Learning from the Rare: Overcoming Class Imbalance in Archaeological Object Detection with Boosting Methods

Detecting surface potsherds using low-altitude remote sensing is challenging due to severe class imbalance and limited training data. This study develops and validates a semi-automatic detection methodology that adapts threshold-optimized boosting classifiers (AdaBoost, XGBoost) to maximize ceramic detection recall under extreme class imbalance in the Western Megaris archeological landscape, Greece. Models were trained on only 15% of the available data to simulate realistic field conditions. Evaluation emphasized recall-oriented metrics (precision, recall, F1-score, AUC) for the minority class, addressing the accuracy paradox where high overall accuracy masks poor rare-class performance. Threshold optimization enabled AdaBoost and XGBoost to achieve substantially improved recall compared to baseline methods, with detection-to-ground-truth ratios of 2.5 and 3.2, respectively, reflecting deliberate prioritization of recall over precision for exploratory survey purposes. The results demonstrate that this methodological framework provides archeologically interpretable screening tools for identifying high-probability ceramic locations, supporting more efficient field survey design and heritage documentation workflows in Mediterranean landscapes.