Agricultural terraces are among the most significant anthropogenic land modifications in the Mediterranean. They are constructed to reduce local slope gradients and facilitate farming by artificially increasing soil thickness. Terraces also reduce soil erosion and enable irrigation practices. Yet, if not maintained or abandoned, they become prone to piping, gully erosion, and landsliding. Nevertheless, incorporating these effects into large-scale hydrological, geomorphological, and agronomic research remains challenging due to limited information on terrace locations and characteristics.We aim to address this gap by presenting a new predominantly automatic approach for detecting and classifying terraced units on a large scale. This scalable tool utilizes freely available data: Google optical satellite imagery (≈2.1 m spatial resolution), ALOS Global DSM (30 m spatial resolution), and ESA WorldCover (10 m spatial resolution). Our study site, Cyprus, with an area of 9,250 km² has a long history of terraced agriculture driven by its rugged terrain. The island features terraces ranging from old, abandoned ones to newly constructed terraces using heavy machinery.The approach employs Object-Based Image Analysis (OBIA). First, images are segmented using SLIC (Simple Linear Iterative Clustering). These segments are populated with information from 22 derivative layers generated from the initial data. For each segment, 36 statistical parameters are calculated. The derived layers include slope, curvature, Gray-Level Co-Occurrence Matrix (GLCM) features, Canny edge detection results.To ensure robust classification, the data was split into tiles, with some used for training and others for validation to minimize spatial autocorrelation. The model was trained using AutoGluon, focusing on CatBoost and Neural Networks. The binary classification achieved a ROC-AUC value of 0.87 and a Matthews Correlation Coefficient (MCC) of 0.44. Subsequently, detected terraces were classified into three morpho-functional classes. Broad agricultural terraces were identified with high accuracy (0.84). Narrow agricultural terraces on steeper slopes with stone walls showed moderate performance (accuracy = 0.72). However, distinguishing narrow terraces built for reforestation from agricultural terraces in similar conditions proved challenging (accuracy = 0.46).Our results demonstrate the potential for developing detailed, large-scale terrace datasets. This, in turn, opens promising perspectives to better assess soil erosion and other geohydrological processes at such scale.

Copper was central to the Late Roman Cypriot economy, represented by large-scale production sites. This study examines often-overlooked small-scale mining by focusing on Pyrga in the Pouzis Valley, Southeast Cyprus. Surveys by the Hala Sultan Tekke Hinterland Survey Project (2021–ongoing) revealed dispersed slag heaps near potential church remains. Metal slag analysis reveals a consistent manganese-rich composition and low residual copper, suggesting controlled and efficient smelting. Viewed alongside the Codex Theodosianus and Codex Justinianus, regulating mining, taxation and landownership, and the proximity of churches to production sites, this raises the possibility that Pyrga’s production was part of a centrally organised network. This research examines how ecclesiastical institutions may have steered local economy, administration and taxation, and technological practices. This dual exploration of administration and technology deepens our understanding of the relationship between ecclesiastical power and the copper economy of Late Roman Cyprus.

Archaeological predictive modelling estimates where undiscovered sites are likely to occur by combining known locations with environmental, cultural, and geospatial variables. We address this challenge using a deep learning approach but must contend with structural label scarcity inherent to archaeology: positives are rare, and most locations are unlabeled. To address this, we adopt a semi-supervised, positive-unlabeled (PU) learning strategy, implemented as a semantic segmentation model and evaluated on two datasets covering a representative range of archaeological periods. Our approach employs dynamic pseudolabeling, refined with a Conditional Random Field (CRF) implemented via an RNN, increasing label confidence under severe class imbalance. On a geospatial dataset derived from a digital elevation model (DEM), our model performs on par with the state-of-the-art, LAMAP, while achieving higher Dice scores. On raw satellite imagery, assessed end-to-end with stratified k-fold cross-validation, it maintains performance and yields predictive surfaces with improved interpretability. Overall, our results indicate that semi-supervised learning offers a promising approach to identifying undiscovered sites across large, sparsely annotated landscapes.

While evidence of ancient place names is a crucial element for our understanding of the historical landscape, many of those toponyms, other than those of major urban centres, have often disappeared in the course of history. The traditional localization of one such ancient toponym, Moatra in the territory of Sagalassos, at the present-day village of Bereket in the central district of Burdur Province (SW Türkiye) has recently been questioned. Allegedly, the vicinity of the modern village presents insufficient remains to support an identification of an ancient settlement there during the Roman Imperial period and this caused scholars to look for its location elsewhere in the area. This article presents an overview of the archaeological evidence from the Bereket intramontane basin and combines it with other strands of evidence to contest this new localization and explain why Moatra could not have been situated anywhere else but at Bereket. These arguments are based on the combination of the results of past and ongoing archaeological, geomorphological and paleo-environmental research, as well as toponymic study. These data help to shed light on the long occupation of the area and clarify the somewhat exceptional nature of the settlement of Moatra within the territory of Sagalassos, providing an outstanding example of how different disciplines can contribute to our understanding of the ancient settlement landscape and the human-environment relationship in the Late Holocene.

