Centre dedocumentation
scientifique

Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery / Run Yu in Forest ecology and management, vol 497 (1 October 2021)  

Public [article]  inForest ecology and management > vol 497 (1 October 2021) . - n° 119493 Titre : Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery Type de document : Article/Communication Auteurs : Run Yu, Auteur ; Youqing Luo, Auteur ; Quan Zhou, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 119493 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] Chine [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dépérissement [Termes IGN] image captée par drone [Termes IGN] image multibande [Termes IGN] maladie phytosanitaire [Termes IGN] milieu tropical [Termes IGN] peuplement mélangé [Termes IGN] Pinus (genre) [Termes IGN] Pinus massoniana [Termes IGN] réflectance spectrale [Termes IGN] Ulmus (genre) Résumé : (auteur) Pine wilt disease (PWD) is a global devastating threat to forest ecosystems. Therefore, a feasible and effective approach to precisely monitor PWD infection is indispensable, especially at the early stages. However, a precise definition of “early stage” and a rapid and high-efficiency method to detect PWD infection have not been well established. In this study, we systematically divided the PWD infection into green, early, middle, and late stages based on the needle color, the resin secretion, and whether the pine wood nematode (PWN) was carried. Simultaneously, an unmanned aerial vehicle (UAV) equipped with multispectral cameras was used to obtain images. Two target detection algorithms (Faster R-CNN and YOLOv4) and two traditional machine learning algorithms based on feature extraction (random forest and support vector machine) were employed to realize the recognition of infected pine trees. Moreover, we took into consideration of the influence of green broad-leaved trees on the identification of pine trees at the early stage of PWD infection. We obtained the following results: (1) the accuracy of Faster R-CNN (60.98–66.7%) was higher than that of YOLOv4 (57.07–63.55%), but YOLOv4 outperformed in terms of model size, processing speed, training time, and testing time; (2) although the traditional machine learning models had higher accuracy (73.28–79.64%), they were not able to directly identify the object from the images; (3) the accuracy of early detection of PWD infection showed an increase of 3.72–4.29%, from 42.36–44.59% to 46.08–48.88%, when broad-leaved trees were considered. In this study, the combination of UAV-based multispectral images and target detection algorithms allowed us to monitor the occurrence of PWD and obtain the distribution of infected trees at an early stage, which can provide technical support for the prevention and control of PWD. Numéro de notice : A2021-658 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2021.119493 En ligne : https://doi.org/10.1016/j.foreco.2021.119493 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98395 [article]

A comparison of ALS and dense photogrammetric point clouds for individual tree detection in radiata pine plantations / Irfan A. Iqbal in Remote sensing, vol 13 n° 17 (September-1 2021)  

Public [article]  inRemote sensing > vol 13 n° 17 (September-1 2021) . - n° 3536 Titre : A comparison of ALS and dense photogrammetric point clouds for individual tree detection in radiata pine plantations Type de document : Article/Communication Auteurs : Irfan A. Iqbal, Auteur ; Jon Osborn, Auteur ; Christine Stone, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 3536 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] arbre isolé [Termes IGN] détection d'arbres [Termes IGN] données lidar [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] photogrammétrie aérienne [Termes IGN] photographie aérienne [Termes IGN] Pinus radiata [Termes IGN] semis de points [Termes IGN] Tasmanie [Termes IGN] télémétrie laser aéroporté Numéro de notice : A2021-689 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs13173536 date de publication en ligne : 06/09/2021 En ligne : https://doi.org/10.3390/rs13173536 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98425 [article]

