Centre dedocumentation
scientifique

Dépouillements

Assessment of Sentinel-1A data for rice crop classification using random forests and support vector machines / Nguyen-Thanh Son in Geocarto international, vol 33 n° 6 (June 2018)  

Public [article]  inGeocarto international > vol 33 n° 6 (June 2018) . - pp 587 - 601 Titre : Assessment of Sentinel-1A data for rice crop classification using random forests and support vector machines Type de document : Article/Communication Auteurs : Nguyen-Thanh Son, Auteur ; Chi-Farn Chen, Auteur ; Cheng-Ru Chen ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 587 - 601 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Sentinel-SAR [Termes IGN] Oryza (genre) [Termes IGN] polarimétrie radar [Termes IGN] production agricole végétale [Termes IGN] Viet Nam Résumé : (Auteur) This study developed an approach to map rice-cropping systems in An Giang and Dong Thap provinces, South Vietnam using multi-temporal Sentinel-1A (S1A) data. The data were processed through four steps: (1) data pre-processing, (2) constructing smooth time series VH backscatter data, (3) rice crop classification using random forests (RF) and support vector machines (SVM) and (4) accuracy assessment. The results indicated that the smooth VH backscatter profiles reflected the temporal characteristics of rice-cropping patterns in the study region. The comparisons between the classification results and the ground reference data indicated that the overall accuracy and Kappa coefficient achieved from RF were 86.1% and 0.72, respectively, which were slightly more accurate than SVM (overall accuracy of 83.4% and Kappa coefficient of 0.67). These results were reaffirmed by the government’s rice area statistics with the relative error in area (REA) values of 0.2 and 2.2% for RF and SVM, respectively. Numéro de notice : A2018-142 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2017.1289555 Date de publication en ligne : 13/02/2017 En ligne : https://doi.org/10.1080/10106049.2017.1289555 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89700 [article]

Mapping rubber trees based on phenological analysis of Landsat time series data-sets / Janatul Aziera binti Abd Razak in Geocarto international, vol 33 n° 6 (June 2018)  

Public [article]  inGeocarto international > vol 33 n° 6 (June 2018) . - pp 627 - 650 Titre : Mapping rubber trees based on phenological analysis of Landsat time series data-sets Type de document : Article/Communication Auteurs : Janatul Aziera binti Abd Razak, Auteur ; Abdul Rashid bin M. Shariff, Auteur ; Noordin bin Ahmad, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 627 - 650 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] arbre sempervirent [Termes IGN] Arecaceae [Termes IGN] carte agricole [Termes IGN] hevea (genre) [Termes IGN] image Landsat [Termes IGN] Malaisie [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] phénologie [Termes IGN] série temporelle Résumé : (Auteur) This study proposes a strategy for accurate mapping of rubber trees through the analysis of Landsat time series datasets. The phenological dynamics of rubber trees were derived from the Normalized Difference Vegetation Index (NDVI) to verify the three important phenological metrics of rubber trees; defoliation, foliation and their growing stages. A decade (2006–2015) ago, Landsat time series NDVIs were used to study the strength of relationship between rubber trees, evergreen trees and oil palm trees. Two important results that could discriminate these three types of vegetation were found; firstly, a weak relationship of NDVIs between rubber trees and evergreen trees during the defoliation period (r2 = 0.1358) and secondly between rubber trees and oil palm trees during the growing period (r2 = 0.2029). This analysis was verified using Support Vector Machine to map the distribution of the three types of vegetation. An accurate mapping strategy of rubber trees was successfully formulated. Numéro de notice : A2018-143 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2017.1289559 Date de publication en ligne : 13/02/2017 En ligne : https://doi.org/10.1080/10106049.2017.1289559 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89701 [article]