Three decades of interdisciplinary research within the Sagalassos Archaeological Research Project has provided extensive archaeological, environmental and geoarchaeological datasets. This paper seeks to bring together these datasets to explore diachronic socio-ecological dynamics within the Sagalassos Study Area, SW Türkiye. For this, we will use the Adaptive Cycles and Resilience Theory framework to explore socio-cultural development during changing climatic and environmental conditions. The paper aims to serve as an in-depth case study of these frameworks, integrating archaeological and environmental data, which – despite the increasing popularity of resilience theory – remains underdeveloped within the field of archaeology, especially within Mediterranean and Anatolian archaeology. We will explore the utility of the adaptive cycle framework for reconstructing diachronic human-environment interactions through changing settlement patterns documented during surveys conducted by the Sagalassos Project. Critical phases within the settlement record can be identified during the last 8000 years including apparent periods of ‘rupture’ during the Middle Chalcolithic, Middle-Late Bronze Age, Hellenistic and Middle-Byzantine periods; representing times of serious upheaval in ‘normal’ cultural traditions and lifeways. The adaptive cycle framework will help distinguish between the effects of environmental changes and social dynamics, as well as their potential interrelations in causing long-term social transformation in the Sagalassos Study Area.

This chapter provides an overview of recent archaeological and palaeo-ecological research conducted within the study region of the ancient city of Sagalassos, Turkey. Recent findings reveal shifting patterns in land use and settlement within the territory, contemporary with the changes the city of Sagalassos underwent during the Late Antique and Byzantine ages (AD 300 to 1243). Land abandonment during the Byzantine Dark Ages was less absolute than previously assumed. Records show a shift from an intensively exploited countryside focussed on an urban community towards a self-sustained, village-oriented society. These changes are reflected in the natural landscape, vegetation becoming more open as crop cultivation gave way to pastoralism during the Byzantine Dark Ages, followed by a slight return to cereal cultivation and arboriculture during the Middle Byzantine period. Sediment and pollen records indicate that vegetation change coincided with changes in local and regional environmental conditions, although there is no evidence that climate change drove societal change.

As we stand on the precipice of unprecedented global challenges, understanding the deep-time patterns of sustainability and resilience is no longer just a scholarly endeavour but imperative for the future of our planet and its inhabitants. The collection of papers in this special issue brings together archaeologists, historians, and environmental scientists around four main topics: (1) social-ecological modelling, (2) long-term human-environment interactions, (3) modelling diachronic landscapes and (4) sustainability and resilience from past to future. Our aims are to come to a better understanding of socio-economic resilience and sustainability in past, present and future societies. Through interdisciplinary collaboration, we aim to forge new conceptual frameworks for understanding complex, long-term socio-ecological dynamics. Through the case studies, theoretical reflections and methodological innovations presented here, this special issue seeks to advance interdisciplinary scholarship on sustainability and resilience and offer fresh insights into the challenges and opportunities that lie ahead in building a sustainable future.

Past land-use reconstructions are a key tool for studying long-term human ecodynamics and addressing pressing questions about the origins and evolutionary dynamics of the Anthropocene. In particular, agricultural landcover reconstructions are vital for understanding long-term human-environment dynamics. Most past agricultural land-use models, however, rely heavily on modelling assumptions, make limited use of known archaeological site locations to constrain or inform their estimates and tend to be limited to general estimates of percentages of plant types within catchments around pollen trapping lakes. The lack of information outside catchment areas and low spatial resolution even within catchments constrain the utility of these models. To address this problem, we propose a new approach that combines archaeological predictive modelling with pollen-based agricultural landcover reconstructions to produce more accurate, spatially explicit past landcover estimates. Here, we present the results of a case study deploying the new approach to produce improved past landcover maps for a region in the Western Taurus Mountains, southwestern Turkey. The study area surrounds Sagalassos, an antique urban centre with a regional settlement history encompassing nine millennia. We produced five archaeological predictive models for the study region using the 'Locally Adaptive Models of Archaeological Potential' (LAMAP) method spanning the Hellenistic through Late Ottoman period. We then combined those predictive surfaces with 'Regional Estimates of VEgetation Abundance from Large Sites' (REVEALS) pollen landcover reconstructions for the same periods based on pollen from sediment cores extracted from three catchments within the study area. Lastly, we compared the resulting hybrid landcover models to the archaeological record using data not used to make the predictions. We found that the hybrid landcover model aligned very well with the known extents of agricultural land-use from the study area. These results indicate that the proposed approach is a viable way to combine pollen-based landcover models with archaeological data and produce more accurate, empirically-based landcover reconstructions reflecting real human activity in the past.

