Détail de l'auteur
Auteur Satoshi Tsuyuki |
Documents disponibles écrits par cet auteur (2)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Exploring the inclusion of Sentinel-2 MSI texture metrics in above-ground biomass estimation in the community forest of Nepal / Santa Pandit in Geocarto international, vol 35 n° 16 ([01/12/2020])
[article]
Titre : Exploring the inclusion of Sentinel-2 MSI texture metrics in above-ground biomass estimation in the community forest of Nepal Type de document : Article/Communication Auteurs : Santa Pandit, Auteur ; Satoshi Tsuyuki, Auteur ; Timothy Dube, Auteur Année de publication : 2020 Article en page(s) : pp 1832 - 1849 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse multibande
[Termes IGN] analyse texturale
[Termes IGN] apprentissage automatique
[Termes IGN] biomasse aérienne
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] forêt
[Termes IGN] image Sentinel-MSI
[Termes IGN] indice de végétation
[Termes IGN] NépalRésumé : (auteur) The potential of the improved resolution Sentinel-2 MSI data was explored through texture metrics, vegetation indices (VIs) and pooled dataset using the Random Forest (RF) machine learning algorithm to estimate Above-ground Biomass (AGB) in a sub-tropical forest of Nepal. Texture metrics were derived based on different working window sizes (3 × 3, 5 × 5, 7 × 7 and 9 × 9), and the results were compared with those obtained, using raw traditional bands (Analysis set 1: 2, 3, 4, 8, 11 and 12), raw traditional and red edge bands (Analysis set 2: Set 1 + Band 5, 6, 7 and 8A), and red edge bands (Analysis set 3) only. Comparatively, the use of pooled data (texture and VIs) yielded higher biomass estimates. The results from pooled data based on the 7 × 7 window size resulted in models with better model fitting parameters. For instance, pooled data produced an R2 = 0.99 and a RMSE = 4.51 t ha−1 (relRMSE = 2.82). Further, the RF model selected dissimilarity, variance and mean from Band 2 and SAVI (Soil adjusted vegetation index) as the most important AGB predictor variables. The results demonstrated that like the red-edge bands, traditional bands were equally important in AGB estimation. Numéro de notice : A2020-727 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1588390 Date de publication en ligne : 10/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1588390 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96334
in Geocarto international > vol 35 n° 16 [01/12/2020] . - pp 1832 - 1849[article]Potential of UAV photogrammetry for characterization of forest canopy structure in uneven-aged mixed conifer–broadleaf forests / Sadeepa Jayathunga in International Journal of Remote Sensing IJRS, vol 41 n° 1 (01 - 08 janvier 2020)
[article]
Titre : Potential of UAV photogrammetry for characterization of forest canopy structure in uneven-aged mixed conifer–broadleaf forests Type de document : Article/Communication Auteurs : Sadeepa Jayathunga, Auteur ; Toshiaki Owari, Auteur ; Satoshi Tsuyuki, Auteur ; Yasumasa Hirata, Auteur Année de publication : 2020 Article en page(s) : pp 53 - 73 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse de groupement
[Termes IGN] couvert forestier
[Termes IGN] forêt de feuillus
[Termes IGN] gestion forestière
[Termes IGN] hauteur des arbres
[Termes IGN] image captée par drone
[Termes IGN] photogrammétrie aérienne
[Termes IGN] photographie aérienne latérale
[Termes IGN] Pinophyta
[Termes IGN] structure d'un peuplement forestierRésumé : (auteur) Forest canopy structure is an important parameter in multipurpose forest management. An understanding of forest structure plays a particularly important role in the management of uneven-aged forests. The identification of vertical and horizontal variations in forest canopy structure using a ground-based survey is resource intensive, hence often demands for alternative data sources. In this study, one of the advanced remote sensing (RS) techniques, i.e. digital aerial photogrammetry was used to characterize forest canopy structure in a mixed conifer–broadleaf forest. We used aerial imagery acquired with a fixed-wing unmanned aerial vehicle (UAV) platform to produce RS metrics that could be used to classify and map forest structure types at landscape scale. Our results demonstrated that few structural and spectral metrics derived from UAV photogrammetric data, e.g. mean height, standard deviation of height, canopy cover, and percentage broadleaf vegetation cover, could characterize the forest structure across landscapes, particularly at the forest management compartment level, in a limited amount of time. We used cluster analysis for classification of forest structure types and identified five forest structure classes with varying levels of forest canopy structural complexity: (1) short, open-canopy, conifer-dominated structure; (2) short, dense-canopy, broadleaf-dominated structure; (3) tall, closed-canopy, broadleaf-dominated structure; (4) very tall, closed-canopy, conifer-dominated structure with a relatively high degree of variation in canopy height; and (5) very tall, closed-canopy, conifer-dominated structure with a relatively low degree of variation in canopy height. These classes showed relationships with forest management activities (e.g. selection harvesting) and natural disturbances (e.g. typhoon damage). Spatial distribution of forest canopy structural complexity that was revealed in this study is capable of providing important information for forest management planning and habitat modelling. Further, the simple, and flexible data-driven method used in this study to characterize forest structure has the potential to be applied with necessary changes over larger landscapes and different forest types for characterizing and mapping forest structural complexity. Numéro de notice : A2020-210 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/01431161.2019.1648900 Date de publication en ligne : 01/08/2019 En ligne : https://doi.org/10.1080/01431161.2019.1648900 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94892
in International Journal of Remote Sensing IJRS > vol 41 n° 1 (01 - 08 janvier 2020) . - pp 53 - 73[article]