Centre de documentation
scientifique

Dépouillements

Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information / Murali Krishna Gumma in Geocarto international, vol 37 n° 7 ([15/04/2022])  

Public [article]  inGeocarto international > vol 37 n° 7 [15/04/2022] . - pp 1833 - 1849 Titre : Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information Type de document : Article/Communication Auteurs : Murali Krishna Gumma, Auteur ; Kimeera Tummala, Auteur ; Sreenath Dixit, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1833 - 1849 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] appariement spectral [Termes IGN] blé (céréale) [Termes IGN] carte de la végétation [Termes IGN] distribution spatiale [Termes IGN] image Sentinel-MSI [Termes IGN] Inde [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] série temporelle [Termes IGN] surface cultivée [Termes IGN] variation saisonnière Résumé : (auteur) Accurate monitoring of croplands helps in making decisions (for insurance claims, crop management and contingency plans) at the macro-level, especially in drylands where variability in cropping is very high owing to erratic weather conditions. Dryland cereals and grain legumes are key to ensuring the food and nutritional security of a large number of vulnerable populations living in the drylands. Reliable information on area cultivated to such crops forms part of the national accounting of food production and supply in many Asian countries, many of which are employing remote sensing tools to improve the accuracy of assessments of cultivated areas. This paper assesses the capabilities and limitations of mapping cultivated areas in the Rabi (winter) season and corresponding cropping patterns in three districts characterized by small-plot agriculture. The study used Sentinel-2 Normalized Difference Vegetation Index (NDVI) 15-day time-series at 10 m resolution by employing a Spectral Matching Technique (SMT) approach. The use of SMT is based on the well-studied relationship between temporal NDVI signatures and crop phenology. The rabi season in India, dominated by non-rainy days, is best suited for the application of this method, as persistent cloud cover will hamper the availability of images necessary to generate clearly differentiating temporal signatures. Our study showed that the temporal signatures of wheat, chickpea and mustard are easily distinguishable, enabling an overall accuracy of 84%, with wheat and mustard achieving 86% and 94% accuracies, respectively. The most significant misclassifications were in irrigated areas for mustard and wheat, in small-plot mustard fields covered by trees and in fragmented chickpea areas. A comparison of district-wise national crop statistics and those obtained from this study revealed a correlation of 96%. Numéro de notice : A2022-497 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1805029 Date de publication en ligne : 18/08/2020 En ligne : https://doi.org/10.1080/10106049.2020.1805029 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100989 [article]

Spectral-spatial classification method for hyperspectral images using stacked sparse autoencoder suitable in limited labelled samples situation / Seyyed Ali Ahmadi in Geocarto international, vol 37 n° 7 ([15/04/2022])  

Public [article]  inGeocarto international > vol 37 n° 7 [15/04/2022] . - pp 2031 - 2054 Titre : Spectral-spatial classification method for hyperspectral images using stacked sparse autoencoder suitable in limited labelled samples situation Type de document : Article/Communication Auteurs : Seyyed Ali Ahmadi, Auteur ; Nasser Mehrshad, Auteur ; Seyyed Mohammadali Arghavan, Auteur Année de publication : 2022 Article en page(s) : pp 2031 - 2054 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de sensibilité [Termes IGN] apprentissage profond [Termes IGN] données étiquetées d'entrainement [Termes IGN] échantillonnage de données [Termes IGN] filtre de Gabor [Termes IGN] image hyperspectrale Résumé : (auteur) Recently, deep learning (DL)-based methods have attracted increasing attention for hyperspectral images (HSIs) classification. However, the complex structure and limited number of labelled training samples of HSIs negatively affect the performance of DL models. In this paper, a spectral-spatial classification method is proposed based on the combination of local and global spatial information, including extended multi-attribute profiles and multiscale Gabor features, with sparse stacked autoencoder (GEAE). GEAE stacks the spatial and spectral information to form the fused features. Also, GEAE generates virtual samples using weighted average of available samples for expanding the training set so that many parameters of DL network can be learned optimally in limited labelled samples situations. Therefore, the similarity between samples is determined with distance metric learning to overcome the problems of Euclidean distance-based similarity metrics. The experimental results on three HSIs datasets demonstrate the effectiveness of the GEAE in comparison to some existing classification methods. Numéro de notice : A2022-498 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1797188 Date de publication en ligne : 10/08/2020 En ligne : https://doi.org/10.1080/10106049.2020.1797188 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100990 [article]