Programme

Agenda

Tuesday, 13 April 2027

8:45-10:00	Workshop session 0: Gentle introduction in the archaeological interpretation of lidar derived data, part 1
10:00-10:30	break
10:30-11:45	Workshop session 0: Gentle introduction in the archaeological interpretation of lidar derived data, part 2
12:00-13:15	lunch
13:30-14:00	Introduction to the meeting
14:00-16:00	Keynote 1 by Martin Dobiaš and Tibor Lieskovský From point clouds to mobile applications Keynote 2 by Dimitrij Mlekuž What became of the mess? Reflections on lidar and archaeological landscapes Keynote 3 by Anthony Corns ??AI in landscape archaeology??
16:00-17:00	coffee break and poster session
17:00-18:30	Invited lecture 1 by Elise Fovet and dave Cowley Integrating ALS in a larger structured information flow Invited lecture 2 by Žiga Kokalj Cross-border airborne laser scanning data Invited lecture 3 by Sara Popović Open ALS data in private archaeology: between making a living and scientific curiosity
19:00-20:00	dinner

Wednesday, 14 April 2027

7:00-8:15	breakfast
8:45-10:00	Introductory discussion about workshops (installing the software/data session)
10:00-10:30	coffee break
10:30-12:30	Workshop session 1
12:30-13:30	lunch
13:30-15:30	Workshop session 2
16:00-19:00	Field trip afternoon
19:30-21:00	International dinner

Thursday, 15 April 2027

7:00-8:15	breakfast
8:45-10:45	Workshop session 3
10:45-11:15	coffee break
11:15-12:30	Round table discussion and closing session
12:30-13:30	lunch

Workshops

Gentle introduction in the archaeological interpretation of airborne lidar derived data

Rebecca Bennett, Luka Škerjanec
You have processed your airborne laser scanning (ALS) data and produced a series of beautiful terrain visualisations – but what comes next? This introductory workshop focuses on the process of identifying and interpreting potential archaeological features in lidar-derived data. We will consider how to move from recognising patterns in terrain visualisations to assessing them as possible traces of past human activity, treating interpretation as an iterative process shaped by observation, comparison, context, and uncertainty.
The workshop will introduce the principles of systematic interpretative mapping, discuss the strengths and limitations of different visualisation techniques, and emphasise the importance of archaeological and landscape context. Particular attention will be given to common interpretative pitfalls and “false friends”: natural landforms, recent landscape modifications, and other features that can easily be mistaken for archaeological remains. We will also explore how to approach uncertain interpretations and why critical observation is essential when interpreting past landscapes from ALS data.

From a point cloud to a visualisation on a mobile phone

Tibor Lieskovsky, Mihaela Prišťáková, Barbora Weissova, Katrin Dornhofer
In this workshop we process a lidar point cloud step by step in QGIS, Mergin Maps and QField and end with a visualisation that can be opened on a mobile phone in the field. We start with simple point cloud operations such as clipping and merging and a look at ground classification, then build a DEM from the chosen point classes. From the DEM we derive standard archaeological visualisations, examine the terrain with profiles and volume calculations, and blend the layers into a single interpretative image. Finally, we optimise and compress the outputs so that they load quickly on a phone or tablet and can be used for orientation and ground truthing. The working material comes from the hillfort of Kočovce-Skalka, which we will visit during the excursion: a UAV survey of the site and the corresponding tile of the Slovak national ALS dataset. Working with both allows us to compare the two sources and to show where lidar reaches its limits, in steep terrain and among ruined architecture, how data volume becomes a practical problem, and what can be done about both. No prior experience with point clouds is needed; participants should bring a laptop with a current QGIS installed.

How to prepare and use ML-ready archaeological data

Nejc Čož, Žiga Kokalj, Jakub Šperka, Susan Curran, Anthony Corns
The rapid development of image analysis techniques and the increasing availability of high-quality airborne laser scanning data (ALS, lidar) are encouraging the use of machine learning in archaeology. The ADAF tool consists of two Jupyter notebooks, one for training (creating specific machine learning models) and one for automatic recognition of archaeological features. While the training part is time-consuming and requires suitable hardware, the recognition part can be done on any modern laptop. This workshop aims to provide participants with hands-on experience with the software and enable them to use it independently for their own projects. We will cover the basics of deep learning in archaeology, the installation, explain all components of the training part and run the detection process. The currently implemented model is optimised to detect three classes of Irish archaeology (barrows, enclosures, ringforts), but you can also input your own model. The software requires minimal interaction and no prior knowledge of machine learning techniques, which greatly increases its accessibility to the archaeological community. The software is tested to run on Windows.

Interpretative mapping – a collaborative workshop

Rebecca Bennet, Luka Škerjanec
Archaeological interpretation is a skill best developed through practice, discussion, and collaboration. In this workshop, participants will put their interpretative skills to the test by working in small groups to explore airborne laser scanning (ALS) visualisations of selected landscapes. Each group will identify and map potential archaeological features, discuss possible interpretations, and consider alternative explanations for ambiguous landscape forms. Groups will then present their findings to the other participants, sharing their observations, reasoning, and uncertainties. Through comparison and collective discussion, we will explore how different perspectives can influence archaeological interpretation and how collaborative approaches can improve the quality and consistency of interpretative mapping. The emphasis is not on finding a single correct answer, but on learning through observation, critical thinking, and the exchange of ideas.

