Descripteur
Documents disponibles dans cette catégorie (1231)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Canopy self-replacement in Pinus sylvestris rear-edge populations following drought-induced die-off and mortality / Jordi Margalef- Marrase in Forest ecology and management, vol 521 (October-1 2022)
[article]
Titre : Canopy self-replacement in Pinus sylvestris rear-edge populations following drought-induced die-off and mortality Type de document : Article/Communication Auteurs : Jordi Margalef- Marrase, Auteur ; Guillem Bagaria, Auteur ; Francisco Lloret, Auteur Année de publication : 2022 Article en page(s) : n° 120427 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] adaptation (biologie)
[Termes IGN] analyse de données
[Termes IGN] canopée
[Termes IGN] Catalogne (Espagne)
[Termes IGN] changement climatique
[Termes IGN] classification et arbre de régression
[Termes IGN] croissance des arbres
[Termes IGN] dépérissement
[Termes IGN] mortalité
[Termes IGN] Pinus sylvestris
[Termes IGN] Quercus pubescens
[Termes IGN] sécheresse
[Vedettes matières IGN] Végétation et changement climatiqueRésumé : (auteur) In recent years, Pinus sylvestris die-off and mortality events have occurred across all its range of distribution, usually associated with recurrent droughts induced by climate change. A shift in canopy dominance towards other better adapted co-existing species can be expected, especially in populations located close to their climatic tolerance limits. Herein, we tested, along a local elevational gradient, whether canopy opening resulting from die-off and mortality favours the growth of a non-dominant co-existing tree species (Quercus pubescens) established in the sub-canopy, in comparison to P. sylvestris sub-canopy trees. We also tested whether the growth of both species is associated with local climatic suitability for these species (extracted from SDMs) or, alternatively, with direct measures of micro-climatic variables. Finally, the effect on tree growth of other micro-local factors such as competition, canopy closure and micro-topography was also tested. Sub-canopy tree growth was enhanced overall by canopy opening resulting from P. sylvestris canopy die-off, but this response was stronger in P. sylvestris trees, reinforcing the self-replacement of this species after die-off. This higher growth rate is related to modifications in the micro-local climate (higher temperatures in the wettest quarter). Conversely, Q. pubescens is less sensitive to micro-local climate conditions but it can grow faster than P. sylvestris on stands with no canopy die-off or mortality. In contrast, climatic suitability extracted from SDMs was negatively related to sub-canopy P. sylvestris growth and had no effect on Q. pubescens. These contrasting results support observations at plot scale that P. sylvestris self-replacement is better explained by local environmental conditions than by values of climatic suitability obtained from regional-scale data-sets. Nevertheless, these climatic suitability measures remain consistent with the overall pattern of low seedling recruitment observed in previous works at the rear edge of species' distribution. This study reveals that short-term shifts in species dominance at a local scale will not necessarily occur in the studied P. sylvestris forests following die-off. This finding endorses the notion that micro-local environment and species traits (i.e., light and temperature tolerance, life-history strategies) modulate the capacity for resilience in rear-edge populations that would probably be prone to collapse otherwise. Numéro de notice : A2022-709 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : https://doi.org/10.1016/j.foreco.2022.120427 Date de publication en ligne : 21/07/2022 En ligne : https://doi.org/10.1016/j.foreco.2022.120427 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101585
in Forest ecology and management > vol 521 (October-1 2022) . - n° 120427[article]Deep learning high resolution burned area mapping by transfer learning from Landsat-8 to PlanetScope / V.S. Martins in Remote sensing of environment, vol 280 (October 2022)
[article]
Titre : Deep learning high resolution burned area mapping by transfer learning from Landsat-8 to PlanetScope Type de document : Article/Communication Auteurs : V.S. Martins, Auteur ; D.P. Roy, Auteur ; H. Huang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 113203 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] Afrique (géographie politique)
[Termes IGN] apprentissage profond
[Termes IGN] carte thématique
[Termes IGN] cartographie automatique
[Termes IGN] correction radiométrique
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] forêt tropicale
[Termes IGN] image Landsat-OLI
[Termes IGN] image PlanetScope
[Termes IGN] incendie
[Termes IGN] précision de la classification
[Termes IGN] régression
[Termes IGN] savaneRésumé : (auteur) High spatial resolution commercial satellite data provide new opportunities for terrestrial monitoring. The recent availability of near-daily 3 m observations provided by the PlanetScope constellation enables mapping of small and spatially fragmented burns that are not detected at coarser spatial resolution. This study demonstrates, for the first time, the potential for automated PlanetScope 3 m burned area mapping. The PlanetScope sensors have no onboard calibration or short-wave infrared bands, and have variable overpass times, making them challenging to use for large area, automated, burned area mapping. To help overcome these issues, a U-Net deep learning algorithm was developed to classify burned areas from two-date Planetscope 3 m image pairs acquired at the same location. The deep learning approach, unlike conventional burned area mapping algorithms, is applied to image spatial subsets and not to single pixels and so incorporates spatial as well as spectral information. Deep learning requires large amounts of training data. Consequently, transfer learning was undertaken using pre-existing Landsat-8 derived burned area reference data to train the U-Net that was then refined with a smaller set of PlanetScope training data. Results across Africa considering 659 PlanetScope radiometrically normalized image pairs sensed one day apart in 2019 are presented. The U-Net was first trained with different numbers of randomly selected 256 × 256 30 m pixel patches extracted from 92 pre-existing Landsat-8 burned area reference data sets defined for 