Archaeology
Geospatial AI and AutoML in Archaeology: Detecting Stone Walling in Kweneng, South Africa
- AI in archaeology
- GeoAI
- AutoML research
- MLJAR AutoML
- mljar-supervised
- archaeological site prediction
- stone walling detection
- Kweneng
- LiDAR archaeology
- remote sensing
- ArcGIS Pro GeoAI
- LightGBM
- CatBoost
- XGBoost
- cultural heritage AI
MLJAR tools were used in the following publication.
Automating Archaeological Discovery: Assessing Geospatial Artificial Intelligence (GeoAI) Tools for Stone Wall Identification in Kweneng, South Africa
Mncedisi J. Siteleki
School of Architecture and Planning, University of the Witwatersrand, Johannesburg, South Africa
This research demonstrates how Geospatial Artificial Intelligence (GeoAI), Automated Machine Learning (AutoML), and remote sensing can support archaeological site discovery. The study applies AutoML tools in ArcGIS Pro, based on the open-source mljar-supervised implementation, to identify stone walling in Kweneng, a Late Iron Age urban settlement in South Africa. Using LiDAR-derived spatial covariates such as elevation, aspect, and slope, the research compares multiple machine learning algorithms and AutoML modes, including LightGBM, XGBoost, CatBoost, random forest, extra trees, decision trees, and linear models. The results show that LightGBM achieved the strongest performance for detecting stone-walled features, while elevation was the most important spatial factor for prediction. This case study illustrates how MLJAR AutoML and GeoAI workflows can accelerate archaeological discovery, improve large-scale landscape analysis, and make machine learning methods more accessible for cultural heritage and computational archaeology.
Archaeometry • April 8, 2026
Research Domains
Explore peer-reviewed and applied machine learning studies across diverse domains, including healthcare analytics, financial modeling, manufacturing optimization, and structured data classification problems.
Why Researchers and ML Engineers Choose MLJAR Studio
A private, AI-powered Python notebook designed for reproducible machine learning experiments, structured benchmarking, and applied research workflows - fully under your control.
Reproducible Machine Learning Experiments
Design structured pipelines, save experiment runs, and compare results across iterations with full transparency. Every validation setup, hyperparameter configuration, and model benchmark is recorded - making your research repeatable and defensible.
Local-First Execution & Data Control
Run all workflows directly on your machine. Sensitive datasets remain private, with no mandatory cloud uploads or external AI services required. Maintain full control over runtime environments and compliance requirements.
Autonomous Model Benchmarking & Optimization
Automatically compare candidate models, perform cross-validation, and run hyperparameter optimization while retaining full visibility into generated Python code and evaluation metrics. Accelerate experimentation without sacrificing methodological rigor.
Build Research-Grade ML Workflows Locally
Run automated model benchmarking, hyperparameter optimization, and autonomous experiments while keeping full control over your data.