Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series
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 agricu...
Guardado en:
Autores principales: | , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/3708c8d3953d49599511664b065a24b9 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:3708c8d3953d49599511664b065a24b9 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:3708c8d3953d49599511664b065a24b92021-11-25T18:54:39ZCrop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series10.3390/rs132245992072-4292https://doaj.org/article/3708c8d3953d49599511664b065a24b92021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4599https://doaj.org/toc/2072-4292While 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.Félix QuintonLoic LandrieuMDPI AGarticlecrop mappingcrop rotationSentinel-2ScienceQENRemote Sensing, Vol 13, Iss 4599, p 4599 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
crop mapping crop rotation Sentinel-2 Science Q |
spellingShingle |
crop mapping crop rotation Sentinel-2 Science Q Félix Quinton Loic Landrieu Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
description |
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. |
format |
article |
author |
Félix Quinton Loic Landrieu |
author_facet |
Félix Quinton Loic Landrieu |
author_sort |
Félix Quinton |
title |
Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
title_short |
Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
title_full |
Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
title_fullStr |
Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
title_full_unstemmed |
Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series |
title_sort |
crop rotation modeling for deep learning-based parcel classification from satellite time series |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/3708c8d3953d49599511664b065a24b9 |
work_keys_str_mv |
AT felixquinton croprotationmodelingfordeeplearningbasedparcelclassificationfromsatellitetimeseries AT loiclandrieu croprotationmodelingfordeeplearningbasedparcelclassificationfromsatellitetimeseries |
_version_ |
1718410578873024512 |