Centre de documentation
scientifique

Predicting vegetation stratum occupancy from airborne LiDAR data with deep learning / Ekaterina Kalinicheva in International journal of applied Earth observation and geoinformation, vol 112 (August 2022)    

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 112 (August 2022) . - n° 102863 Titre : Predicting vegetation stratum occupancy from airborne LiDAR data with deep learning Type de document : Article/Communication Auteurs : Ekaterina Kalinicheva , Auteur ; Loïc Landrieu , Auteur ; Clément Mallet , Auteur ; Nesrine Chehata , Auteur Année de publication : 2022 Projets : TOSCA-FRISBEE / Article en page(s) : n° 102863 Note générale : bibliographie This study has been co-funded by CNES (TOSCA FRISBEE Project, convention no200769/00) and CONFETTI Project (Nouvelle Aquitaine Region project, France). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] apprentissage semi-dirigé [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] parcelle agricole [Termes IGN] régression [Termes IGN] semis de points [Termes IGN] strate végétale Résumé : (auteur) We propose a new deep learning-based method for estimating the occupancy of vegetation strata from airborne 3D LiDAR point clouds. Our model predicts rasterized occupancy maps for three vegetation strata corresponding to lower, medium, and higher cover. Our weakly-supervised training scheme allows our network to only be supervised with vegetation occupancy values aggregated over cylindrical plots containing thousands of points. Such ground truth is easier to produce than pixel-wise or point-wise annotations. Our method outperforms handcrafted and deep learning baselines in terms of precision by up to 30%, while simultaneously providing visual and interpretable predictions. We provide an open-source implementation along with a dataset of 199 agricultural plots to train and evaluate weakly supervised occupancy regression algorithms. Numéro de notice : A2022-578 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2022.102863 Date de publication en ligne : 19/07/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102863 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99425 [article]

Documents numériques

peut être téléchargé Predicting vegetation stratum ... - pdf auteur Adobe Acrobat PDF

Towards low vegetation identification: A new method for tree crown segmentation from LiDAR data based on a symmetrical structure detection algorithm (SSD) / Langning Huo in Remote sensing of environment, vol 270 (March 2022)  

Public [article]  inRemote sensing of environment > vol 270 (March 2022) . - n° 112857 Titre : Towards low vegetation identification: A new method for tree crown segmentation from LiDAR data based on a symmetrical structure detection algorithm (SSD) Type de document : Article/Communication Auteurs : Langning Huo, Auteur ; Eva Lindberg, Auteur ; Johan Holmgren, Auteur Année de publication : 2022 Article en page(s) : n° 112857 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] forêt boréale [Termes IGN] hauteur à la base du houppier [Termes IGN] houppier [Termes IGN] inventaire forestier étranger (données) [Termes IGN] segmentation [Termes IGN] semis de points [Termes IGN] sous-bois [Termes IGN] sous-étage [Termes IGN] strate végétale [Termes IGN] structure d'un peuplement forestier [Termes IGN] Suède Résumé : (auteur) Obtaining low vegetation data is important in order to quantify the structural characteristics of a forest. Dense three-dimensional (3D) laser scanning data can provide information on the vertical profile of a forest. However, most studies have focused on the dominant and subdominant layers of the forest, while few studies have tried to delineate the low vegetation. To address this issue, we propose a framework for individual tree crown (ITC) segmentation from laser data that focuses on both overstory and understory trees. The framework includes 1) a new algorithm (SSD) for 3D ITC segmentation of dominant trees, by detecting the symmetrical structure of the trees, and 2) removing points of dominant trees and mean shift clustering of the low vegetation. The framework was tested on a boreal forest in Sweden and the performance was compared 1) between plots with different stem density levels, vertical complexities, and tree species composition, and 2) using airborne laser scanning (ALS) data, terrestrial laser scanning (TLS) data, and merged ALS and TLS data (ALS + TLS data). The proposed framework achieved detection rates of 0.87 (ALS + TLS), 0.86 (TLS), and 0.76 (ALS) when validated with field-inventory data (of trees with a diameter at breast height ≥ 4 cm). When validating the estimated number of understory trees by visual interpretation, the framework achieved 19%, 21%, and 39% root-mean-square error values with ALS + TLS, TLS, and ALS data, respectively. These results show that the SSD algorithm can successfully separate laser points of overstory and understory trees, ensuring the detection and segmentation of low vegetation in forest. The proposed framework can be used with both ALS and TLS data, and achieve ITC segmentation for forests with various structural attributes. The results also illustrate the potential of using ALS data to delineate low vegetation. Numéro de notice : A2022-127 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112857 Date de publication en ligne : 03/01/2022 En ligne : https://doi.org/10.1016/j.rse.2021.112857 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99707 [article]

Relationships between species richness and ecosystem services in Amazonian forests strongly influenced by biogeographical strata and forest types / Gijs Steur in Scientific reports, vol 12 (2022)  

