Centre de documentation
scientifique

Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network / Chen Chen in Remote sensing of environment, vol 270 (March 2022)  

Public [article]  inRemote sensing of environment > vol 270 (March 2022) . - n° 112885 Titre : Aboveground biomass of salt-marsh vegetation in coastal wetlands: Sample expansion of in situ hyperspectral and Sentinel-2 data using a generative adversarial network Type de document : Article/Communication Auteurs : Chen Chen, Auteur ; Yi Ma, Auteur ; Guangbo Ren, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112885 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biomasse aérienne [Termes IGN] carte d'occupation du sol [Termes IGN] carte thématique [Termes IGN] image hyperspectrale [Termes IGN] image Sentinel-MSI [Termes IGN] littoral [Termes IGN] marais salant [Termes IGN] réseau antagoniste génératif Résumé : (auteur) Coastal wetlands are main components of the “blue carbon” ecosystems in coastal zones. Salt-marsh biomass is especially important regarding climate-change mitigation. Generating high precision biomass maps for evaluating the ecological functions of coastal wetlands is essential; however, conducting accurate biomass inversions with limited in situ observations from coastal wetlands is challenging. We propose a generative adversarial network with a constrained factor model (GAN-CF) for expanding limited in situ salt-marsh biomass observations. We used Sentinel-2 images and a deep belief network based on the conjugate gradient method (CG-DBN) for obtaining land-cover maps and the salt-marsh distribution (species: Phragmites australis, Suaeda glauca, Spartina alterniflora, and mixed species dominated by Tamarix chinensis) in the study area. This study bridges in situ hyperspectral and Sentinel-2 multispectral data by a satellite-band equivalent conversion model. The biomass and multispectral data derived from Sentinel-2 were used as input for the proposed GAN-CF model, which produced and constrained the generated samples based on the features (i.e., spectra, vegetation index, and biomass) of the in situ observations. Aboveground biomass (AGB) maps at 10-m spatial resolution were produced by constructing multiple linear regression models (MLRMs) based on the generated samples of each salt-marsh type using Sentinel-2 images. The quantity and richness of the generated samples improved the AGB estimations in the study area. The inversion accuracy of S. alterniflora was significantly improved (RMSE = 3.71 Mg/ha); the estimated AGB was strongly related to the in situ observations (R = 0.923). The estimated AGB was validated using in situ observations. The total amount of salt-marsh AGB in the study area in 2019 was estimated at 2.36 × 105 Mg, with 7.95 Mg/ha average. The salt-marsh biomass in decreasing order was as follows: P. australis (12.7 Mg/ha) > S. alterniflora (11.5 Mg/ha) > mixed species (8.97 Mg/ha) > S. glauca (2.18 Mg/ha). The salt-marsh area in decreasing order was as follows: S. glauca (10,410 ha) > P. australis (7320 ha) > mixed species (6740 ha) > S. alterniflora (5240 ha). By a feasibility analysis we estimated the biomass based on the Sentinel-2 data covering the Yellow River delta wetland in May, July, and September 2019 and the Jiaozhou Bay wetland in September 2019 by using the generated samples. The generated samples based on the 2013–2019 in situ observations constitute a salt-marsh biomass database, which can be useful for quantifying the regional carbon storage and ecological restoration monitoring. Numéro de notice : A2022-128 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112885 Date de publication en ligne : 07/01/2022 En ligne : https://doi.org/10.1016/j.rse.2021.112885 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99710 [article]

Decision fusion of deep learning and shallow learning for marine oil spill detection / Junfang Yang in Remote sensing, vol 14 n° 3 (February-1 2022)  

Public [article]  inRemote sensing > vol 14 n° 3 (February-1 2022) . - n° 666 Titre : Decision fusion of deep learning and shallow learning for marine oil spill detection Type de document : Article/Communication Auteurs : Junfang Yang, Auteur ; Yi Ma, Auteur ; Yabin Hu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 666 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme de fusion [Termes IGN] analyse multiéchelle [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] hydrocarbure [Termes IGN] image hyperspectrale [Termes IGN] marée noire [Termes IGN] milieu marin [Termes IGN] pollution des mers [Termes IGN] précision de la classification [Termes IGN] sous ensemble flou [Termes IGN] surveillance écologique [Termes IGN] transformation en ondelettes Résumé : (auteur) Marine oil spills are an emergency of great harm and have become a hot topic in marine environmental monitoring research. Optical remote sensing is an important means to monitor marine oil spills. Clouds, weather, and light control the amount of available data, which often limit feature characterization using a single classifier and therefore difficult to accurate monitoring of marine oil spills. In this paper, we develop a decision fusion algorithm to integrate deep learning methods and shallow learning methods based on multi-scale features for improving oil spill detection accuracy in the case of limited samples. Based on the multi-scale features after wavelet transform, two deep learning methods and two classical shallow learning algorithms are used to extract oil slick information from hyperspectral oil spill images. The decision fusion algorithm based on fuzzy membership degree is introduced to fuse multi-source oil spill information. The research shows that oil spill detection accuracy using the decision fusion algorithm is higher than that of the single detection algorithms. It is worth noting that oil spill detection accuracy is affected by different scale features. The decision fusion algorithm under the first-level scale features can further improve the accuracy of oil spill detection. The overall classification accuracy of the proposed method is 91.93%, which is 2.03%, 2.15%, 1.32%, and 0.43% higher than that of SVM, DBN, 1D-CNN, and MRF-CNN algorithms, respectively. Numéro de notice : A2022-125 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14030666 Date de publication en ligne : 30/01/2022 En ligne : https://doi.org/10.3390/rs14030666 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99688 [article]

An incremental isomap method for hyperspectral dimensionality reduction and classification / Yi Ma in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 6 (June 2021)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 87 n° 6 (June 2021) . - pp 445 - 455 Titre : An incremental isomap method for hyperspectral dimensionality reduction and classification Type de document : Article/Communication Auteurs : Yi Ma, Auteur ; Zezhong Zheng, Auteur ; Yutang Ma, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 445 - 455 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme d'apprentissage [Termes IGN] classification barycentrique [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] échantillonnage de données [Termes IGN] image AVIRIS [Termes IGN] image hyperspectrale [Termes IGN] squelettisation [Termes IGN] utilisation du sol Résumé : (Auteur) Many manifold learning algorithms conduct an eigen vector analysis on a data-similarity matrix with a size of N×N, where N is the number of data points. Thus, the memory complexity of the analysis is no less than O(N2). We present in this article an incremental manifold learning approach to handle large hyperspectral data sets for land use identification. In our method, the number of dimensions for the high-dimensional hyperspectral-image data set is obtained with the training data set. A local curvature variation algorithm is utilized to sample a subset of data points as landmarks. Then a manifold skeleton is identified based on the landmarks. Our method is validated on three AVIRIS hyperspectral data sets, outperforming the comparison algorithms with a k–nearest-neighbor classifier and achieving the second best performance with support vector machine. Numéro de notice : A2021-375 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.87.7.445 Date de publication en ligne : 01/06/2021 En ligne : https://doi.org/10.14358/PERS.87.7.445 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97829 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2021061	SL	Revue	Centre de documentation	Revues en salle	Disponible