Uporaba učenja s prenosom znanja za medregionalno kartiranje poljščin

Spatial Transfer Learning for Cross-Regional Crop Mapping

Author(s):

Miloš Pandžić, Dejan Pavlović, Oskar Marko, Milan Kilibarda

Abstract:

Accurate information on crop spatial distribution is essential for modern agriculture, which faces increasing pressure from global food demand and climate change. Advances in Earth observation, satellite data availability, and machine learning (ML) have enabled effective large-scale crop monitoring. However, traditional crop mapping approaches rely on large labeled datasets, which are often costly and difficult to obtain, motivating the use of alternative strategies. Transfer learning (TL) addresses this limitation by enabling models trained in data-rich regions to be adapted to regions with limited or no labeled data. In this study, we investigate TL for crop type classification using Random Forest (RF) and encoder-only Transformer with a classification head across three data modalities: Sentinel-1, Sentinel-2, and their combination. Satellite time series were interpolated to regular 15-day intervals to ensure consistent model input. Models were trained on a large labeled dataset from Slovenia and transferred to Serbia, where labeled data availability is limited. We evaluated off-the-shelf model transfer and fine-tuning strategies. The best performance was achieved by a Transformer-based TL approach with a frozen feature extractor and fine-tuned classifier head, reaching an F1 score of 91% and outperforming the in-region supervised benchmark by 7%. These results demonstrate the potential of TL for cross-regional crop mapping in the studied regions while substantially reducing reliance on large labeled datasets.

Keywords:

transfer learning, crop mapping, Sentinel-1, Sentinel-2, transformer, random forest

DOI: 10.15292/geodetski-vestnik.2026.02.268-288

Citation:

Miloš Pandžić, Dejan Pavlović, Oskar Marko, Milan Kilibarda (2026). Uporaba učenja s prenosom znanja za medregionalno kartiranje poljščin. | Spatial Transfer Learning for Cross-Regional Crop Mapping. Geodetski vestnik, 70 (2), 268-288. DOI: 10.15292/geodetski-vestnik.2026.02.268-288