Connect with us

Archaeology

Archaeologists use AI to identify new archaeological sites in Mesopotamia

Published

on

Archaeologists from the University of Bologna have developed a system of AI algorithms that can identify previously undiscovered archaeological sites in the southern Mesopotamian plain.

Deep learning has found multiple uses in every field of application. In the context of archaeology, it can help in classifying objects and text, finding similarities, building 3D models, and the detection of sites.

The team conducted a test in the Maysan Province of Iraq, where the AI algorithm correctly identified sites of interest with an accuracy of 80%.

The results of the study, published in the journal Scientific Reports, emphasises the issue of thousands of satellite photos in archives that would require a large amount of resources to analyse, however, using an automatic AI system, this would massively reduce the time and resources needed.

According to the study authors: “This procedure falls into the domain of Remote Sensing (RS) which indicates the act of detecting and/or monitoring a point of interest from a distance. In the world of archaeology, this operation has become invaluable with the availability of more and better imagery from satellites that can be combined with older sources of information.”

The researchers utilised a dataset consisting of vector shapes representing the archaeologically recorded sites within the southern Mesopotamian floodplain. Through training, they developed a system capable of identifying and delineating sites using pretrained models for semantic segmentation, fine-tuned on satellite imagery, and masks of the site shapes.

The study authors said: “The potential applications of this method are far reaching and do not only concern its speed: it should rather be seen as a necessary complement to traditional expert-based photointerpretation, adding to the latter in many cases site features which may go overlooked but are likely to be significant.”

University of Bologna

https://doi.org/10.1038/s41598-023-36015-5

Header Image Credit : University of Bologna

Continue Reading

Archaeology

Archaeologists search crash site of WWII B-17 for lost pilot

Published

on

By

Archaeologists from Cotswold Archaeology are excavating the crash site of a WWII B-17 Flying Fortress in an English woodland.

The B-17 Flying Fortress is an American four-engine heavy bomber aircraft developed in the 1930s for the United States Army Air Corps (USAAC).

The bomber was mainly used in the European theatre for daylight strategic bombing, complimenting the RAF Bomber Command’s night bombers in attacking German industrial, military and civilian targets.

Cotswold Archaeology have been tasked by the Defense POW / MIA Accounting Agency to search the crash site for the remains of the pilot, who died when the B-17 crashed following a system failure in 1944.

Image Credit : Cotswold Archaeology

At the time, the plane was carrying a payload of 12,000lbs of Torpex, an explosive comprised of 42% RDX, 40% TNT, and 18% powdered aluminium. Torpex was mainly used for the Upkeep, Tallboy and Grand Slam bombs, as well as underwater munitions.

The pilot was declared MIA when the plane exploded into an inferno, however, using modern archaeological techniques, the researchers plan to systematically excavate and sieve the waterlogged crash site to recover plane ID numbers, personal effects, and any surviving human remains.

It is the hope of the excavation team members that they will be able to recover the pilot’s remains and return him to the United States for burial with full military honours.

The Defense POW/MIA Accounting Agency (DPAA) is an agency within the U.S. Department of Defense whose mission is to recover unaccounted Department of Defense personnel listed as prisoners of war (POW) or missing in action (MIA) from designated past conflicts.

Header Image Credit : Cotswold Archaeology

Sources : Cotswold Archaeology

This content was originally published on www.heritagedaily.com – © 2023 – HeritageDaily

Continue Reading

Archaeology

Roman Era tomb found guarded by carved bull heads

Published

on

By

Archaeologists excavating at the ancient Tharsa necropolis have uncovered a Roman Era tomb guarded by two carved bull heads.

Tharsa is located near Kuyulu village in southeastern Turkey along the Adıyaman-Şanlıurfa Highway.

The site was situated on a major Roman highway from Doliche to Samosata, which today consists of a two settlement mounds and a large necropolis that dates from the 3rd century to the Byzantine period.

Excavations first commenced in 2021 which discovered a collection of Turuş Rock Tombs, a type of tomb construction carved directly into the bedrock.

In the latest season, archaeologists have excavated another Turuş Rock Tomb, however, this example was found to have two carved bull heads which is decorated with garlands and rosettes between the horns.

Bull heads, known as Bucranium, were a form of carved decoration commonly used in Classical architecture. In Ancient Rome, bucrania were often used on the friezes of temples in the Doric order of architecture, later influencing the architecture of buildings from the Renaissance, Baroque, and Neoclassical periods.

Architectural examples of bucrania are representations of the practice of displaying garlanded, sacrificial oxen, whose heads were displayed on the temple walls.

Like similar Turuş Rock Tombs, the bull heads are carved directly into the bedrock, guarding a dozen rock cut steps descending into the burial chamber which has three arched niches known as acrosolia.

Mustafa Çelik, Deputy Director of Adıyaman Museum, said, “Tharsa Ancient City consists of 3 main archaeological areas: Big Mound, Small Mound and Necropolis Area. We started excavations in the necropolis area in 2024. We added 2 more rock tombs to the rock tombs we had previously uncovered. One of them is the rock tomb we identified today.”

Header Image Credit : Adıyaman Museum

Sources : Adıyaman Museum

This content was originally published on www.heritagedaily.com – © 2023 – HeritageDaily

Continue Reading

Trending

Generated by Feedzy