Contrary to the idiosyncratic "tell-type" urban settlements that epitomize Late Bronze Age societies in the eastern Mediterranean and the Near East, a handful of major urban settlements on Cyprus, such as Hala Sultan Tekke and Maroni, embodied a completely different notion of urban engineering. Instead of dense urban city centers where numerous residents resided close to each other, these "atypical" settlements were apparently organized with broad areas of open space between smaller occupational "clusters." By means of archaeological survey combined with a landscape archaeological approach, the Hala Sultan Tekke Hinterland Survey Project (HST-HASP) aims to (re)evaluate this unique type of spatial organization at the Late Bronze Age settlement at Dromolaxia-Vyzakia, as well as to reconstruct the long-term, multiperiod lifecycle of the settlement and its surrounding landscape. The project by the Vrije Universiteit Brussel aims to investigate the site's hinterland and its relation and position within the broader Tremithos Valley region.

While we know that the visualization of quantifiable uncertainty impacts the confidence in insights, little is known about whether the same is true for uncertainty that originates from aspects so inherent to the data that they can only be accounted for qualitatively. Being embedded within an archaeological project, we realized how assessing such qualitative uncertainty is crucial in gaining a holistic and accurate understanding of regional spatio-temporal patterns of human settlements over millennia. We therefore investigated the impact of visualizing qualitative implicit errors on the sense-making process via a probe that deliberately represented three distinct implicit errors, i.e., differing collection methods, subjectivity of data interpretations and assumptions on temporal continuity. By analyzing the interactions of 14 archaeologists with different levels of domain expertise, we discovered that novices became more actively aware of typically overlooked data issues and domain experts became more confident of the visualization itself. We observed how participants quoted social factors to alleviate some uncertainty, while in order to minimize it they requested additional contextual breadth or depth of the data. While our visualization did not alleviate all uncertainty, we recognized how it sparked reflective meta-insights regarding methodological directions of the data. We believe our findings inform future visualizations on how to handle the complexity of implicit errors for a range of user typologies and for highly data-critical application domains such as the digital humanities.

This chapter advances social metabolism as a suitable framework for interdisciplinary studies of human-environment interactions in the past. We apply this framework to the comparison of two case studies of environmental changes and societal responses in the area of Sagalassos (SW Turkey): the onset of the Beyşehir Occupation phase during first millennium BCE and the Medieval Climatic Anomaly at the start of the second millennium AD. Both periods are characterised by changing environmental conditions that required societies to alter subsistence strategies, economic system and social organisation. We show how local communities responded to the challenges and opportunities offered by changing circumstances in various ways. When possible they created stable environments that served as niches of habitation and provided for all local needs in energy and resources, while also accounting for the trade-off effects between the need for increased security versus exploiting the available environmental potential.

Kurucay Hoyuk can be considered a key site for our understanding of Late Prehistory in southwest Turkey and above all, the poorly known Late Chalcolithic (4200-3100 B.C.). Until now, limited research has been conducted on the relationship between the excavated site and its surrounding. This article discusses the Late Chalcolithic results of an integrated survey in the vicinity of Kurucay Hoyuk in the Burdur Plain. Drawing upon these results, this paper illustrates that the site was far from an isolated feature during the 4th millennium B.C. The picture that emerges is one of a differentiated settlement system consisting of both larger hoyuk/tell settlements (like Kurucay Koyuk) and smaller sized, possibly short-lived, flat settlements. These results are further contextualized within the developments that took place in the region during the Chalcolithic, which seem to have opened the door for communities to become more complex during the Early Bronze Age.

The western Taurus mountains, southwest Turkey, comprise a diverse set of landscape zones that are characterized by great altitude variations. This article focuses on the agricultural so-called marginal highlands within this mountainous region. Large parts of the uplands are labeled "marginal" nowadays as they are not regarded as highly productive in terms of agricultural output or permanent occupation. Three decades of interdisciplinary research within the Sagalassos Archaeological Research Project (KU Leuven) have provided an enormous amount of archaeological, bioarchaeological, and geoarchaeological data-sets that will be brought together in this article to explore diachronic patterns in human-environmental interactions within these areas. The study demonstrates not only the archaeological value of a highland area, but its vulnerability for human impact as well. The changing environments both naturally and sociopolitically favored a more resilient behavior of the human groups within the highlands.

It has been argued that the Late Neolithic (6500–6100 BCE) settlement pattern in southwestern Turkey is dominated by small farming settlements (mound sites/höyüks) lo- cated in the most optimal zones of the landscape, that is, it exhibited a nucleated settlement pattern. On the basis of new intensive field-walking data from the Burdur Plain, which is known for the Neolithic sites of Hacılar and Kuruçay Höyük, it was possible to test this sup- position and examine to what extent this pattern is biased by research methods rather than reflecting ancient realia. However, the survey failed to revealed any new Neolithic sites, thus largely corroborating the nucleated settlement pattern. These results are in contrast with the succeeding Early Chalcolithic (6100–5600 BCE) period where a number of new sites have been detected that indicate a more dispersed settlement pattern. I argue that the socioeconomic organization of the Neolithic community itself may explain this absence of a dispersed and differentiated settlement pattern during the LN in southwestern Turkey. Considering the developments taking place around the second half of the seventh millen- nium BCE, I argue that this period in southwestern Turkey is a transitional one, during which the Neolithic way of life became established in the region.