Coniferous and broad-leaved forest distinguishing using L-band polarimetric SAR data / Fang Shang in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 9 (September 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > Vol 59 n° 9 (September 2021) . - pp 7487 - 7499 Titre : Coniferous and broad-leaved forest distinguishing using L-band polarimetric SAR data Type de document : Article/Communication Auteurs : Fang Shang, Auteur ; Taiga Saito, Auteur ; Saya Ohi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 7487 - 7499 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] bande L [Termes IGN] détection de changement [Termes IGN] détection de cible [Termes IGN] distribution spatiale [Termes IGN] forêt de feuillus [Termes IGN] image ALOS-PALSAR [Termes IGN] image radar moirée [Termes IGN] Japon [Termes IGN] Pinophyta [Termes IGN] polarimétrie radar Résumé : (auteur) This article proposes a coniferous and broad-leaved forest distinguishing method using L-band polarimetric SAR data based on the structure-orientation parameter. The structure-orientation parameter is one of the averaged Stokes vector-based discriminators which is sensitive to the composition of equivalent horizontal and vertical structures. In the proposed method, the structure-orientation parameters is compensated by employing the scattered power information to remove the influence of the topography. The final distinguishing result is generated based on the statistical feature of the compensated parameters. The experiments using several sets of ALOS2-PALSAR2 level 1.1 data prove that the proposed method has high performance for forest-type distinguishing. Numéro de notice : A2021-648 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3032468 date de publication en ligne : 03/11/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3032468 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98355 [article]

Using electrical resistivity tomography to detect wetwood and estimate moisture content in silver fir (Abies alba Mill.) / Ludovic Martin in Annals of Forest Science [en ligne], vol 78 n° 3 (September 2021)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 78 n° 3 (September 2021) . - n° 65 Titre : Using electrical resistivity tomography to detect wetwood and estimate moisture content in silver fir (Abies alba Mill.) Type de document : Article/Communication Auteurs : Ludovic Martin, Auteur ; Sébastien Cochard, Auteur ; Stefan Mayr, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 65 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Abies alba [Termes IGN] bois sur pied [Termes IGN] filière bois - forêt [Termes IGN] forêt humide [Termes IGN] humidité du sol [Termes IGN] Massif central (France) [Termes IGN] résistivité [Termes IGN] teneur en eau de la végétation [Termes IGN] tomographie Résumé : (auteur) Key message : Using several experimental approaches, we have demonstrated that electrical resistivity tomography (ERT) is a reliable nondestructive tool for estimating the moisture content of heartwood in situ. ERT measurements show that water pockets in heartwood (wetwood) are present in a large majority (90%) of silver fir ( Abies alba Mill.) trunks. Context : For wood professionals, the presence of wetwood in wood logs leads to an increase in costs, especially during the drying process. Assessing these internal properties in situ with a nondestructive method will provide reliable information for improved management of respective forests. Aims : The objective of this study was to evaluate the efficiency of the electrical resistivity tomography (ERT) tool to detect wetwood in standing trees and to estimate the mean moisture content (MC) of silver fir trunks. Methods : The study was carried out in 3 forests located in the region “Massif Central” in France. We selected 58 silver fir trees, visually healthy and without visible default. Each tree has been subject to regular ERT measurements for more than a year. At the same time, one to three cores were taken from each tree in order to measure the actual MC of the wood. Results : 90% of the silver fir trees showed the presence of wetwood in their heartwood. Our results showed a significant correlation between the mean heartwood MC measured on cores and the mean electrical resistivity (ER) obtained with ERT. Conclusion : The presence of wetwood occurs in a high proportion of the silver fir trees studied, and (ii) ERT can be used to estimate the average MC of the heartwood of standing trees. However, the data provided by ERT vary seasonally and do not allow the precise location of wetwood. Numéro de notice : A2021-622 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-021-01078-9 date de publication en ligne : 27/07/2021 En ligne : https://doi.org/10.1007/s13595-021-01078-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98244 [article]

Spatial patterns of living and dead small trees in subalpine Norway spruce forest reserves in Switzerland / Eva Bianchi in Forest ecology and management, vol 494 (15 August 2021)  

