Centre de documentation
scientifique

Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks / Sina Mohammadi in ISPRS Journal of photogrammetry and remote sensing, vol 198 (April 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 198 (April 2023) . - pp 272 - 283 Titre : Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks Type de document : Article/Communication Auteurs : Sina Mohammadi, Auteur ; Mariana Belgiu, Auteur ; Alfred Stein, Auteur Année de publication : 2023 Article en page(s) : pp 272 - 283 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] cultures [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] série temporelle Résumé : (auteur) Deep learning methods have achieved promising results in crop mapping using satellite image time series. A challenge still remains on how to better learn discriminative feature representations to detect crop types when the model is applied to unseen data. To address this challenge and reveal the importance of proper supervision of deep neural networks in improving performance, we propose to supervise intermediate layers of a designed 3D Fully Convolutional Neural Network (FCN) by employing two middle supervision methods: Cross-entropy loss Middle Supervision (CE-MidS) and a novel middle supervision method, namely Supervised Contrastive loss Middle Supervision (SupCon-MidS). This method pulls together features belonging to the same class in embedding space, while pushing apart features from different classes. We demonstrate that SupCon-MidS enhances feature discrimination and clustering throughout the network, thereby improving the network performance. In addition, we employ two output supervision methods, namely F1 loss and Intersection Over Union (IOU) loss. Our experiments on identifying corn, soybean, and the class Other from Landsat image time series in the U.S. corn belt show that the best set-up of our method, namely IOU+SupCon-MidS, is able to outperform the state-of-the-art methods by scores of 3.5% and 0.5% on average when testing its accuracy across a different year (local test) and different regions (spatial test), respectively. Further, adding SupCon-MidS to the output supervision methods improves scores by 1.2% and 7.6% on average in local and spatial tests, respectively. We conclude that proper supervision of deep neural networks plays a significant role in improving crop mapping performance. The code and data are available at: https://github.com/Sina-Mohammadi/CropSupervision. Numéro de notice : A2023-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2023.03.007 Date de publication en ligne : 29/03/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.03.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103105 [article]

A new strategy for improving the accuracy of forest aboveground biomass estimates in an alpine region based on multi-source remote sensing / Yali Zhang in GIScience and remote sensing, vol 60 n° 1 (2023)  

Public [article]  inGIScience and remote sensing > vol 60 n° 1 (2023) . - n° 2163574 Titre : A new strategy for improving the accuracy of forest aboveground biomass estimates in an alpine region based on multi-source remote sensing Type de document : Article/Communication Auteurs : Yali Zhang, Auteur ; Ni Wang, Auteur ; Yuliang Wang, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 2163574 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biomasse aérienne [Termes IGN] biomasse forestière [Termes IGN] carte forestière [Termes IGN] Chine [Termes IGN] données multisources [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] image Landsat-TM [Termes IGN] image radar moirée [Termes IGN] image Sentinel-MSI [Termes IGN] phénologie [Termes IGN] puits de carbone [Termes IGN] santé des forêts Résumé : (auteur) Spatially explicit information on the distribution of dominant tree species groups and aboveground biomass (AGB) in forested areas is essential for developing targeted forest management and biodiversity conservation measures, as well as assessing forest carbon sequestration capacity. There is a shortage of continuously updated 30-m spatial resolution products for mapping dominant tree species groups. The vast majority of remote sensing-based AGB estimation approaches have relatively low accuracy for dominant tree species groups or forest types and are unsuitable for AGB modeling. Therefore, this study aims to develop an integrated framework that considers the phenological characteristics of different tree species to improve the mapping accuracies of forest dominant tree groups and corresponding AGB estimates. Thirty-meter resolution maps of dominant tree species groups were created using machine learning algorithms and phenological parameters. Features extracted from optical and radar images and phenological characteristics were used to construct AGB estimation models in a temporally consistent manner to improve the AGB estimation accuracy and perform dynamic AGB monitoring. The proposed method accurately characterized the dynamic distribution of the dominant tree species groups in the study area. The traditional AGB model that does not consider different forest types or species had an R2 value of 0.52, whereas the proposed model that considers phenology and forest types had an R2 value of 0.67. This result indicates that incorporating information on phenology and dominant species improves the accuracy of AGB estimations. The AGB in most regions was 30–55 t/ha, showing that the majority of the forests were young or middle-aged stands, and the areal percentage of AGB greater than 30 t/ha increased during the study period, suggesting an improvement in forest quality. Furthermore, the oak AGB was the highest, indicating that oak afforestation should be encouraged to enhance the carbon sequestration capacity of future forest ecosystems. The results provide new insights for researchers and managers to understand the trends of forest development and forest health, as well as technical information and a database for formulating more rational forest management strategies. Numéro de notice : A2023-121 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1080/15481603.2022.2163574 Date de publication en ligne : 03/01/2023 En ligne : https://doi.org/10.1080/15481603.2022.2163574 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102496 [article]

Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning / Thiên-Anh Nguyen in Remote sensing of environment, vol 281 (November 2022)  

Public [article]  inRemote sensing of environment > vol 281 (November 2022) . - n° 113217 Titre : Mapping forest in the Swiss Alps treeline ecotone with explainable deep learning Type de document : Article/Communication Auteurs : Thiên-Anh Nguyen, Auteur ; Benjamin Kellenberger, Auteur ; Devis Tuia, Auteur Année de publication : 2022 Article en page(s) : n° 113217 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Alpes [Termes IGN] apprentissage profond [Termes IGN] canopée [Termes IGN] carte forestière [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] écotone [Termes IGN] hauteur des arbres [Termes IGN] image à très haute résolution [Termes IGN] image aérienne [Termes IGN] image RVB [Termes IGN] inventaire forestier étranger (données) [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] Suisse Résumé : (auteur) Forest maps are essential to understand forest dynamics. Due to the increasing availability of remote sensing data and machine learning models like convolutional neural networks, forest maps can these days be created on large scales with high accuracy. Common methods usually predict a map from remote sensing images without deliberately considering intermediate semantic concepts that are relevant to the final map. This makes the mapping process difficult to interpret, especially when using opaque deep learning models. Moreover, such procedure is entirely agnostic to the definitions of the mapping targets (e.g., forest types depending on variables such as tree height and tree density). Common models can at best learn these rules implicitly from data, which greatly hinders trust in the produced maps. In this work, we aim at building an explainable deep learning model for forest mapping that leverages prior knowledge about forest definitions to provide explanations to its decisions. We propose a model that explicitly quantifies intermediate variables like tree height and tree canopy density involved in the forest definitions, corresponding to those used to create the forest maps for training the model in the first place, and combines them accordingly. We apply our model to mapping forest types using very high resolution aerial imagery and lay particular focus on the treeline ecotone at high altitudes, where forest boundaries are complex and highly dependent on the chosen forest definition. Results show that our rule-informed model is able to quantify intermediate key variables and predict forest maps that reflect forest definitions. Through its interpretable design, it is further able to reveal implicit patterns in the manually-annotated forest labels, which facilitates the analysis of the produced maps and their comparison with other datasets. Numéro de notice : A2022-794 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2022.113217 Date de publication en ligne : 01/09/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101928 [article]

Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information / Ozlem Akar in Geocarto international, vol 37 n° 22 ([10/10/2022])  

Public [article]  inGeocarto international > vol 37 n° 22 [10/10/2022] . - pp 6643 - 6670 Titre : Land use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information Type de document : Article/Communication Auteurs : Ozlem Akar, Auteur ; Esra Tunc Gormus, Auteur Année de publication : 2022 Article en page(s) : pp 6643 - 6670 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte d'occupation du sol [Termes IGN] carte de la végétation [Termes IGN] classification orientée objet [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] filtre de Gabor [Termes IGN] image hyperspectrale [Termes IGN] matrice de co-occurrence [Termes IGN] niveau de gris (image) [Termes IGN] texture d'image [Termes IGN] transformation en ondelettes [Termes IGN] Turquie Résumé : (auteur) Land use and Land cover (LULC) mapping is one of the most important application areas of remote sensing which requires both spectral and spatial resolutions in order to decrease the spectral ambiguity of different land cover types. Airborne hyperspectral images are among those data which perfectly suits to that kind of applications because of their high number of spectral bands and the ability to see small details on the field. As this technology has newly developed, most of the image processing methods are for the medium resolution sensors and they are not capable of dealing with high resolution images. Therefore, in this study a new framework is proposed to improve the classification accuracy of land use/cover mapping applications and to achieve a greater reliability in the process of mapping land use map using high resolution hyperspectral image data. In order to achieve it, spatial information is incorporated together with spectral information by exploiting feature extraction methods like Grey Level Co-occurrence Matrix (GLCM), Gabor and Morphological Attribute Profile (MAP) on dimensionally reduced image with highest accuracy. Then, machine learning algorithms like Random Forest (RF) and Support Vector Machine (SVM) are used to investigate the contribution of texture information in the classification of high resolution hyperspectral images. In addition to that, further analysis is conducted with object based RF classification to investigate the contribution of contextual information. Finally, overall accuracy, producer’s/user’s accuracy, the quantity and allocation based disagreements and location and quantity based kappa agreements are calculated together with McNemar tests for the accuracy assessment. According to our results, proposed framework which incorporates Gabor texture information and exploits Discrete Wavelet Transform based dimensionality reduction method increase the overall classification accuracy up to 9%. Amongst individual classes, Gabor features boosted classification accuracies of all the classes (soil, road, vegetation, building and shadow) to 7%, 6%, 6%, 8%, 9%, and 24% respectively with producer’s accuracy. Besides, 17% and 10% increase obtained in user’s accuracy with MAP (area) feature in classifying road and shadow classes respectively. Moreover, when the object based classification is conducted, it is seen that the OA of pixel based classification is increased further by 1.07%. An increase between 2% and 4% is achieved with producer’s accuracy in soil, vegetation and building classes and an increase between 1% and 3% is achieved by user’s accuracy in soil, road, vegetation and shadow classes. In the end, accurate LULC map is produced with object based RF classification of gabor features added airborne hyperspectral image which is dimensionally reduced with DWT method. Numéro de notice : A2022-729 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1944453 Date de publication en ligne : 09/11/2021 En ligne : https://doi.org/10.1080/10106049.2021.1944453 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101675 [article]

