An Explorative Application of Random Forest Algorithm for Archaeological Predictive Modeling. A Swiss Case Study

The present work proposes an innovative approach to surveys and demonstrates the effectiveness of bringing together traditional archaeological questions, such as the exploration and the analysis of settlement patterns, with the most innovative technologies related to Machine Learning. Namely, we applied Random Forest, an ensemble learning method based on decision trees, to perform archaeological predictive modeling (APM) for the Canton of Zurich, in Switzerland. This was done based on a dataset of known archaeological sites dating back to the Roman Age. The APM represents an automated decision-making and probabilistic reasoning tool that is relevant for archaeological risk assessment and cultural heritage management. Machine learning-based approaches can learn from data and make predictions, starting from the acquired knowledge, through the modeling of the hidden relationships between a set of observations, representing the dependent variable (i.e. the archeological sites), and the independent variables (i.e. the geo-environmental features prone to influence the site locations). The main objective of the present study is to assess the spatial probability of presence for Roman settlements within the study area. As results, we produced: 1) a probability map, expressing the likelihood of finding a Roman site at different locations; 2) the importance ranking of the geo-environmental features influencing the presence of the archeological sites. These outputs in our results are of paramount importance, not only in verifying the reliability of the data, but also in stimulating experts in different ways. Also, these results help evaluate the benefits and constraints of using such innovative techniques and, ultimately, help explore the performance of machine learning-based models in processing archaeological information.

• Publication year

  2021

• Venue

  Journal of Computer Applications in Archaeology

• Publication date

  2021-05-21

• Fields of study

  Computer Science, History

• Identifiers
  DOI 10.5334/JCAA.71
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Potential of deep learning segmentation for the extraction of archaeological features from historical map series

  2021cited by this paper
• Algorithmic Classification and Statistical Modelling of Coastal Settlement Patterns in Mesolithic South-Eastern Norway

  2020cited by this paper
• Predictive Spatial Modelling

  2020cited by this paper
• Automated detection of archaeological mounds using machine-learning classification of multisensor and multitemporal satellite data

  2020cited by this paper
• A Machine Learning-Based Approach for Wildfire Susceptibility Mapping. The Case Study of the Liguria Region in Italy

  2020cited by this paper
• A brave new world for archaeological survey: Automated machine learning-based potsherd detection using high-resolution drone imagery

  2019cited by this paper
• Convolutional neural networks for archaeological site detection – Finding “princely” tombs

  2019cited by this paper
• Natural risk assessment and mitigation of cultural heritage sites in North‐eastern Romania (Valea Oii river basin)

  2019cited by this paper
• Archaeology that counts: International colloquium on digital archaeology

  2019cited by this paper
• Explorative Spatial Analysis of Neandertal Sites using Terrain Analysis and Stochastic Environmental Modelling

  2018cited by this paper
• Wildfire susceptibility mapping: Deterministic vs. stochastic approaches

  2018cited by this paper
• Europe’s lost forests: a pollen-based synthesis for the last 11,000 years

  2018cited by this paper
• Predictive modeling for archaeological site locations: Comparing logistic regression and maximal entropy in north Israel and north-east China

  2018cited by this paper
• A novel ensemble modeling approach for the spatial prediction of tropical forest fire susceptibility using LogitBoost machine learning classifier and multi-source geospatial data

  2018cited by this paper
• blockCV: an R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models

  2018cited by this paper
• A review of statistically-based landslide susceptibility models

  2018cited by this paper
• Data-driven mapping of the potential mountain permafrost distribution.

  2017cited by this paper
• Evaluating Mesolithic settlement patterns in mountain environments (Dolomites, Eastern Italian Alps): The role of research biases and locational strategies

  2017cited by this paper
• Evaluation of digital soil mapping approaches with large sets of environmental covariates

  2017cited by this paper
• Mapping landslide susceptibility using data-driven methods.

  2017cited by this paper
• Quantitative Methods in Archaeology Using R

  2017cited by this paper
• Predictivity – postdictivity: a theoretical framework

  2016cited by this paper
• Developing a Collaborative Strategy to Manage and Preserve Cultural Heritage During the Libyan Conflict. The Case of the Gebel Nāfusa

  2016cited by this paper
• A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India)

  2016cited by this paper
• Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling

  2015cited by this paper
• A supervised machine-learning approach towards geochemical predictive modelling in archaeology

  2015cited by this paper
• Predictive modeling for preventive Archaeology: overview and case study

  2014cited by this paper
• Combining glaciological and archaeological methods for gauging glacial archaeological potential

  2014cited by this paper
• R: A language and environment for statistical computing.

  2014cited by this paper
• Un modello speditivo per la carta del Rischio Relativo nei Beni Culturali

  2014cited by this paper
• Identifying the origin of groundwater samples in a multi-layer aquifer system with Random Forest classification

  2013cited by this paper
• Archäologische Kulturgüter in der Schweiz - eine Ressource im Spannungsfeld von Zersiedlung und Verdichtung

  2013cited by this paper
• L'archéologie, une affaire publique: les enjeux de la réglementation et du financement

  2013cited by this paper
• Enhanced Archaeological Predictive Modelling in Space Archaeology

  2013cited by this paper
• An ethnoarchaeological inductive model for predicting archaeological site location: A case-study of pastoral settlement patterns in the Val di Fiemme and Val di Sole (Trentino, Italian Alps)

  2013cited by this paper
• Qualitative Landscape Theories and Archaeological Predictive Modelling—A Journey Through No Man’s Land?

