Centre dedocumentation
scientifique

Evaluating Sentinel-1A datasets for rice leaf area index estimation based on machine learning regression models / Lamin R. Mansaray in Geocarto international, vol 37 n° 5 ([01/03/2022])  

Public [article]  inGeocarto international > vol 37 n° 5 [01/03/2022] . - pp 1225 - 1236 Titre : Evaluating Sentinel-1A datasets for rice leaf area index estimation based on machine learning regression models Type de document : Article/Communication Auteurs : Lamin R. Mansaray, Auteur ; Fumin Wang, Auteur ; Adam Sheka Kanu, Auteur ; Lingbo Yang, Auteur Année de publication : 2022 Article en page(s) : pp 1225 - 1236 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage automatique [Termes IGN] Chine [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] Extreme Gradient Machine [Termes IGN] image Sentinel-SAR [Termes IGN] jeu de données localisées [Termes IGN] Leaf Area Index [Termes IGN] modèle de régression [Termes IGN] plus proche voisin, algorithme du [Termes IGN] polarisation [Termes IGN] rizière Résumé : (Auteur) Three Sentinel-1A datasets in vertical transmitted and horizontal received (VH) and vertical transmitted and vertical received (VV) polarisations, and the linear combination of VH and VV (VHVV) are evaluated for rice green leaf area index (LAI) estimation using four machine learning regression models [Support Vector Machine (SVM), k-Nearest Neighbour (k-NN), Random Forest (RF) and Gradient Boosting Decision Tree (GBDT)]. Results showed that for the entire growing season, VV outperformed VH, recording an R2 of 0.68 and an RMSE of 0.98 m2/m2 with the k-NN model. However, VHVV produced the most accurate estimates with GBDT (R2 of 0.82 and RMSE of 0.68 m2/m2), followed by that of VHVV with RF (R2 of 0.78 and RMSE of 0.90 m2/m2). Our findings have further confirmed that combining VH and VV data can achieve improved rice growth modelling, and that tree-based algorithms can better handle data dimensionality. Numéro de notice : A2022-274 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1773545 Date de publication en ligne : 05/06/2020 En ligne : https://doi.org/10.1080/10106049.2020.1773545 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100753 [article]

Accuracies of support vector machine and random forest in rice mapping with Sentinel-1A, Landsat-8 and Sentinel-2A datasets / Lamin R. Mansaray in Geocarto international, vol 35 n° 10 ([01/08/2020])  

Public [article]  inGeocarto international > vol 35 n° 10 [01/08/2020] . - pp 1088 - 1108 Titre : Accuracies of support vector machine and random forest in rice mapping with Sentinel-1A, Landsat-8 and Sentinel-2A datasets Type de document : Article/Communication Auteurs : Lamin R. Mansaray, Auteur ; Fumin Wang, Auteur ; Jingfeng Huang, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 1088 - 1108 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] carte de la végétation [Termes IGN] Chine [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] jeu de données [Termes IGN] polarisation [Termes IGN] rizière [Termes IGN] surface cultivée Résumé : (auteur) SVM and RF are widely used in rice mapping. However, their performance with single and different combinations of satellite datasets is rarely reported. Hence we report their rice mapping accuracies for two seasons using Sentinel-1A, Landsat-8 and Sentinel-2A images. The VH and VV polarizations of Sentinel-1A, and two spectral indices (SIs) of Landsat-8 and Sentine1-2A were used to obtain seven datasets (VH, VV, SI, VHVV, VHSI, VVSI and VHVVSI), and on which SVM and RF were applied and accuracies were assessed. VHSI showed the highest overall accuracy for both algorithms in both years. SVM with VHSI had a slightly higher accuracy (90.8%) than RF with VHSI (89.2%) in 2015 while in 2016 RF with VHSI showed a slightly higher accuracy (95.2%) than SVM with VHSI (93.4%). Although they produced equivalent accuracies within years, RF is more sensitive to additional data, given a 6.0% increase from 2015 to 2016 with VHSI. Numéro de notice : A2020-443 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1568586 Date de publication en ligne : 18/03/2019 En ligne : https://doi.org/10.1080/10106049.2019.1568586 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95501 [article]