CRANE

We are pleased to share that our newest institutional partner, Prof. Scott Branting and the University of Central Florida, have just received follow on National Endowment for the Humanities – Digital Humanities Advancement Grant for the Documenting and Triaging Cultural Heritage (DATCH) Project. The total amount of the grant is $375,000 (including $50,000 in matching funds).

The Documenting and Triaging Cultural Heritage (DATCH) project at the University of Central Florida (UCF) is developing an open-source software with the purpose of creating native 3D drawings and undertaking comparative field assessments using head mounted display augmented reality devices. DATCH will do this by leveraging the core capabilities of augmented reality hardware such as Microsoft HoloLens, the HoloLens 2, and Magic Leap One and augment them with software development. The software is built within Unity to allow for the capabilities developed to function in a cross-platform manner.

In 2021, the first of three years of software development and testing, the team plans to: 1) update the prototype software to run on the HoloLens 2 and Magic Leap One devices, 2) work on integrating GPS devices for real-world geolocation, 3) expand the user interface and import/export capabilities, 4) test the new capabilities and preliminary accuracy on projects at UCF and within CRANE institutional members and on field projects in the US and in the Middle East.

You can also read our previous story about the CRANE – DATCH partnership.

The “Green Sahara” era of humid climates in Africa might not seem, at first glance, to be part of CRANE’s purview. But CRANE post-doctoral researcher Deepak Chandan, who recently co-authored a research paper on climate modeling for that period with CRANE Co-Investigator, U of T Physics Professor W. Richard Peltier, says it’s very relevant to CRANE: “One of CRANE’s interests is to understand why settled habitation and civilizations arose in certain places,” he explains, and climate doesn’t stop at borders or oceans. “Climate in one part of the world can affect another. For example, research by U of T Physics graduate student Yiling Huo has shown that the West African monsoon has an impact as far away as Southeast Asia as well.”

One of the challenges of such Global Climate Models (CGMs), is that they are “very coarse”, as Chandan puts it, producing singular information for an area roughly 100 km by 100 km. Chandan and Peltier’s goal is to find out how climate affected different areas in different ways, and for that, they need to use “dynamical downscaling”, which involves running a higher-resolution Regional Coupled-Climate Model (RCM). Chandan says this model “gets hints for what the climate of the region should look like from the global model, but runs on a much higher-resolution grid, and contains physics that the coarser-resolution global model cannot simulate.” This model runs on a resolution of 30 km, and Chandan says they’re working to narrow it down even further, to 10 km.

Chandan also says that because there is so much data on the Green Sahara period, “you have a very good chance of finding relevant high-quality information that you can use to constrain the predictions of the models,” since the phenomenon that produced the Green Sahara affected other surrounding regions as well, including the Arabian Peninsula, Levant and Mesopotamia.

Chandan reports that U of T Physics graduate student Fengyi Xie has been working to perfect the modeling pipeline, which will facilitate the next step of the study involving agent-based modeling of Middle Eastern landscapes and land use, and the Bronze Age communities that lived in them. Chandan says that CRANE’s agent-based modeling effort integrates climate dynamics, simulated with a high-fidelity high-resolution model, and human dynamics. This not only helps to ground and refine climate models, it also “enables us to gain valuable insights into the adaptive strategies of these historical communities, as well as their longer-term environmental impacts.”

Written by Jaime Weinman (jaimeweinman.com).

We are pleased to share the great news that Dr. Rana Özbal (Koç University, Turkey) and Dr. Kamal Badreshany (Durham University, UK) have received the Newton Mobility Grant for their research project titled “Innovative Exchanges: The Development, Dissemination, and Adoption of the Earliest Pottery Traditions in the Eastern Mediterranean“.

This project seeks to reveal the nature of exchange, social interaction, and pathways for technological innovation amongst early farming communities in the fertile crescent through the proxy of ceramic material. The Northern Levant saw the emergence of settled farming lifestyles and the earliest adoption of pottery technology around 7,000 BC. Scholars refer to this material as Dark-Faced Burnished Ware (DFBW) and it is of exceptional quality. Yet, there is much that remains unclear about the use of these vessels, and, indeed, the societies of the time. The region is geographically diverse defined by coastal and inland areas occurring on a north-south axis parallel to the Mediterranean Sea. The zones exhibit distinct climates and are separated by mountains that hinder communication leading to distinct agricultural and, perhaps, social rhythms. Evidence across a range of categories (e.g. pottery and lithic types, architecture, settlement patterns, etc.) has led these two researchers to hypothesize that likewise two distinct zones of intensive interaction existed among Neolithic communities, fostered by easier communication and similar geographically conditioned subsistence strategies.