Riparian ecosystems mapping at fine scale: a density approach based on multi-temporal UAV photogrammetric point clouds / Elena Belcore in Remote sensing in ecology and conservation, vol 8 n° 5 (October 2022)  

Public [article]  inRemote sensing in ecology and conservation > vol 8 n° 5 (October 2022) . - pp 644 - 655 Titre : Riparian ecosystems mapping at fine scale: a density approach based on multi-temporal UAV photogrammetric point clouds Type de document : Article/Communication Auteurs : Elena Belcore, Auteur ; Melissa Latella, Auteur Année de publication : 2022 Article en page(s) : pp 644 - 655 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] carte de la végétation [Termes IGN] densité de la végétation [Termes IGN] détection d'objet [Termes IGN] forêt ripicole [Termes IGN] houppier [Termes IGN] image captée par drone [Termes IGN] Italie [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] orthophotoplan numérique [Termes IGN] semis de points [Termes IGN] structure-from-motion Résumé : (auteur) In recent years, numerous directives worldwide have addressed the conservation and restoration of riparian corridors, activities that rely on continuous vegetation mapping to understand its volumetric features and health status. Mapping riparian corridors requires not only fine-scale resolution but also the coverage of relatively large areas. The use of Unmanned Aerial Vehicles (UAV) allows for meeting both conditions, although the cost-effectiveness of their use is highly influenced by the type of sensor mounted on them. Few works have so far investigated the use of photogrammetric sensors for individual tree crown detection, despite being cheaper than the most common Light Detection and Ranging (LiDAR) ones. This work aims to improve the individual crown detection from UAV-photogrammetric datasets in a two fold way. Firstly, the effectiveness of a new approach that has already achieved interesting results in LiDAR applications was tested for photogrammetric point clouds. The test was carried out by comparing the accuracy achieved by the new approach, which is based on the point density features of the analysed dataset, with those related to the more common local maxima and textural methods. The results indicated the potentiality of the density-based method, which achieved accuracy values (0.76F-score) consistent with the traditional methods (0.49–0.80F-score range) but was less affected by under- and over-fitting. Secondly, the potential improvement of working on intra-annual multi-temporal datasets was assessed by applying the density-based approach to seven different scenarios, three of which were constituted by single-epoch datasets and the remaining given by the joining of the others. The F-score increased from 0.67 to 0.76 when passing from single- to multi-epoch datasets, aligning with the accuracy achieved by the new method when applied to LiDAR data. The results demonstrate the potential of multi-temporal acquisitions when performing individual crown detection from photogrammetric data. Numéro de notice : A2022-879 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1002/rse2.267 Date de publication en ligne : 22/03/2022 En ligne : https://doi.org/10.1002/rse2.267 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102193 [article]

Using multi-temporal tree inventory data in eucalypt forestry to benchmark global high-resolution canopy height models. A showcase in Mato Grosso, Brazil / Adrián Pascual in Ecological Informatics, vol 70 (September 2022)  

Permalink

Losses of tree cover in California driven by increasing fire disturbance and climate stress / Jonathan A. Wang in AGU Advances, vol 3 n° 4 (August 2022)  

Permalink

About tree height measurement: Theoretical and practical issues for uncertainty quantification and mapping / Samuele De petris in Forests, vol 13 n° 7 (July 2022)  

Permalink

The promising combination of a remote sensing approach and landscape connectivity modelling at a fine scale in urban planning / Elie Morin in Ecological indicators, vol 139 (June 2022)  

Permalink

Classification of vegetation classes by using time series of Sentinel-2 images for large scale mapping in Cameroon / Hermann Tagne in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)  

Permalink

Vegetation cover mapping from RGB webcam time series for land surface emissivity retrieval in high mountain areas / Benedikt Hiebl in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Permalink

Fusion of optical, radar and waveform LiDAR observations for land cover classification / Huiran Jin in ISPRS Journal of photogrammetry and remote sensing, vol 187 (May 2022)  

Permalink

Production of optimum forest roads and comparison of these routes with current forest roads: a case study in Maçka, Turkey / Faruk Yildirim in Geocarto international, vol 37 n° 8 ([01/05/2022])  

Permalink

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])  

Permalink

Parcel-based summer maize mapping and phenology estimation combined using Sentinel-2 and time series Sentinel-1 data / Yanyan Wang in International journal of applied Earth observation and geoinformation, vol 108 (April 2022)  

Permalink