No full text
Unpublished conference/Abstract (Scientific congresses and symposiums)
Prediction of compressed sward height of Walloon pastures from sentinel-2 images using machine learning algorithms.
Nickmilder, Charles; Tedde, Anthony; Lejeune, Philippe et al.
2020ADSA 2020 Virtual annual meeting
 

Files


Full Text
No document available.
Annexes
test4.mp4
Publisher postprint (27.85 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
remote sensing; compressed sward height; machine learning
Abstract :
[en] ROADSTEP is a Walloon research program aiming to develop decision tools to help farmers in their daily herd monitoring on pastures. One of the aims is to develop a modeling tool to predict the availability of pasture feeding based on satellite images, meteorological variables and soil characteristics. 7737 compressed sward heights (CSH) were measured on 2 farms recorded with Jenquip EC20G platemeter in July and August 2019. They were used to calibrate and validate 73 predictive models of CSH. The tested algorithms were linear regression, lars, cubist, generalized linear model, neural network, random forest and linear support vector machine. The explaining variables were the 11 sentinel-2 reflectance bands at the bottom of atmosphere. Those bands and CSH were introduced directly in the model but also through their logarithm, square-root, square and cube forms to test the possible nonlinear relationships between them. The reduction of dimensionality of X-matrix through the estimation of principal components as well as partial least squares factors was also tested. To guarantee independence between calibration and validation, calibration was made on CSH (ranging from 12 to 158 mm with an average value of 59.4+-22.3 mm) measured on a farm and validation on CSH (ranging from 13 to 247.5 mm with an average value of 53.2+-21.6 mm) measured on another farm. The model that performed the best was a generalized linear model from the gamma family using an inverse link function. Calibration and validation RMSE were respectively equal to 17.4 and 20.7 mm or 29.3 and 28.9% of their respective mean. These results are only preliminary. Additional sampling periods and pastures are needed to improve the models’ robustness. Moreover, the second step of this research will consist in adding information related to meteorological data and soil characteristics to enhance the prediction power of the developed models.
Disciplines :
Agriculture & agronomy
Author, co-author :
Nickmilder, Charles  ;  Université de Liège - ULiège > Département GxABT > Biosystems Dynamics and Exchanges
Other collaborator :
Tedde, Anthony  ;  Université de Liège - ULiège > Département GxABT > Modélisation et développement
Lejeune, Philippe ;  Université de Liège - ULiège > Département GxABT > Gestion des ressources forestières et des milieux naturels
Dufrasne, Isabelle  ;  Université de Liège - ULiège > Dpt. de gestion vétérinaire des Ressources Animales (DRA) > Nutrition des animaux domestiques
Lessire, Françoise  ;  Université de Liège - ULiège > Dpt. de gestion vétérinaire des Ressources Animales (DRA) > Nutrition des animaux domestiques
Tychon, Bernard ;  Université de Liège - ULiège > DER Sc. et gest. de l'environnement (Arlon Campus Environ.) > Eau, Environnement, Développement
Lebeau, Frédéric  ;  Université de Liège - ULiège > Département GxABT > Biosystems Dynamics and Exchanges
Soyeurt, Hélène  ;  Université de Liège - ULiège > Département GxABT > Modélisation et développement
Language :
English
Title :
Prediction of compressed sward height of Walloon pastures from sentinel-2 images using machine learning algorithms.
Publication date :
24 June 2020
Event name :
ADSA 2020 Virtual annual meeting
Event organizer :
American dairy science association
Event date :
22/06/2020 - 24/06/2020
Audience :
International
References of the abstract :
393 in https://www.adsa.org/Portals/0/SiteContent/Docs/Meetings/2020ADSA/ADSA2020_Abstracts.pdf?v20200708
Name of the research project :
ROADSTEP
Available on ORBi :
since 08 January 2021

Statistics


Number of views
87 (8 by ULiège)
Number of downloads
10 (2 by ULiège)

Bibliography


Similar publications



Contact ORBi