Özbal and Badreshany will investigate ceramic assemblages from key sites across both zones, integrating a traditional style-focused macroscopic approach with a novel materials science-based methodology. The results will shed new light on exchange networks and the intensity and orientation of social interactions. Ceramics were widely traded at the time and produced in multiple locations, unlike other categories of material culture which are made of geographically restricted materials. Characterizing their textural, mineralogical and chemical composition will reveal where ceramics found at a site were produced and, in turn, inform on trade patterns and their intensity.

Petrographic and geochemical methods applied to ceramics to determine provenance and circulation are well-established, but these scholars will for the first time utilize an electron microscope based automated mineralogy platform (Zeiss Mineralogic), which will generate a petrographic dataset of higher quality and on a far larger scale than previous studies. The machine is one of only five in the UK and is maintained and managed in part by Durham Archaeology, ensuring regular access for the applicants.  This data will be reinforced through geochemical fingerprinting using ICP-OES/MS to provide further support for provenance determinations. The ICP instruments are located at Koç University Archaeology and Central Labs respectively.

The project plans to draw on a geographically extensive dataset of 100 DFBW samples, broadly contemporary, from two coastal regions and two inland regions. The coastal regions included are the Northern Lebanese Coast and the Amuq plain (S. Turkey) while the Beqaa Valley (Lebanon) and the upper and middle Orontes Valley (W. Syria) represent the inland regions in the study. The samples from different sites will be categorized macroscopically into groupings thought to represent discreet productions. Samples will be sectioned and polished for automated mineralogy analysis and powders will be taken for acid digestion and analysis via ICP. The resulting data will be processed utilizing statistical procedures including principal components analysis and cluster analysis, and compared to existing geochemical and petrographic datasets. 

PMIP (Paleoclimate Modelling Intercomparison Project) is an international project for coordinating palaeoclimate modelling activities designed to understand the mechanisms of climate change and test whether climate models can represent a climate state different from the present day. PMIP organizes coordinated model experiments for key periods in the past, designed to study the impact of changes in various boundary conditions, external events, and the impact of feedbacks in climate models. As a result, work with PMIP has become an important focus of CRANE’s Climate Modelling Project. The annual PMIP 2020 Conference was originally organized for Nanjing, China, between October 26-30, but was predominantly held online due to Covid-19. CRANE researchers Dick Peltier, Deepak Chandan, and Yiling Huo of the Department of Physics presented CRANE-related work.

The first presentation by Deepak Chandan and Dick Peltier was entitled:

African Humid Period Sustained by Robust Vegetation, Soil and Lake Feedbacks

The second presentation was by Yiling Huo, along with Peltier and Chandan, and was entitled:

Dynamically Downscaled Climate Simulations for the South and Southeast Asian Monsoon during the Mid-Holocene

The full paper discussing Deepak and Dick’s research on the “Green Sahara” can be found at:

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020GL088728

Trawling ancient history with neural nets.

Originally published in the New York Times, Nov 24, 2020, by Zach Zorich.

Finding the tomb of an ancient king full of golden artifacts, weapons and elaborate clothing seems like any archaeologist’s fantasy. But searching for them, Gino Caspari can tell you, is incredibly tedious.

Dr. Caspari, a research archaeologist with the Swiss National Science Foundation, studies the ancient Scythians, a nomadic culture whose horse-riding warriors terrorized the plains of Asia 3,000 years ago. The tombs of Scythian royalty contained much of the fabulous wealth they had looted from their neighbors. From the moment the bodies were interred, these tombs were popular targets for robbers; Dr. Caspari estimates that more than 90 percent of them have been destroyed.

He suspects that thousands of tombs are spread across the Eurasian steppes, which extend for millions of square miles. He had spent hours mapping burials using Google Earth images of territory in what is now Russia, Mongolia and Western China’s Xinjiang province. “It’s essentially a stupid task,” Dr. Caspari said. “And that’s not what a well-educated scholar should be doing.”

As it turned out, a neighbor of Dr. Caspari’s in the International House, in the Morningside Heights neighborhood of Manhattan, had a solution. The neighbor, Pablo Crespo, at the time a graduate student in economics at City University of New York who was working with artificial intelligence to estimate volatility in commodity prices, told Dr. Caspari that what he needed was a convolutional neural network to search his satellite images for him. The two bonded over a shared academic philosophy, of making their work openly available for the benefit of the greater scholarly community, and a love of heavy metal music. Over beers in the International House bar, they began a collaboration that put them at the forefront of a new type of archaeological analysis.

A convolutional neural network, or C.N.N., is a type of artificial intelligence that is designed to analyze information that can be processed as a grid; it is especially well suited to analyzing photographs and other images. The network sees an image as a grid of pixels. The C.N.N. that Dr. Crespo designed starts by giving each pixel a rating based on how red it is, then another for green and for blue. After rating each pixel according to a variety of additional parameters, the network begins to analyze small groups of pixels, then successively larger ones, looking for matches or near-matches to the data it has been trained to spot.

