Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcity

2025-10-19

AI Summary

To address the challenges of scarce positive samples and large unlabeled regions in archaeological site prediction, this paper proposes a semi-supervised Positive-Unlabeled (PU) learning framework. Methodologically, it integrates a semantic segmentation backbone, a dynamic pseudo-labeling strategy, and a CRF-RNN joint optimization module, enabling end-to-end training on digital elevation models (DEM) and multi-source satellite imagery to enhance pseudo-label confidence and spatial consistency under extreme class imbalance. The key contribution lies in unifying local spatial constraints modeled by Conditional Random Fields (CRFs) with long-range dependencies captured by Recurrent Neural Networks (RNNs), thereby improving prediction interpretability. Experiments demonstrate that our method achieves a higher Dice score than LAMAP on DEM data and maintains robust performance across hierarchical cross-validation on satellite imagery, significantly outperforming baseline approaches.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

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.

Problem

• Addressing archaeological site discovery under severe label scarcity
• Using semi-supervised pseudolabeling for rare positive site identification
• Improving predictive performance on geospatial and satellite imagery data

Innovation

• Semi-supervised positive-unlabeled learning for archaeology
• Dynamic pseudolabeling with CRF-RNN refinement
• Semantic segmentation on DEM and satellite imagery