeleton discovered in a tomb in the country’s...

Could the Kerkenes Settlement be Gordion the Second?

1 August 2022

1 August 2022

Although the settlement on the Kerkenes mountain, located within the borders of Sorgun district of Yozgat, has been known and...

1000-Year-Old Tomb Found in Perre Ancient City in southeast Turkey

1 July 2021

1 July 2021

A 1,000-year-old tomb was unearthed in the ancient city of Perre in Adiyaman province. Perre is one of the five...

4000-year-old sword found in Finland

12 October 2021

12 October 2021

A Bronze Age sword dating back as far as 1700 B.C.was discovered broken in items in Finland this previous summer...