Working in their spare time, the two researchers ran 1,212 satellite images through the network for months, asking it to look for circular stone tombs and to overlook other circular, tomblike things such as piles of construction debris and irrigation ponds.

At first they worked with images that spanned roughly 2,000 square miles. They used three-quarters of the imagery to train the network to understand what a Scythian tomb looks like, correcting the system when it missed a known tomb or highlighted a nonexistent one. They used the rest of the imagery to test the system. The network correctly identified known tombs 98 percent of the time.

Creating the network was simple, Dr. Crespo said. He wrote it in less than a month using the programming language Python and at no cost, not including the price of the beers. Dr. Caspari hopes that their creation will give archaeologists a way to find new tombs and to identify important sites so that they can be protected from looters.

Other convolutional neural networks are beginning to automate a variety of repetitive tasks that are usually foisted on to graduate students. And they are opening new windows on to the past. Some of the jobs that these networks are inheriting include classifying pottery fragments, locating shipwrecks in sonar images and finding human bones that are for sale, illegally, on the internet.

“Netflix is using this kind of technique to show you recommendations,” Dr. Crespo, now a senior data scientist for Etsy, said. “Why shouldn’t we use it for something like saving human history?”

Gabriele Gattiglia and Francesca Anichini, both archaeologists at the University of Pisa in Italy, excavate Roman Empire-era sites, which entails analyzing thousands of broken bits of pottery. In Roman culture nearly every type of container, including cooking vessels and the amphoras used for shipping goods around the Mediterranean, was made of clay, so pottery analysis is essential for understanding Roman life.

The task involves comparing pottery sherds to pictures in printed catalogs. Dr. Gattiglia and Dr. Anichini estimate that only 20 percent of their time is spent excavating sites; the rest is spent analyzing pottery, a job for which they are not paid. “We started dreaming about some magic tool to recognize pottery on an excavation,” Dr. Gattiglia said.

That dream became the ArchAIDE project, a digital tool that will allow archaeologists to photograph a piece of pottery in the field and have it identified by convolutional neural networks. The project, which received financing from the European Union’s Horizon 2020 research and innovation program, now involves researchers from across Europe, as well as a team of computer scientists from Tel Aviv University in Israel who designed the C.N.N.s.

The project involved digitizing many of the paper catalogs and using them to train a neural network to recognize different types of pottery vessels. A second network was trained to recognize the profiles of pottery sherds. So far, ArchAIDE can identify only a few specific pottery types, but as more researchers add their collections to the database the number of types is expected to grow.

“I dream of a catalog of all types of ceramics,” Dr. Anichini said. “I don’t know if it is possible to complete in this lifetime.”

Saving time is one of the biggest advantages of using convolutional neural networks. In marine archaeology, ship time is expensive, and divers cannot spend too much time underwater without risking serious pressure-related injuries. Chris Clark, an engineer at Harvey Mudd College in Claremont, Calif., is addressing both problems by using an underwater robot to make sonar scans of the seafloor, then using a convolutional neural network to search the images for shipwrecks and other sites. In recent years he has been working with Timmy Gambin, an archaeologist at the University of Malta, to search the floor of the Mediterranean Sea around the island of Malta.

Their system got off to a rough start: On one of its first voyages, they ran their robot into a shipwreck and had to send a diver down to retrieve it. Things improved from there. In 2017, the network identified what turned out to be the wreck of a World War II-era dive bomber off the coast of Malta. Dr. Clark and Dr. Gambin are now working on another site that was identified by the network, but did not want to discuss the details until the research has gone through peer-review.

Shawn Graham, a professor of digital humanities at Carleton University in Ottawa, uses a convolutional neural network called Inception 3.0, designed by Google, to search the internet for images related to the buying and selling of human bones. The United States and many other countries have laws requiring that human bones held in museum collections be returned to their descendants. But there are also bones being held by people who have skirted these laws. Dr. Graham said he had even seen online videos of people digging up graves to feed this market.

“These folks who are being bought and sold never consented to this,” Dr. Graham said. “This does continued violence to the communities from which these ancestors have been removed. As archaeologists, we should be trying to stop this.”

He made some alterations to Inception 3.0 so that it could recognize photographs of human bones. The system had already been trained to recognize objects in millions of photographs, but none of those objects were bones; he has since trained his version on more than 80,000 images of human bones. He is now working with a group called Countering Crime Online, which is using neural networks to track down images related to the illegal ivory trade and sex trafficking.

Dr. Crespo and Dr. Caspari said that the social sciences and humanities could benefit by incorporating the tools of information technology into their work. Their convolutional neural network was easy to use and freely available for anyone to modify to suit their own research needs. In the end, they said, scientific advances come down to two things.

“Innovation really happens at the intersections of established fields,” Dr. Caspari said. Dr. Crespo added: “Have a beer with your neighbor every once in a while.”