{"id":14481,"date":"2024-10-13T10:14:37","date_gmt":"2024-10-13T10:14:37","guid":{"rendered":"https:\/\/dsrc.haifa.ac.il\/?p=14481"},"modified":"2025-04-06T16:18:11","modified_gmt":"2025-04-06T16:18:11","slug":"when-the-past-meets-the-future-determining-origins-of-ancient-metal-objects-using-a-machine-learning-approach","status":"publish","type":"post","link":"https:\/\/dsrc.haifa.ac.il\/?p=14481","title":{"rendered":"When the past meets the future: Determining Origins of Ancient Metal Objects using a Machine Learning Approach"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

When the past meets the future: \nDetermining Origins of Ancient Metal Objects using a Machine Learning Approach \n\n<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Tzilla Eshel - Department of Archaeology
Tsvi Kuflik - Department of Information Systems<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Machine Learning
Algorithms<\/strong>
<\/strong><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Digital Humanities
<\/strong><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

SEED Grant 2023<\/strong><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

\"\"<\/p>\n

For over 6,000 years, metals play an important role in human development, having a longlasting effect on wealth, trade, technology and wars. Today, geochemists can trace the origin of some of these metals, and identify from which ore they were produced. This enables archaeologists to reconstruct ancient trade routes and economic developments. The method is based on the isotopic ratios of lead in the metal. One of the problems is that there is a large amount of data of ores, with some overlaps that make it difficult to differentiate between the ores and associate between artifacts and ores. We address this challenge for the first time by applying machine learning algorithms. By leveraging large datasets of isotopic information from known ore deposits, machine learning algorithms systematically analyze patterns and relationships within the data. This approach helps identify subtle variations in isotopic compositions that may indicate specific metal sources, making the results independent of human interpretation. Unlike existing methods that rely on visual comparisons and do not account for outliers, our approach is more systematic and objective. It provides more accurate and efficient methods for tracing the origins of ancient metal objects, significantly reducing overlaps between ores and offering new insights into the economic and cultural dynamics of past civilizations.<\/p>\n

Dr. Tzilla Eshel<\/a><\/span><\/strong> is an Archaeometallurgist at the School of Archaeology and Maritime Cultures at the University of Haifa. She studies the origin of silver and its use as pre-monetary currency. Dr. Eshel co-heads the excavations at el-Ahwat, a site with evidence of metalworking from the Early Iron Age. Lead Isotope analysis is a key tool in her work, enabling to reconstruct metal-trade networks.<\/p>\n

Prof. Tsvi Kuflik<\/span>\u00a0<\/a> is a professor of information systems at the Information Systems department. His main research area is intelligent user interfaces, but he works also on related areas including user modeling, recommender systems and explainable AI. In addition, Prof. Kuflik collaborates in recent years on research related to “Digital Humanities” where state of the art machine learning techniques are applied for research in the humanities and the current research is a good example where supervised machine learning techniques are applied in archaeology \u2013 aiming to identify the source of metallic object based on their content of lead isotopes.<\/p>\n

Evgeny Shnyr is a Master’s student in the Information Systems department, currently working on his thesis under the supervision of Dr. Tzilla Eshel and Prof. Tsvi Kuflik. His research, combining Dr. Eshel’s expertise in archaeology and Prof. Kuflik’s knowledge of machine learning, focuses on applying advanced algorithms to improve the provenance of metals by enhancing lead isotope analysis. Utilizing large datasets of isotopic information from known ore deposits, this approach identifies subtle variations in isotopic compositions that traditional methods might overlook. This reduces overlaps between ores and provides new insights into the economic and cultural dynamics of past civilizations, representing a pioneering effort in integrating advanced data analysis with archaeological science.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

\"\"<\/p>\n

For over 6,000 years, metals play an important role in human development, having a longlasting effect on wealth, trade, technology and wars. Today, geochemists can trace the origin of some of these metals, and identify from which ore they were produced. This enables archaeologists to reconstruct ancient trade routes and economic developments. The method is based on the isotopic ratios of lead in the metal. One of the problems is that there is a large amount of data of ores, with some overlaps that make it difficult to differentiate between the ores and associate between artifacts and ores. We address this challenge for the first time by applying machine learning algorithms. By leveraging large datasets of isotopic information from known ore deposits, machine learning algorithms systematically analyze patterns and relationships within the data. This approach helps identify subtle variations in isotopic compositions that may indicate specific metal sources, making the results independent of human interpretation. Unlike existing methods that rely on visual comparisons and do not account for outliers, our approach is more systematic and objective. It provides more accurate and efficient methods for tracing the origins of ancient metal objects, significantly reducing overlaps between ores and offering new insights into the economic and cultural dynamics of past civilizations.<\/p>\n

Dr. Tzilla Eshel<\/a><\/span><\/strong> is an Archaeometallurgist at the School of Archaeology and Maritime Cultures at the University of Haifa. She studies the origin of silver and its use as pre-monetary currency. Dr. Eshel co-heads the excavations at el-Ahwat, a site with evidence of metalworking from the Early Iron Age. Lead Isotope analysis is a key tool in her work, enabling to reconstruct metal-trade networks.<\/p>\n

Prof. Tsvi Kuflik<\/span>\u00a0<\/a> is a professor of information systems at the Information Systems department. His main research area is intelligent user interfaces, but he works also on related areas including user modeling, recommender systems and explainable AI. In addition, Prof. Kuflik collaborates in recent years on research related to “Digital Humanities” where state of the art machine learning techniques are applied for research in the humanities and the current research is a good example where supervised machine learning techniques are applied in archaeology \u2013 aiming to identify the source of metallic object based on their content of lead isotopes.<\/p>\n

Evgeny Shnyr is a Master’s student in the Information Systems department, currently working on his thesis under the supervision of Dr. Tzilla Eshel and Prof. Tsvi Kuflik. His research, combining Dr. Eshel’s expertise in archaeology and Prof. Kuflik’s knowledge of machine learning, focuses on applying advanced algorithms to improve the provenance of metals by enhancing lead isotope analysis. Utilizing large datasets of isotopic information from known ore deposits, this approach identifies subtle variations in isotopic compositions that traditional methods might overlook. This reduces overlaps between ores and provides new insights into the economic and cultural dynamics of past civilizations, representing a pioneering effort in integrating advanced data analysis with archaeological science.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Tzilla Eshel
\nTsvi Kuflik<\/p>\n","protected":false},"author":93,"featured_media":14483,"comment_status":"open","ping_status":"open","sticky":false,"template":"elementor_header_footer","format":"standard","meta":{"_acf_changed":false,"_eb_attr":"","footnotes":""},"categories":[88,29,131,70,103,64,23,81],"tags":[37,46,47],"class_list":["post-14481","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-88","category-algorithms","category-archaeology","category-digital-humanities","category-information-systems","category-machine-learning","category-research-blog","category-seed","tag-algorithms","tag-artificial-intelligence","tag-data-mining","entry","has-media"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t