Centre dedocumentation
scientifique

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 219 - 230 Titre : Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees Type de document : Article/Communication Auteurs : Hamid Hamraz, Auteur ; Nathan B. Jacobs, Auteur ; Marco A. Contreras, Auteur ; Chase H. Clark, Auteur Année de publication : 2019 Article en page(s) : pp 219 - 230 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] houppier [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] semis de points Résumé : (auteur) The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees segmented from airborne LiDAR data. To enable processing by a deep convolutional neural network (CNN), we designed two discrete representations using leaf-off and leaf-on LiDAR data: a digital surface model with four channels (DSM × 4) and a set of four 2D views (4 × 2D). A training dataset of tree crowns was generated via segmentation of tree crowns, followed by co-registration with field data. Potential mislabels due to GPS error or tree leaning were corrected using a statistical ensemble filtering procedure. Because the training data was heavily unbalanced (~8% conifers), we trained an ensemble of CNNs on random balanced sub-samples. Benchmarked against multiple traditional shallow learning methods using manually designed features, the CNNs improved accuracies up to 14%. The 4 × 2D representation yielded similar classification accuracies to the DSM × 4 representation (~82% coniferous and ~90% deciduous) while converging faster. Further experimentation showed that early/late fusion of the channels in the representations did not affect the accuracies in a significant way. The data augmentation that was used for the CNN training improved the classification accuracies, but more real training instances (especially coniferous) likely results in much stronger improvements. Leaf-off LiDAR data were the primary source of useful information, which is likely due to the perennial nature of coniferous foliage. LiDAR intensity values also proved to be useful, but normalization yielded no significant improvement. As we observed, large training data may compensate for the lack of a subset of important domain data. Lastly, the classification accuracies of overstory trees (~90%) were more balanced than those of understory trees (~90% deciduous and ~65% coniferous), which is likely due to the incomplete capture of understory tree crowns via airborne LiDAR. In domains like remote sensing and biomedical imaging, where the data contain a large amount of information and are not friendly to human visual system, human-designed features may become suboptimal. As exemplified by this study, automatic, objective derivation of optimal features via deep learning can improve prediction tasks in such domains. Numéro de notice : A2019-547 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.011 date de publication en ligne : 03/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94192 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019121	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019123	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019122	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Phosphorus availability in relation to soil properties and forest productivity in Pinus sylvestris L. plantations / Teresa Bueis in Annals of Forest Science [en ligne], Vol 76 n° 4 (December 2019)  

Public [article]  inAnnals of Forest Science [en ligne] > Vol 76 n° 4 (December 2019) Titre : Phosphorus availability in relation to soil properties and forest productivity in Pinus sylvestris L. plantations Type de document : Article/Communication Auteurs : Teresa Bueis, Auteur ; Felipe Bravo, Auteur ; Valentin Pando, Auteur ; et al., Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] biomasse forestière [Termes descripteurs IGN] écosystème forestier [Termes descripteurs IGN] Espagne [Termes descripteurs IGN] industrie forestière [Termes descripteurs IGN] phosphore [Termes descripteurs IGN] Pinus sylvestris [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Key message : Pinus sylvestris L. productivity in Spanish plantations is driven by P availability, which, in turn, is determined by the activity of soil microorganisms, responsible for inorganic P solubilization; Fe and Al contents, responsible for P retention; and organic matter, which is source of organic P, inhibits its precipitation as insoluble compounds, and reduces P retention. Context : Phosphorus is often a limiting nutrient in forest ecosystems mainly due to the low solubility of P compounds and the sorption processes occurring in soils. Aims : The main aims of this work were to evaluate soil P availability, to assess which soil properties are driving P availability, and to study whether soil P availability is determining forest productivity in Pinus sylvestris L. plantations in Northern Spain. Methods : Soil properties and forest productivity were studied in 34 plots located in monospecific P. sylvestris plantations. Tiessen and Moir (Canadian Society of Soil Science 75–86, 1993) sequential fractionation method was carried out to determine different forms of soil P and to provide a comprehensive assessment of available P in soils. To explore the relationships between these variables, canonical correlation analyses and Pearson’s correlations were studied. Results : Significant correlations were found between P fractions and soil properties related to Fe and Al contents, organic matter, and microbial biomass. Besides, significant correlations were found between site index and the studied P fractions except for P extracted with anion exchange membrane (PAEM) and the recalcitrant P fraction. Conclusion : In the studied soils, P availability is low and the predominant fractions of P are the recalcitrant forms. Aluminum and iron contents in the soils studied play an important role in sorption processes related to the highly and moderately labile P fractions and the organic phosphorus. P availability seems to be regulated by both processes: biochemical mineralization, where phosphatase activity is relevant, and biological mineralization of the soil organic matter. Phosphorus availability affects forest productivity in the Pinus sylvestris plantations studied. Numéro de notice : A2019-531 Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-019-0882-3 date de publication en ligne : 18/10/2019 En ligne : https://doi.org/10.1007/s13595-019-0882-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94119 [article]

