Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series
TL
TL;DR
This paper takes advantage of the increasing quantity of annotated satellite data to model simultaneously the inter- and intra-annual agricultural dynamics of yearly parcel classification with a deep learning approach and releases the first large-scale multi-year agricultural dataset with over 300,000 annotated parcels.
Abstract
While annual crop rotations play a crucial role for agricultural optimization, they have been largely ignored for automated crop type mapping. In this paper, we take advantage of the increasing quantity of annotated satellite data to propose to model simultaneously the inter- and intra-annual agricultural dynamics of yearly parcel classification with a deep learning approach. Along with simple training adjustments, our model provides an improvement of over 6.3% mIoU over the current state-of-the-art of crop classification, and a reduction of over 21% of the error rate. Furthermore, we release the first large-scale multi-year agricultural dataset with over 300,000 annotated parcels.
References41 items
1
Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
2
Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification
3
Pre-season crop type mapping using deep neural networks
4
Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
5