Machine Learning (ML) is reshaping archaeology, offering powerful tools for analyzing a wide range of data, from geospatial information and material artifact data to textual records. The rapid adoption of ML in archaeological research has transformed our ability to identify and interpret complex patterns. ML automates existing methods and introduces innovative approaches such as computer vision and big data analysis.

This TIFA serves as your gateway to understanding how ML can be practically applied in archaeology. Over the course of three immersive days, you will gain a comprehensive grasp of ML’s role in archaeology and acquire the skills needed to take advantage of its potential effectively. Join us on this transformative journey and unlock the full capabilities of ML in your archaeological research


  • Gain practical insights into the real-world applications of machine learning in archaeology, including a comprehensive understanding of the benefits and challenges involved.
  • Develop both theoretical and practical foundations in machine learning, covering essential workflow components and critical data considerations.
  • Learn to identify suitable scenarios for deploying machine learning techniques and select appropriate workflows to tackle archaeological research questions effectively.


  • Introduction to Machine Learning: Explore fundamental concepts and principles that underlie machine learning.
  • Applications of Machine Learning in Archaeology: Gain a broad overview of various use cases where ML has revolutionized archaeological research.
  • Types of Data in Archaeology: Discover the diverse data types used in archaeology and their integration with ML techniques.
  • Machine Learning Workflow: Understand the key components and steps involved in crafting an effective ML workflow.
  • Data Preprocessing: Learn the art of cleaning, formatting, and preparing archaeological data for meaningful analysis.
  • Supervised Learning: Delve into classification and regression techniques tailored for archaeological contexts.
  • Unsupervised Learning: Explore clustering and dimensionality reduction methods, uncovering hidden patterns within archaeological datasets.
  • Evaluation and Validation of ML Models: Master the art of assessing model performance and ensuring the reliability of results.
  • Addressing Potential Biases: Understand the ethical implications of ML and techniques to mitigate biases.
  • Case Studies: Dive into real-world examples showcasing successful ML applications in archaeological research.
  • Practical Hands-on Exercises: Apply machine learning algorithms to archaeological datasets and gain practical experience.
  • Resources and Further Education: Receive recommendations for additional learning and research opportunities.


Dr. Alex Brandsen‘s research interests bridge Archaeology and Computer Science, with a particular passion for creating practical tools to assist other archaeologists in their research. In his postdoc project, he employs text mining techniques and machine learning to extract hidden information from archaeological texts in multiple languages. This endeavor aims to develop an online tool that enables researchers to perform detailed and fine-grained searches across extensive archaeological literature. Alex is equally enthusiastic about teaching and has contributed to various courses in both the Faculty of Archaeology and LIACS, covering subjects ranging from databases to machine learning. He holds degrees in Archaeology (BA, Leiden, 2009) and Archaeological Information Systems (MSc, York, 2010). His journey in web development led him to work in the UK for seven years before returning to the Faculty of Archaeology in 2017 as a PhD candidate in Digital Archaeology. In 2021, he started the EXALT project, furthering his commitment to advancing archaeological research through computational tools and methods.
Prof. Dr. Björn Menze joined the Department of Quantitative Biomedicine as a Full Professor for Biomedical Image Analysis and Machine Learning in September 2020. His research lies at the intersection of biomedical image computing, machine learning, and medical imaging. His work focuses on transforming qualitative visual inspections of biomedical image data into quantitative descriptions and functional interpretations of disease processes. He utilizes models from biophysics, computational physiology, and machine learning with applications in clinical neuroimaging and tumor growth modeling. Prof. Menze also explores how these models can be applied to big databases to uncover correlations between model features and disease patterns on a population scale. His research contributes to improving the understanding of image-marker generating processes and personalized treatments in personalized medicine. Prof. Dr. Björn Menze has extended his computational expertise from biomedical domains to archaeology, notably in Near Eastern Archaeology. He has collaborated on projects that combined satellite imagery and computational methods to unearth ancient settlements and map long-term settlement patterns, particularly in Northern Mesopotamia and the Upper Khabur basin of northeastern Syria. Through these collaborations, Prof. Menze contributed to identifying over thousands of places of ancient and modern settlement, revealing insights into some of the earliest urban places in the Near East. His work has been recognized in various reputable publications including Geo Magazin, Spiegel, and Nature.

Approach and mode: 

This TIFA will combine theoretical lectures, as well as hands-on practical sessions which are pivotal to this workshop, ensuring a holistic learning experience. The emphasis on practical sessions represents a great opportunity for participants to apply learned concepts real-time, enhancing their comprehension and skills. It’s recommended for participants to have a foundational understanding or knowledge of programming syntax in Python or R, as the basics of these programming languages will not be covered during the workshop. Importantly, participants are required to bring along their laptops for the practical exercises, and they are welcome to discuss and review their own data with our instructors during the course.

Certificates of completion will be issued exclusively to those who attend the entire three-day workshop.

The course will take place only in person in the facilities of the University of Algarve, Faro, Portugal.

Suggested audience: 

The workshop is designed for archaeologists at all career stages, including master’s students, Ph.D. candidates, and postdoctoral researchers, who are interested in incorporating machine learning techniques into their archaeological research. It offers a specialized learning experience tailored to equip archaeologists with the skills needed to effectively utilize machine learning in their studies.

Number of participants:

Maximum 24 participants


Registration for this workshop entails a fee, with students being charged 150€ and researchers 200€. These fees contribute towards facilitating a conducive and enriching learning environment. All travel, accommodation, and subsistence costs are to be borne by the participants.

Interested individuals are required to fill in the form below, including a CV, by the deadline of the 17th of December 2023. In the event that we receive more than 24 applications, a selection process will ensue. Selected participants will be extended an invitation, while others will be placed on a waiting list, to be considered should spots become available.

Register here


Deadline for application: 17th December, 2023, 23:59 (WET)
Notification of acceptance and final program: January 2024
Start of the course: 5th of March 2024, 9AM.

Don’t miss this opportunity to unlock the potential of machine learning in your archaeological research. Apply now to secure your place in this practical-oriented workshop and work towards using data-driven methodologies to gain new archaeological insights.

For inquiries or more information, please contact gdevevey@ualg.pt