Public [article]  inForest ecology and management > vol 494 (15 August 2021) . - n° 119315 Titre : Spatial patterns of living and dead small trees in subalpine Norway spruce forest reserves in Switzerland Type de document : Article/Communication Auteurs : Eva Bianchi, Auteur ; Harald Bugmann, Auteur ; Martina Lena Hobi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 119315 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de groupement [Termes IGN] distance [Termes IGN] espace topologique [Termes IGN] fonction K de Ripley [Termes IGN] forêt alpestre [Termes IGN] forêt subalpine [Termes IGN] mortalité [Termes IGN] Picea abies [Termes IGN] régénération (sylviculture) [Termes IGN] réserve forestière [Termes IGN] Suisse [Termes IGN] topographie locale [Termes IGN] voisinage (topologie) [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Spatial patterns can reveal a lot about ecological processes, but our knowledge of the spatial ecology of tree regeneration at a fine scale is quite limited. Therefore, we studied the spatial patterns of living and dead small trees in two subalpine Norway spruce forest reserves in Switzerland (Scatlè and Bödmerenwald) using three types of analyses. First, we investigated the distances of small trees to the nearest large neighboring tree and, by using maximum distances as indicator, inferred the size of forest gaps, detecting mainly forest gaps of small size, although with two exceptions that were driven by large-scale disturbances. Second, we accounted for spatial inhomogeneity in the pattern of small and large trees (i.e., variations in local tree densities) by including environmental covariates in point pattern models. Latitude (within the forest reserve), elevation and aspect contributed significantly to explaining the density of living and dead small trees, and partly of living and dead large trees. Yet, the influence of these environmental covariates varied between the two reserves due to their different topography and peculiar site conditions. Third, we analyzed neighborhood interactions between small and large trees based on the vicinity and size of trees. In both forest reserves, small living trees were randomly dispersed around large dead trees over a broad range of distances and, at certain distances in one reserve, even dispersed away from them. Small living trees further showed clustering around large living trees at short distances and dispersion at large distances. Small dead trees featured mainly a random pattern, although with a tendency to cluster around large neighbors at short distances, irrespective whether these were living or dead. Yet, the weakening of clustering with increasing distances indicates that the influence of large trees on small trees varies with spatial scale and thus that these neighborhood interactions are scale-dependent. Overall, our study contributes to a better understanding of the spatial ecology of mortality in small trees and ultimately of tree regeneration processes and stand dynamics in mountain forests. Numéro de notice : A2021-583 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2021.119315 date de publication en ligne : 11/05/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119315 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98198 [article]

Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN) / Zhenbang Hao in ISPRS Journal of photogrammetry and remote sensing, vol 178 (August 2021)  

Permalink

Forest floor bryophyte and lichen diversity in Scots pine and Norway spruce production forests / Lisa Petersson in Forest ecology and management, vol 493 (1st August 2021)  

Permalink

Detecting structural changes induced by Heterobasidion root rot on Scots pines using terrestrial laser scanning / Timo P Pitkänen in Forest ecology and management, vol 492 (15 July 2021)  

Permalink

Estimation of biomass increase and CUE at a young temperate scots pine stand concerning drought occurrence by combining eddy covariance and biometric methods / Paulina Dukat in Forests, vol 12 n° 7 (July 2021)  

Permalink

Phenotypic variability and differences in the drought response of Norway spruce pendula and pyramidalis half-sib families / Marius Budeanu in Forests, vol 12 n° 7 (July 2021)  

Permalink

The presence of shade-intolerant conifers facilitates the regeneration of Quercus petraea in mixed stands / Jeremy Borderieux in Forest ecology and management, vol 491 (1st July 2021)  

Permalink

Unexpected negative effect of available water capacity detected on recent conifer forest growth trends across wide environmental gradients / Clémentine Ols in Ecosystems, vol 24 n° inconnu ([01/07/2021])  

Permalink

Forest cover mapping and Pinus species classification using very high-resolution satellite images and random forest / Laura Alonso-Martinez in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2-2021 (July 2021)  

Permalink

Characterization of mixed and monospecific stands of Scots pine and Maritime pine: soil profile, physiography, climate and vegetation cover data / Daphne Lopez-Marcos in Annals of Forest Science [en ligne], vol 78 n° 2 (June 2021)  

Permalink

Predicting tree species based on the geometry and density of aerial laser scanning point cloud of treetops / Nina Kranjec in Geodetski vestnik, vol 65 n° 2 (June - August 2021)  

Permalink