Public [article]  inScientific reports > vol 12 (2022) . - n° 5960 Titre : Relationships between species richness and ecosystem services in Amazonian forests strongly influenced by biogeographical strata and forest types Type de document : Article/Communication Auteurs : Gijs Steur, Auteur ; Hans Ter Steege, Auteur ; René W. Verburg, Auteur ; Daniel Sabatier, Auteur ; Jean-François Molino, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5960 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Amazonie [Termes IGN] forêt tropicale [Termes IGN] produit forestier non ligneux [Termes IGN] puits de carbone [Termes IGN] richesse floristique [Termes IGN] service écosystémique [Termes IGN] strate végétale [Termes IGN] volume en bois [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Despite increasing attention for relationships between species richness and ecosystem services, for tropical forests such relationships are still under discussion. Contradicting relationships have been reported concerning carbon stock, while little is known about relationships concerning timber stock and the abundance of non-timber forest product producing plant species (NTFP abundance). Using 151 1-ha plots, we related tree and arborescent palm species richness to carbon stock, timber stock and NTFP abundance across the Guiana Shield, and using 283 1-ha plots, to carbon stock across all of Amazonia. We analysed how environmental heterogeneity influenced these relationships, assessing differences across and within multiple forest types, biogeographic regions and subregions. Species richness showed significant relationships with all three ecosystem services, but relationships differed between forest types and among biogeographical strata. We found that species richness was positively associated to carbon stock in all biogeographical strata. This association became obscured by variation across biogeographical regions at the scale of Amazonia, resembling a Simpson’s paradox. By contrast, species richness was weakly or not significantly related to timber stock and NTFP abundance, suggesting that species richness is not a good predictor for these ecosystem services. Our findings illustrate the importance of environmental stratification in analysing biodiversity-ecosystem services relationships. Numéro de notice : A2022-308 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET Nature : Article DOI : 10.1038/s41598-022-09786-6 Date de publication en ligne : 08/04/2022 En ligne : http://dx.doi.org/10.1038/s41598-022-09786-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100403 [article]

Planning coastal Mediterranean stone pine (Pinus pinea L.) reforestations as a green infrastructure: combining GIS techniques and statistical analysis to identify management options / Luigi Portoghesi in Annals of forest research, vol 65 n° 1 (January - June 2022)  

Public [article]  inAnnals of forest research > vol 65 n° 1 (January - June 2022) . - pp 31 - 46 Titre : Planning coastal Mediterranean stone pine (Pinus pinea L.) reforestations as a green infrastructure: combining GIS techniques and statistical analysis to identify management options Type de document : Article/Communication Auteurs : Luigi Portoghesi, Auteur ; Antonio Tomao, Auteur ; Simone Bollati, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 31 - 46 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de groupement [Termes IGN] approche hiérarchique [Termes IGN] carte forestière [Termes IGN] Italie [Termes IGN] littoral méditerranéen [Termes IGN] peuplement pur [Termes IGN] Pinus pinea [Termes IGN] reboisement [Termes IGN] résilience écologique [Termes IGN] structure de la végétation [Termes IGN] système d'information géographique [Termes IGN] utilisation du sol [Vedettes matières IGN] Sylviculture Résumé : (auteur) Mediterranean stone pine reforestations are common characteristics of the Italian Tyrrhenian coast, which mostly maintain uniform and monolayered stand structures. However, improving structural diversity is an effective climate change adaptation strategy in forest management. The aim of this study was to implement a methodology which allows distinct reforested areas such as a single green infrastructure to be managed according to the surrounding land use and the characteristics of the forest stands. 240 hectares of Mediterranean stone pine forests located along a 16 km strip of the Lazio coast (Central Italy) were mapped. Twelve attributes describing the pine stands and showing possible constraints for future management decisions were associated to each forest patch. A hierarchical cluster analysis was performed to group the pinewood patches according to their similarity level and five different groups were identified. For each group, different silvicultural methods were proposed to guide the compositional and structural evolution of the stands, in order to make them suitable for providing services required locally and increasing overall diversity at landscape scale. The results of the study highlight how coastal land uses can offer effective inputs to differentiate the management of forest systems and therefore achieve greater variety and resilience in the landscape over time. This approach is particularly useful in the case of very homogeneous stands such as the stone pine reforestations under study. Numéro de notice : A2022-798 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.15287/afr.2022.2176 Date de publication en ligne : 27/06/2022 En ligne : https://doi.org/10.15287/afr.2022.2176 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101958 [article]

Self-thinning tree mortality models that account for vertical stand structure, species mixing and climate / David I. Forrester in Forest ecology and management, Vol 487 ([01/05/2021])  

