Field-Level Classification of Winter Catch Crops Using Sentinel-2 Time Series: Model Comparison and Transferability
Winter catch crops are promoted in the European Union under the Common Agricultural Policy to improve soil health and reduce nitrate leaching from agricultural fields. Currently, Member States often monitor farmers’ adoption through on-site inspections for a limited subset of parcels. Because of its potential for region-wide coverage, this study investigates the potential of Sentinel-2 satellite time series to classify catch crops at the field level in Flanders (Belgium). The first objective was to classify catch crops and identify the optimal model and time-series input for this task. The second objective was to apply these findings in a real-world scenario, aiming to provide reliable early-season predictions in a separate target year, testing early-season performance and temporal transferability. The following three models were compared: Random Forest (RF), Time Series Forest (TSF), and a One-Dimensional Convolutional Neural Network (1D-CNN). The results showed that, with a limited field-based training dataset, RF produced the most robust results across different time-series inputs, achieving a median F1-score of >88% on the best dataset. Additionally, the early-season performance of the models was delayed in the target year, reaching the F1-score threshold of 85% at least one month later in the season compared to the training years, with large timing differences between the models.
Details
| Volume | 16 |
|---|---|
| Magazine issue | 24 |
| Type | A1: Web of Science-article |
| Category | Research |
| Magazine | Remote Sensing |
| Publisher | MDPI AG |
| Language | English |
Bibtex
@misc{023d2faf-6385-4da5-8285-82fd7a131a88,
title = "Field-Level Classification of Winter Catch Crops Using Sentinel-2 Time Series: Model Comparison and Transferability",
abstract = "Winter catch crops are promoted in the European Union under the Common Agricultural Policy to improve soil health and reduce nitrate leaching from agricultural fields. Currently, Member States often monitor farmers’ adoption through on-site inspections for a limited subset of parcels. Because of its potential for region-wide coverage, this study investigates the potential of Sentinel-2 satellite time series to classify catch crops at the field level in Flanders (Belgium). The first objective was to classify catch crops and identify the optimal model and time-series input for this task. The second objective was to apply these findings in a real-world scenario, aiming to provide reliable early-season predictions in a separate target year, testing early-season performance and temporal transferability. The following three models were compared: Random Forest (RF), Time Series Forest (TSF), and a One-Dimensional Convolutional Neural Network (1D-CNN). The results showed that, with a limited field-based training dataset, RF produced the most robust results across different time-series inputs, achieving a median F1-score of >88% on the best dataset. Additionally, the early-season performance of the models was delayed in the target year, reaching the F1-score threshold of 85% at least one month later in the season compared to the training years, with large timing differences between the models.",
author = "Kato Vanpoucke and Stien Heremans and Emily Buls and Ben Somers",
year = "2024",
month = dec,
day = "10",
doi = "https://doi.org/10.3390/rs16244620",
language = "English",
publisher = "MDPI AG",
address = "Belgium,
type = "Other"
}