Mapping dead forest cover using a deep convolutional neural network and digital aerial photography / Jean-Daniel Sylvain in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 156 (October 2019) . - pp 14 - 26 Titre : Mapping dead forest cover using a deep convolutional neural network and digital aerial photography Type de document : Article/Communication Auteurs : Jean-Daniel Sylvain, Auteur ; Guillaume Drolet, Auteur ; Nicolas Brown, Auteur Année de publication : 2019 Article en page(s) : pp 14 - 26 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre mort [Termes descripteurs IGN] base de données forestières [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] feuillu [Termes descripteurs IGN] forêt boréale [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] peuplement mélangé [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] Québec (Canada) [Termes descripteurs IGN] santé des forêts Résumé : (Auteur) Tree mortality is an important forest ecosystem variable having uses in many applications such as forest health assessment, modelling stand dynamics and productivity, or planning wood harvesting operations. Because tree mortality is a spatially and temporally erratic process, rates and spatial patterns of tree mortality are difficult to estimate with traditional inventory methods. Remote sensing imagery has the potential to detect tree mortality at spatial scales required for accurately characterizing this process (e.g., landscape, region). Many efforts have been made in this sense, mostly using pixel- or object-based methods. In this study, we explored the potential of deep Convolutional Neural Networks (CNNs) to detect and map tree health status and functional type over entire regions. To do this, we built a database of around 290,000 photo-interpreted trees that served to extract and label image windows from 20 cm-resolution digital aerial images, for use in CNN training and evaluation. In this process, we also evaluated the effect of window size and spectral channel selection on classification accuracy, and we assessed if multiple realizations of a CNN, generated using different weight initializations, can be aggregated to provide more robust predictions. Finally, we extended our model with 5 additional classes to account for the diversity of landcovers found in our study area. When predicting tree health status only (live or dead), we obtained test accuracies of up to 94%, and up to 86% when predicting functional type only (broadleaf or needleleaf). Channel selection had a limited impact on overall classification accuracy, while window size increased the ability of the CNNs to predict plant functional type. The aggregation of multiple realizations of a CNN allowed us to avoid the selection of suboptimal models and help to remove much of the speckle effect when predicting on new aerial images. Test accuracies of plant functional type and health status were not affected in the extended model and were all above 95% for the 5 extra classes. Our results demonstrate the robustness of the CNN for between-scene variations in aerial photography and also suggest that this approach can be applied at operational level to map tree mortality across extensive territories. Numéro de notice : A2019-316 Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2019.07.010 date de publication en ligne : 02/08/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.07.010 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93353 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019101	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019103	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019102	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Transferability and calibration of airborne laser scanning based mixed-effects models to estimate the attributes of sawlog-sized Scots pines / Lauri Korhonen in Silva fennica, vol 53 n° 3 (2019)  

Public [article]  inSilva fennica > vol 53 n° 3 (2019) Titre : Transferability and calibration of airborne laser scanning based mixed-effects models to estimate the attributes of sawlog-sized Scots pines Type de document : Article/Communication Auteurs : Lauri Korhonen, Auteur ; Jaakko Repola, Auteur ; Tomi Karjalainen, Auteur ; Petteri Packalen, Auteur ; Matti Maltamo, Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] détection d'arbres [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] erreur systématique [Termes descripteurs IGN] estimation statistique [Termes descripteurs IGN] étalonnage de modèle [Termes descripteurs IGN] hauteur à la base du houppier [Termes descripteurs IGN] houppier [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] lasergrammétrie [Termes descripteurs IGN] Pinus sylvestris [Termes descripteurs IGN] placette d'échantillonnage [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Airborne laser scanning (ALS) data is nowadays often available for forest inventory purposes, but adequate field data for constructing new forest attribute models for each area may be lacking. Thus there is a need to study the transferability of existing ALS-based models among different inventory areas. The objective of our study was to apply ALS-based mixed models to estimate the diameter, height and crown base height of individual sawlog sized Scots pines (Pinus sylvestrisL.) at three different inventory sites in eastern Finland. Different ALS sensors and acquisition parameters were used at each site. Multivariate mixed-effects models were fitted at one site and the models were validated at two independent test sites. Validation was carried out by applying the fixed parts of the mixed models as such, and by calibrating them using 1–3 sample trees per plot. The results showed that the relative RMSEs of the predictions were 1.2–6.5 percent points larger at the test sites compared to the training site. Systematic errors of 2.4–6.2 percent points also emerged at the test sites. However, both the RMSEs and the systematic errors decreased with calibration. The results showed that mixed-effects models of individual tree attributes can be successfully transferred and calibrated to other ALS inventory areas in a level of accuracy that appears suitable for practical applications. Numéro de notice : A2019-379 Thématique : FORET/IMAGERIE Nature : Article DOI : 10.14214/sf.10179 date de publication en ligne : 31/07/2019 En ligne : https://doi.org/10.14214/sf.10179 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93446 [article]

Vulnerability of forest ecosystems to fire in the French Alps / Sylvain Dupire in European Journal of Forest Research, Vol 138 n° 5 (octobre 2019)  