  2012cited by this paper
• Support vector machine for multi-classification of mineral prospectivity areas

  2012cited by this paper
• Integration of various geophysical data with geological and geochemical data to determine additional drilling for copper exploration

  2012cited by this paper
• Integrating Archaeological Theory and Predictive Modeling: a Live Report from the Scene

  2012cited by this paper
• MAPPA Project. Methodologies Applied to Archaeological Potential Predictivity

  2011cited by this paper
• Framing the Early Middle Ages Europe and the Mediterranean, 400-800

  2011cited by this paper
• A predictive model of archaeological potential: An example from northwestern Belize

  2009cited by this paper
• The golden years for mathematics and computers in archaeology (1965-1985)

  2009cited by this paper
• Modeling Settlement Patterns of the Late Classic Maya Civilization with Bayesian Methods and Geographic Information Systems

  2009cited by this paper
• Geographic information systems in archaeological analysis : a predictive model in the detection of rural Roman villae

  2009cited by this paper
• Archaeological predictive models for the Elbe valley around Dresden, Saxony, Germany

  2008cited by this paper
• Confidence Maps: a Tool to Evaluate Archaeological Data’s Relevance in Spatial Analysis

  2008cited by this paper
• Mathematics and Archaeology

  2008cited by this paper
• Classification and Regression by randomForest

  2007cited by this paper
• Case Studies in Archaeological Predictive Modeling

  2007cited by this paper
• Diagnosis of Diabetic Retinopathy

  2006cited by this paper
• Framing the early middle ages. Europe and the Mediterranean, 400–800 – Chris Wickham

  2006cited by this paper
• GIS based models and estimation methods for the probability of archaeological site location

  2006cited by this paper
• Predictive Modelling for Archaeological Heritage Management: a research agenda

  2005cited by this paper
• Applied Logistic Regression

  2002influential reference
• Soil Limitations to Agrarian Land Production in Premodern Iceland

  2002cited by this paper
• Autoroutes et archéologie en Suisse

  2002cited by this paper
• Practical Applications of GIS for Archaeologists: A Predictive Modelling Toolkit

  1999cited by this paper
• Classification and regression

  1997cited by this paper
• Beyond the Map

  1996cited by this paper
• A Machine Learning-Based Approach to

  year unknowncited by this paper

• A reconstruction of the Indigenous maize farming niche of Utah

  2026cites this paper
• A comparative analysis of stone- and earth-wall settlement locations of the Lower Xiajiadian Culture in Aohan Banner, China

  2025cites this paper
• Machine learning applications in archaeological practices: a review

  2025cites this paper
• Understanding the spread of agriculture in the Western Mediterranean (6th-3rd millennia BC) with Machine Learning tools

  2025cites this paper
• Probabilistic Models for Predicting Archaeological Site Locations in Marj Bisri (Southern Lebanon): Comparing Frequency Ratio and Shannon’s Entropy

  2025cites this paper
• Home is where my villa is: a machine learning-based predictive suitability map for Roman features in Northern Noricum (ca. 50–500 CE/Lower Austria/AUT)

  2025cites this paper
• Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcity

  2025cites this paper
• Predictive Modeling for Targeted Archaeological Survey of Arsacid Period Sites in the Iranian Borderland Region of the Araxes River Valley

  2025cites this paper
• Maximum entropy and GIS: An approach to assessing the settlement pattern of the Ninevite 5 culture (3000–2500 BCE) in the Upper Great Zab region (Erbil Province, Kurdistan region of Iraq)

  2025cites this paper
• Explainable artificial intelligence with negative sample optimization for archaeological site prediction in Surkhandarya Uzbekistan

  2025cites this paper
• An Analysis of Research Trends for Using Artificial Intelligence in Cultural Heritage

  2024cites this paper
• VNIR–SWIR reflectance spectroscopy as a nondestructive technique for compositional determination of archaeological talc samples with a machine learning approach

  2024cites this paper
• Predictive modeling in geoarchaeology: An evaluation of machine learning algorithms and topographic variables on the Serranópolis City - Brazil

  2024cites this paper
• Preserving Sculptural Heritage in the Era of Digital Transformation: Methods and Challenges of 3D Art Assessment

  2024cites this paper
• Machine Learning-Driven Archaeological Site Prediction in the Central Part of Jharkhand, India Using Multi-parametric Geospatial Data

  2024cites this paper
• Modeling the paths of ethno-political traditions and building cultural routes by means of ethnodesign and GIS

  2024cites this paper
• A multi-method approach with machine learning to evaluating the distribution and intensity of prehistoric land use in Eastern Iberia

  2023cites this paper
• Open-Access Archaeological Predictive Modeling Using Zonal Statistics: A Case Study from Zanzibar, Tanzania

  2023cites this paper
• A prediction model for Xiangyang Neolithic sites based on a random forest algorithm

  2023cites this paper
• Discovering the Ancient Tomb under the Forest Using Machine Learning with Timing-Series Features of Sentinel Images: Taking Baling Mountain in Jingzhou as an Example

  2023cites this paper
• Material Culture Studies in the Age of Big Data: Digital Excavation of Homemade Face-Mask Production during the COVID-19 Pandemic

  2022cites this paper