Public [article]  inForest ecology and management > Vol 487 [01/05/2021] . - n° 118936 Titre : Self-thinning tree mortality models that account for vertical stand structure, species mixing and climate Type de document : Article/Communication Auteurs : David I. Forrester, Auteur ; Thomas G. Backer, Auteur ; Stephen R. Elms, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 118936 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Abies alba [Termes IGN] Australie [Termes IGN] auto-éclaircie [Termes IGN] changement climatique [Termes IGN] Chine [Termes IGN] dépérissement [Termes IGN] Eucalyptus nitens [Termes IGN] Fagus sylvatica [Termes IGN] modèle de croissance végétale [Termes IGN] mortalité [Termes IGN] peuplement forestier [Termes IGN] peuplement mélangé [Termes IGN] Picea abies [Termes IGN] Pinus sylvestris [Termes IGN] Quercus pedunculata [Termes IGN] Quercus sessiliflora [Termes IGN] structure de la végétation [Termes IGN] Suisse [Vedettes matières IGN] Sylviculture Résumé : (auteur) Self-thinning dynamics are often considered when managing stand density in forests and are used to constrain forest growth models. However, self-thinning relationships are often quantified using only data at a conceptualised self-thinning line, even though self-thinning can begin before the stand actually reaches a self-thinning line. Also, few self-thinning relationships account for the effects of species composition in mixed-species forests, and stand structure such as relative height of species (in mixtures), and/or size or age cohorts in uneven-aged forests. Such considerations may be important given the effects of global climate change and interest in mixed-species and uneven-aged forests. The objective of this study was to develop self-thinning relationships based on changes in the tree density relative to mean tree diameter, instead of focusing only on data for state variables (e.g. tree density) at the self-thinning line. This was done while also considering how the change in tree density is influenced by site quality and stand structure (species composition and relative height). The relationships were modelled using data from temperate Australian Eucalyptus plantations (436 plots), subtropical forests in China (88 plots), and temperate forests in Switzerland (1055 plots). Zero-inflated and hurdle generalized linear models with Poisson and negative binomial distributions were fit for several species, as well as for all-species equations. The intercepts and slopes of the self-thinning lines were higher than many published studies which may have resulted from both the less restrictive equation form and data selection. The rates of self-thinning often decreased as the proportion of the object species increased, as relative height increased (species or size cohort became more dominant), and as site (quality) index increased. The effects of aridity varied between species, with self-thinning increasing with aridity index for Abies alba, Pinus sylvestris, Quercus petraea and Quercus robur, but decreasing with aridity index for Eucalyptus nitens, Fagus sylvatica and Picea abies as sites became wetter and cooler. Self-thinning model parameters were not correlated with species traits, including specific leaf area, wood basic density or crown diameter – stem diameter allometry. All-species self-thinning relationships based on all data could be adjusted using a correction factor for rarer species where there were insufficient data to develop species-specific equations. The approach and equations developed could be used in forest growth models to calculate how the tree density declines as mean tree size increases, as height changes relative to other cohorts or species, as species proportions change, and as climatic and edaphic conditions change. Numéro de notice : A2021-355 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1016/j.foreco.2021.118936 Date de publication en ligne : 18/02/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.118936 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97612 [article]

Sensitivity of voxel-based estimations of leaf area density with terrestrial LiDAR to vegetation structure and sampling limitations: A simulation experiment / Maxime Soma in Remote sensing of environment, vol 257 (May 2021)  

Permalink

Proposition d’un référentiel de description et de détection de la végétation dans une agglomération / Mathilde Segaud (2021) 

Permalink

The effect of leaf-on and leaf-off forest canopy conditions on LiDAR derived estimations of forest structural diversity / Sophie Davison in International journal of applied Earth observation and geoinformation, vol 92 (October 2020)  

Permalink

Digital terrain, surface, and canopy height models from InSAR backscatter-height histograms / Gustavo H.X. Shiroma in IEEE Transactions on geoscience and remote sensing, vol 58 n° 6 (June 2020)  

Permalink

Estimation et suivi de la ressource en bois en France métropolitaine par valorisation des séries multi-temporelles à haute résolution spatiale d'images optiques (Sentinel-2) et radar (Sentinel-1, ALOS-PALSAR) / David Morin (2020)  

Permalink

Can forest structural diversity be a response to anthropogenic stress? A case study in old-growth fir Abies alba Mill. stands / Rafał Podlaski in Annals of Forest Science, vol 75 n° 4 (December 2018)  

Permalink

Estimating forest structural attributes using UAV-LiDAR data in Ginkgo plantations / Kun Liu in ISPRS Journal of photogrammetry and remote sensing, vol 146 (December 2018)  

Permalink

Responses of the structure and function of the understory plant communities to precipitation reduction across forest ecosystems in Germany / Katja Felsmann in Annals of Forest Science, vol 75 n° 1 (March 2018)  

Permalink

Predicting temperate forest stand types using only structural profiles from discrete return airborne lidar / Melissa Fedrigo in ISPRS Journal of photogrammetry and remote sensing, vol 136 (February 2018)  

Permalink

Wind loads and competition for light sculpt trees into self-similar structures / Christophe Eloy in Nature communications, vol 8 (2017)  

Permalink