Dépôt numérique
RECHERCHER

Alfalfa yield estimation based on time series of Landsat 8 and PROBA-V images: An investigation of machine learning techniques and spectral-temporal features.

Téléchargements

Téléchargements par mois depuis la dernière année

Azadbakht, Mohsen; Ashourloo, Davoud; Aghighi, Hossein; Homayouni, Saeid ORCID logoORCID: https://orcid.org/0000-0002-0214-5356; Shahrabi, Hamid Salehi; Matkan, AliAkbar et Radiom, Soheil (2022). Alfalfa yield estimation based on time series of Landsat 8 and PROBA-V images: An investigation of machine learning techniques and spectral-temporal features. Remote Sensing Applications: Society and Environment , vol. 25 . p. 100657. DOI: 10.1016/j.rsase.2021.100657.

[thumbnail of P4031.pdf]
Prévisualisation
PDF
Télécharger (1MB) | Prévisualisation

Résumé

Remote Sensing (RS) technology provides regular monitoring of alfalfa farms, as a major source of forage production worldwide. Phenological characteristics derived from time series of RS imagery provide a valuable information source to estimate crop yield accurately. In this study, we computed spectral vegetation indices (SVIs) from time series of Landsat 8 and PROBA-V images to extract temporal characteristics of alfalfa farms throughout the growth periods in three consecutive years in the Moghan plain, Iran. Then, several new spectral-temporal features were developed based on phenological characteristics of alfalfa during the growing season. Such features particularly describe geometry and variations of the temporal curves and are thus invaluable in describing phenological attributes. We conducted several feature selection methods due to the variety of features. Machine learning (ML) methods, including ridge, lasso, Gaussian Process Regression (GPR), Random Forest Regression (RFR), Boosted Regression Trees (BRT), and Support Vector Regression (ν-SVR) were utilized to build inversion models in order to estimate alfalfa yields, where the results showed satisfactory performance of GPR using the selected features by GS (RMSE=1114.0 kg/ha), RReliefF (RMSE=1157.7 kg/ha) and Boruta (RMSE=1210.2 kg/ha) as compared to the complete feature dataset (RMSE=1237.4 kg/ha). Overall, the developed phenological features coupled with feature selection methods resulted in the appropriate performance of the ML methods in alfalfa yield estimation.

Type de document: Article
Mots-clés libres: precision agriculture; alfalfa yield estimation; machine learning; time series images; feature selection
Centre: Centre Eau Terre Environnement
Date de dépôt: 09 févr. 2022 15:41
Dernière modification: 09 févr. 2022 15:41
URI: https://espace.inrs.ca/id/eprint/12216

Gestion Actions (Identification requise)

Modifier la notice Modifier la notice