Article (Scientific journals)
Harvesting Insights from the Sky: Satellite-Powered Automation for Detecting Mowing Based on Predicted Compressed Sward Heights
Dichou, Killian; Nickmilder, Charles; Tedde, Anthony et al.
2024In Applied Sciences, 14 (5), p. 1923
Peer Reviewed verified by ORBi
 

Files


Full Text
manuscript_final.pdf
Publisher postprint (1.4 MB) Creative Commons License - Attribution
Download
Annexes
1_graphical abstract_V5.png
(221.54 kB) Creative Commons License - Attribution
Graphical abstract for the article " Harvesting Insights from the Sky: Satellite-Powered Automation for Detecting Mowing Based on Predicted Compressed Sward Heights"
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Computer Science Applications; Machine learning; compressed sward height; mowing; pasture
Abstract :
[en] The extensive identification of mowing events on a territory holds significant potential to help monitor shifts in biodiversity and contribute to assessing the impacts of drought events. Additionally, it provides valuable insights into farming practices and their consequential economic and ecological effects. To overcome challenges in obtaining reference grazing information directly from the field, this study introduces a novel methodology leveraging the compressed sward height (CSH) derived from Sentinel-1, Sentinel-2, and meteorological data, boasting an accuracy of 20 mm. Our central hypothesis posits that the mowing status of a parcel can be automatically discerned by analyzing the distribution and variation of its CSH values. Employing a two-step strategy, we first applied unsupervised algorithms, specifically k-means and isolation forest, and subsequently amalgamated the outcomes with a partial least squares analysis on an extensive dataset encompassing 194,657 pastures spanning the years 2018 to 2021. The culmination of our modeling efforts yielded a validation accuracy of 0.66, as ascertained from a focused dataset of 68 pastures. Depending on the studied year and with a threshold fixed at 0.50, 21% to 57% of all the parcels in the Wallonia dataset were tagged as mown by our model. This study introduces an innovative approach for the automated detection of mown parcels, showcasing its potential to monitor agricultural activities at scale.
Disciplines :
Agriculture & agronomy
Author, co-author :
Dichou, Killian  ;  Université de Liège - ULiège > Département GxABT > Modélisation et développement
Nickmilder, Charles   ;  Université de Liège - ULiège > Département GxABT > Echanges Eau - Sol - Plantes
Tedde, Anthony  ;  Université de Liège - ULiège > TERRA Research Centre > Modélisation et développement ; National Funds for Scientific Research, 1000 Brussels, Belgium
Franceschini, Sébastien  ;  Université de Liège - ULiège > TERRA Research Centre
Brostaux, Yves  ;  Université de Liège - ULiège > TERRA Research Centre > Modélisation et développement
Dufrasne, Isabelle  ;  Université de Liège - ULiège > Département de gestion vétérinaire des Ressources Animales (DRA) > Nutrition des animaux domestiques
Lessire, Françoise  ;  Université de Liège - ULiège > Fundamental and Applied Research for Animals and Health (FARAH) > FARAH: Productions animales durables
Glesner, Noémie;  Fourrages Mieux ASBL, Horritine 1, Michamps, 6600 Bastogne, Belgium
Soyeurt, Hélène  ;  Université de Liège - ULiège > Département GxABT > Modélisation et développement
 These authors have contributed equally to this work.
Language :
English
Title :
Harvesting Insights from the Sky: Satellite-Powered Automation for Detecting Mowing Based on Predicted Compressed Sward Heights
Publication date :
26 February 2024
Journal title :
Applied Sciences
eISSN :
2076-3417
Publisher :
MDPI AG
Volume :
14
Issue :
5
Pages :
1923
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
SPW - Service Public de Wallonie [BE]
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE]
Funding number :
D31-1393/S1; D65-1435; T.0221.19
Funding text :
This work was supported by the Service Public de Wallonie with the projects ROAD-STEP [grant number D31-1393/S1] and WALLeSmart [grant number D65-1435] and by the Luxembourg National Research Fund with the project SIMBA [grant number T.0221.19].
Available on ORBi :
since 28 February 2024

Statistics


Number of views
60 (3 by ULiège)
Number of downloads
7 (2 by ULiège)

Bibliography


Similar publications



Contact ORBi