Public [article]  inEuropean Journal of Forest Research > Vol 138 n° 5 (octobre 2019) . - pp 813 – 830 Titre : Vulnerability of forest ecosystems to fire in the French Alps Type de document : Article/Communication Auteurs : Sylvain Dupire, Auteur ; Thomas Curt, Auteur ; Sylvain Bigot, Auteur ; Thibaut Fréjaville, Auteur Année de publication : 2019 Article en page(s) : pp 813 – 830 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] canopée [Termes descripteurs IGN] castanea sativa [Termes descripteurs IGN] changement climatique [Termes descripteurs IGN] diamètre à hauteur de poitrine [Termes descripteurs IGN] écosystème forestier [Termes descripteurs IGN] Fagus (genre) [Termes descripteurs IGN] forêt alpestre [Termes descripteurs IGN] France (administrative) [Termes descripteurs IGN] houppier [Termes descripteurs IGN] incendie de forêt [Termes descripteurs IGN] inventaire forestier national (données France) [Termes descripteurs IGN] larix decidua [Termes descripteurs IGN] logiciel de simulation [Termes descripteurs IGN] mortalité [Termes descripteurs IGN] Pinus sylvestris [Termes descripteurs IGN] sécheresse [Termes descripteurs IGN] variation saisonnière [Termes descripteurs IGN] vulnérabilité [Vedettes matières IGN] Végétation et changement climatique Résumé : (auteur) Forest fires are expected to be more frequent and more intense with climate change, including in temperate and mountain forest ecosystems. In the Alps, forest vulnerability to fire resulting from interactions between climate, fuel types, vegetation structure and tree resistance to fire is little understood. This paper aims at identifying trends in the vulnerability of Alpine forest ecosystems to fire at different scales (tree species, stand level and biogeographic level) and according to three different climatic conditions (cold season, average summer and extremely dry summer). To explore Alpine forest vulnerability to fire, we used surface fuel measurements, forest inventory and fire weather data to simulate fire behaviour and ultimately post-fire tree mortality across 4438 forest plots in the French Alps. The results showed that cold season fires (about 50% of the fires in the French Alps) have a limited impact except on low-elevation forests of the Southern Alps (mainly Oak, Scots pine). In average summer conditions, mixed and broadleaved forests of low elevations suffer the highest mortality rates (up to 75% in coppices). Finally, summer fires occurring in extremely dry conditions promote high mortality across all forest communities. Lowest mortality rates were observed in high forest stands composed of tree species presenting adaptation to surface fires (e.g. thick bark, high canopy) such as Larch forests of the internal Alps. This study provides insights on the vulnerability of the main tree species and forest ecosystems of the French Alps useful for the adaptation of forest management practices to climate changes. Numéro de notice : A2019-565 Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10342-019-01206-1 date de publication en ligne : 19/06/2019 En ligne : https://doi.org/10.1007/s10342-019-01206-1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94414 [article]

La succession végétale dans les Landes de Gascogne et la position de l’Avoine de Thore (Pseudarrhenatherum longifolium) / Pierre Lafon in Evaxiana, n° 6 (2019)

Permalink

The relationship between climate and the intra-annual oxygen isotope patterns from pine trees: a case study along an elevation gradient on Corsica, France / Sonja Szymczak in Annals of Forest Science [en ligne], Vol 76 n° 3 (September 2019)  

Permalink

The utility of terrestrial photogrammetry for assessment of tree volume and taper in boreal mixedwood forests / Christopher Mulverhill in Annals of Forest Science [en ligne], Vol 76 n° 3 (September 2019)  

Permalink

Increasing precision for French forest inventory estimates using the k-NN technique with optical and photogrammetric data and model-assisted estimators / Dinesh Babu Irulappa Pillai Vijayakumar in Remote sensing, vol 11 n° 8 (August 2019)  

Permalink

Comparison of three algorithms to estimate tree stem diameter from terrestrial laser scanner data / Joris Ravaglia in Forests, vol 10 n° 7 (July 2019)  

Permalink

Mapping leaf chlorophyll content from Sentinel-2 and RapidEye data in spruce stands using the invertible forest reflectance model / Roshanak Darvishzadeh in International journal of applied Earth observation and geoinformation, vol 79 (July 2019)  

Permalink

Occlusion probability in operational forest inventory field sampling with ForeStereo / Fernando Montes in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 7 (July 2019)  

Permalink

Combining low-density LiDAR and satellite images to discriminate species in mixed Mediterranean forest / Angela Blázquez-Casado in Annals of Forest Science [en ligne], vol 76 n° 2 (June 2019)  

Permalink

Estimating forest stand density and structure using Bayesian individual tree detection, stochastic geometry, and distribution matching / Kasper Kansanen in ISPRS Journal of photogrammetry and remote sensing, vol 152 (June 2019)  

Permalink

Site and age-dependent responses of Picea abies growth to climate variability / Petr Čermák in European Journal of Forest Research, vol 138 n° 3 (June 2019)  

Permalink