Tsanet: A Deep Learning Framework for the Delineation of Agricultural Fields Utilizing Satellite Image Time Series

Abstract

Satellite image time series (SITS), such as Sentinel-2 imagery, plays a crucial role in the delineation of agricultural fields by reducing the impacts of ambiguities due to the spatial arrangement of field boundaries. Existing delineate field parcel models rely extensively on spatial features derived from single-date imagery. However, several studies have exploited the potential of SITS to effectively tackle the complexities associated with the intrinsic consistency between agricultural fields and their boundaries. This paper proposes a novel Two-Stream Attention convolutional neural network (TSANet) to capture the subtle difference between agricultural fields from SITS. Specifically, a field temporal semantic stream is introduced to adaptively leverage the significance of spatial-spectral-temporal feature representation associated with the location of agricultural parcels, especially where transitions in crop types take place. Considering the consistency between field parcels and their boundaries, we develop a field boundary prediction stream to enhance the extraction of edge features, particularly beneficial for the extraction of small and irregular agricultural parcels. Moreover, a field parcel refining block is employed to further enhance the geometric accuracy of agricultural fields. We conducted experiments on Sentinel-2 images from the Netherlands. Results showed that our approach produced a better layout of agricultural fields, with an average F1-score of 0.91 than the existing 3D-Unet, U-TEA, and BiConvLSTM. In addition, the robust generalizability of the proposed model was verified by the temporal transfer and large-scale spatial prediction from the analysis of both quantitative and qualitative results. We compared the difference between SITS and the corresponding composite images, which further verified the influence of temporal variation on the proposed approach. This paper provides a general guide for delineating agricultural parcels using SITS.

Keywords: Agricultural field delineation, Satellite image time series, Convolutional Neural Network, Multi-task learning, Attention Mechanism