Presentations

KEYNOTE 1
From point clouds to mobile applications

Martin Dobiaš and Tibor Lieskovský
Airborne laser scanning data are widely used in archaeology and heritage management, but the path from a delivered point cloud to a verified observation in the field remains demanding. Classification, DEM generation and visualisation are done at a workstation, with tools ranging from expensive commercial packages to libraries such as PDAL that are powerful but hard for non-specialists to maintain. This is not specific to archaeology, and it is why QGIS developers ran three community-funded campaigns in 2020–2022 to bring point clouds into QGIS. The first part of the presentation, given by one of the QGIS core developers, follows this work from the first native point cloud layer through COPC support, 2D/3D visualisation and profiles, to PDAL-based processing and classification and editing of points. The second part moves the results out of the office: with cloud-optimised rasters and open-source mobile applications such as Mergin Maps and QField, DEM derivatives can be viewed on a phone or tablet. Examples from heritage protection in Slovakia, from castle ruins to a national ALS dataset, show how this supports orientation and ground truthing in the field.

KEYNOTE 2
What became of the mess? Reflections on lidar and archaeological landscapes

Dimitrij Mlekuž
What happens when we can see more of the landscape than we know how to make sense of? Airborne laser scanning has made landscapes wonderfully, sometimes uncomfortably, crowded. Traces overlap, interrupt one another, disappear and return. What once seemed empty becomes full; what seemed familiar becomes strange. The idea of “messy landscapes” was an attempt to stay with this complexity, to ask what it might do to landscape archaeology. Looking back, where have we arrived? Have we changed our understanding of landscapes as much as we have changed our ability to see them? What happens to the mess when we turn it into mapped features, classifications and chronologies? How much uncertainty survives the journey from a lidar data visualisation to an archaeological account? And what remains? What escapes a terrain model, resists recognition, or falls between our categories? Which questions have become easier to answer, and which have quietly disappeared from view? Returning to some early promises and provocations, this talk asks what we have learned to see, what we have learned to overlook, and what an archaeology of messy landscapes might still become.

KEYNOTE 3
??AI in landscape archaeology??

Anthony Corns

INVITED LECTURE 1
Integrating ALS in a larger structured information flow

Elise Fovet, Dave Cowley
At one level integrating airborne laser scanning (ALS, lidar) outputs into knowledge-creation workflows is a simple matter of loading layers and data – putting it all in GIS! This supports the interpretation of multiple datasets in a common spatial framework, with the facility to compare ALS data, aerial imagery, historic maps and a range of other data. However, the applications of ALS data depend on many factors, such as present day and historical land use and the purpose at hand. And, integrating datasets is not necessarily the same as integrated knowledge-creation. This presentation reviews examples of how multiple datasets, including ALS derivatives, may be assimilated into knowledge creation workflows. This includes the practical issues of creating metadata for accountable information, but also considering where certainty in interpretation is sought, and how emphasis is given to different data. Moreover, it will explore how geospatial tools can be leveraged to analyse spatio-temporal relationships, enabling to uncover patterns, trends, and interactions across time and space. By creating analytical models, these tools not only facilitate a deeper understanding of landscape dynamics but also help decipher the complexities of particular landscapes.

INVITED LECTURE 2
Cross-border airborne laser scanning data

Žiga Kokalj
We will discuss four types of boundaries. The first is the boundary of visibility, which airborne laser scanning (ALS, lidar) has already shifted considerably: archaeological features can now be detected even in forested, impassable and remote environments. The second is the geographical boundary. Lidar data acquisition is most often constrained by modern administrative boundaries, making it difficult to study historically connected landscapes. The third is the boundary of interoperability. National or regional ALS datasets differ in terms of their characteristics and acquisition times, derived elevation models, file formats, licenses, and access methods and restrictions. The nominal openness of data therefore does not necessarily translate into cross-border usability. The fourth is the boundary of accessibility. Open data are not necessarily easy to obtain, and accessible data are not necessarily ready for practical use. A published point cloud may still mean terabytes of data, demanding and time-consuming processing, as well as specialised expertise, software, and hardware. For many archaeological tasks, high-quality elevation models and analytical visualisations, ready for interpretation, are therefore often more valuable.

INVITED LECTURE 3
Open ALS data in private archaeology: between making a living and scientific curiosity

Sara Popović
What does open ALS data mean for an archaeologist running a small business? Drawing on experience from an independent archaeological practice in Croatia, this talk explores how access to data has shaped both commissioned work and research pursued out of scientific curiosity. Examples from landscape interpretation, including Roman land divisions, illustrate the opportunities open data creates for professional services and independent discoveries. They also raise practical questions about the time and expertise required to turn accessible data into archaeological knowledge, and the sometimes blurred boundaries between paid work and research undertaken in supposedly free time. Through a personal account of these overlapping activities, the talk considers how open ALS data supports a livelihood, fuels research, and creates an ever-growing list of landscapes to investigate.