Multi-Year Time Series Transfer Learning: Application of Early Crop Classification
Remote Sensing · 10.01.2024 · 16 (2) · 270
DOI: 10.3390/rs16020270 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 10.01.2024. Verfasst von Matej Račič und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Slovenian Research Agency.
Abstract (Originalsprache)
Crop classification is an important task in remote sensing with many applications, such as estimating yields, detecting crop diseases and pests, and ensuring food security. In this study, we combined knowledge from remote sensing, machine learning, and agriculture to investigate the application of transfer learning with a transformer model for variable length satellite image time series (SITS). The objective was to produce a map of agricultural land, reduce required interventions, and limit in-field visits. Specifically, we aimed to provide reliable agricultural land class predictions in a timely manner and quantify the necessary amount of reference parcels to achieve these outcomes. Our dataset consisted of Sentinel-2 satellite imagery and reference crop labels for Slovenia spanning over years 2019, 2020, and 2021. We evaluated adaptability through fine-tuning in a real-world scenario of early crop classification with limited up-to-date reference data. The base model trained on a different year achieved an average F1 score of 82.5% for the target year without having a reference from the target year. To increase accuracy with a new model trained from scratch, an average of 48,000 samples are required in the target year. Using transfer learning, the pre-trained models can be efficiently adapted to an unknown year, requiring less than 0.3% (1500) samples from the dataset. Building on this, we show that transfer learning can outperform the baseline in the context of early classification with only 9% of the data after 210 days in the year.
Förderung
- Slovenian Research Agency
Zitieren
APA
Račič, M., Oštir, K., Zupanc, A., & Zajc, L. Č. (2024). Multi-Year Time Series Transfer Learning: Application of Early Crop Classification. Remote Sensing, 16(2), 270. https://doi.org/10.3390/rs16020270
Vancouver
Račič M, Oštir K, Zupanc A, Zajc LČ. Multi-Year Time Series Transfer Learning: Application of Early Crop Classification. Remote Sensing. 2024;16(2):270. doi:10.3390/rs16020270
BibTeX
@article{Rai2024,
author = {Račič, Matej and Oštir, Krištof and Zupanc, Anže and Zajc, Luka Čehovin},
title = {Multi-Year Time Series Transfer Learning: Application of Early Crop Classification},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {2},
pages = {270},
doi = {10.3390/rs16020270}
}
EUVIMED