Agricultural Land Cover Mapping through Two Deep Learning Models in the Framework of EU’s CAP Activities Using Sentinel-2 Multitemporal Imagery
-
Published:2023-09-22
Issue:19
Volume:15
Page:4657
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Papadopoulou Eleni1, Mallinis Giorgos2ORCID, Siachalou Sofia2, Koutsias Nikos3ORCID, Thanopoulos Athanasios C.4, Tsaklidis Georgios1
Affiliation:
1. Department of Mathematics, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece 2. School of Rural and Surveying Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece 3. Department of Sustainable Agriculture, University of Patras, 30100 Agrinio, Greece 4. Hellenic Statistical Authority (ELSTAT), 18510 Piraeus, Greece
Abstract
The images of the Sentinel-2 constellation can help the verification process of farmers’ declarations, providing, among other things, accurate spatial explicit maps of the agricultural land cover. The aim of the study is to design, develop, and evaluate two deep learning (DL) architectures tailored for agricultural land cover and crop type mapping. The focus is on a detailed class scheme encompassing fifteen distinct classes, utilizing Sentinel-2 imagery acquired on a monthly basis throughout the year. The study’s geographical scope covers a diverse rural area in North Greece, situated within southeast Europe. These architectures are a Temporal Convolutional Neural Network (CNN) and a combination of a Recurrent and a 2D Convolutional Neural Network (R-CNN), and their accuracy is compared to the well-established Random Forest (RF) machine learning algorithm. The comparative approach is not restricted to simply presenting the results given by classification metrics, but it also assesses the uncertainty of the classification results using an entropy measure and the spatial distribution of the classification errors. Furthermore, the issue of sampling strategy for the extraction of the training set is highlighted, targeting the efficient handling of both the imbalance of the dataset and the spectral variability of instances among classes. The two developed deep learning architectures performed equally well, presenting an overall accuracy of 90.13% (Temporal CNN) and 90.18% (R-CNN), higher than the 86.31% overall accuracy of the RF approach. Finally, the Temporal CNN method presented a lower entropy value (6.63%), compared both to R-CNN (7.76%) and RF (28.94%) methods, indicating that both DL approaches should be considered for developing operational EO processing workflows.
Subject
General Earth and Planetary Sciences
Reference97 articles.
1. European Commission (2023, August 09). The Common Agricultural Policy at a Glance. Available online: https://agriculture.ec.europa.eu/common-agricultural-policy/cap-overview/cap-glance_en#cap2023-27. 2. Spatial Information in European Agricultural Data Management. Requirements and Interoperability Supported by a Domain Model;Land Use Policy,2016 3. National High-Resolution Cropland Classification of Japan with Agricultural Census Information and Multi-Temporal Multi-Modality Datasets;Xia;Int. J. Appl. Earth Obs. Geoinf.,2023 4. Sarvia, F., Xausa, E., De Petris, S., Cantamessa, G., and Borgogno-Mondino, E. (2021). A Possible Role of Copernicus Sentinel-2 Data to Support Common Agricultural Policy Controls in Agriculture. Agronomy, 11. 5. Abubakar, G.A., Wang, K., Shahtahamssebi, A., Xue, X., Belete, M., Gudo, A.J.A., Shuka, K.A.M., and Gan, M. (2020). Mapping Maize Fields by Using Multi-Temporal Sentinel-1A and Sentinel-2A Images in Makarfi, Northern Nigeria, Africa. Sustainability, 12.
|
|