2014 and 2015. The U-Net trained with 300,000 Landsat patches provided about 13% 30 m burn omission and commission errors with respect to 65,000 independent 30 m evaluation patches. The U-Net was then refined by training on 5,000 256 × 256 3 m patches extracted from independently interpreted PlanetScope burned area reference data. Qualitatively, the refined U-Net was able to more precisely delineate 3 m burn boundaries, including the interiors of unburned areas, and better classify “faint” burned areas indicative of low combustion completeness and/or sparse burns. The refined U-Net 3 m classification accuracy was assessed with respect to 20 independently interpreted PlanetScope burned area reference data sets, composed of 339.4 million 3 m pixels, with low 12.29% commission and 12.09% omission errors. The dependency of the U-Net classification accuracy on the burned area proportion within 3 m pixel 256 × 256 patches was also examined, and patches Numéro de notice : A2022-774 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.113203 Date de publication en ligne : 08/08/2022 En ligne : https://doi.org/10.1016/j.rse.2022.113203 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101802
in Remote sensing of environment > vol 280 (October 2022) . - n° 113203[article]Detecting overmature forests with airborne laser scanning (ALS) / Marc Fuhr in Remote sensing in ecology and conservation, vol 8 n° 5 (October 2022)
[article]
Titre : Detecting overmature forests with airborne laser scanning (ALS) Type de document : Article/Communication Auteurs : Marc Fuhr, Auteur ; Etienne Lalechère, Auteur ; Jean-Matthieu Monnet, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 731 - 743 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] Abies alba
[Termes IGN] âge du peuplement forestier
[Termes IGN] Bootstrap (statistique)
[Termes IGN] canopée
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] coefficient de corrélation
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] Fagus sylvatica
[Termes IGN] Picea abies
[Termes IGN] Préalpes (France)
[Termes IGN] semis de points
[Termes IGN] structure d'un peuplement forestierRésumé : (auteur) Building a network of interconnected overmature forests is crucial for the conservation of biodiversity. Indeed, a multitude of plant and animal species depend on forest structural maturity attributes such as very large living trees and deadwood. LiDAR technology has proved to be powerful when assessing forest structural parameters, and it may be a promising way to identify existing overmature forest patches over large areas. We first built an index (IMAT) combining several forest structural maturity attributes in order to characterize the structural maturity of 660 field plots in the French northern Pre-Alps. We then selected or developed LiDAR metrics and applied them in a random forest model designed to predict the IMAT. Model performance was evaluated with the root mean square error of prediction obtained from a bootstrap cross-validation and a Spearman correlation coefficient calculated between observed and predicted IMAT. Predictors were ranked by importance based on the average increase in the squared out-of-bag error when the variable was randomly permuted. Despite a non-negligible RMSEP (0.85 for calibration and validation data combined and 1.26 for validation data alone), we obtained a high correlation (0.89) between the observed and predicted IMAT values, indicating an accurate ranking of the field plots. LiDAR metrics for height (maximum height and height heterogeneity) were among the most important metrics for predicting forest maturity, together with elevation, slope and, to a lesser extent, with metrics describing the distribution of echoes' intensities. Our framework makes it possible to reconstruct a forest maturity gradient and isolate maturity hot spots. Nevertheless, our approach could be considerably strengthened by taking into consideration site fertility, collecting other maturity attributes in the field or developing adapted LiDAR metrics. Including additional spectral or textural metrics from optical imagery might also improve the predictive capacity of the model. Numéro de notice : A2022-880 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1002/rse2.274 Date de publication en ligne : 15/07/2022 En ligne : https://doi.org/10.1002/rse2.274 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102197
in Remote sensing in ecology and conservation > vol 8 n° 5 (October 2022) . - pp 731 - 743[article]DSNUNet: An improved forest change detection network by combining Sentinel-1 and Sentinel-2 images / Jiawei Jiang in Remote sensing, vol 14 n° 19 (October-1 2022)
[article]
Titre : DSNUNet: An improved forest change detection network by combining Sentinel-1 and Sentinel-2 images Type de document : Article/Communication Auteurs : Jiawei Jiang, Auteur ; Yuanjun Xing, Auteur ; Wei Wei, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5046 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] apprentissage profond
[Termes IGN] Chine
[Termes IGN] détection de changement
[Termes IGN] gestion forestière
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] réseau neuronal siamois
[Termes IGN] ressources forestièresRésumé : (auteur) The use of remote sensing images to detect forest changes is of great significance for forest resource management. With the development and implementation of deep learning algorithms in change detection, a large number of models have been designed to detect changes in multi-phase remote sensing images. Although synthetic aperture radar (SAR) data have strong potential for application in forest change detection tasks, most existing deep learning-based models have been designed for optical imagery. Therefore, to effectively combine optical and SAR data in forest change detection, this paper proposes a double Siamese branch-based change detection network called DSNUNet. DSNUNet uses two sets of feature branches to extract features from dual-phase optical and SAR images and employs shared weights to combine features into groups. In the proposed DSNUNet, different feature extraction branch widths were used to compensate for a difference in the amount of information between optical and SAR images. The proposed DSNUNet was validated by experiments on the manually annotated forest change detection dataset. According to the obtained results, the proposed method outperformed other change detection methods, achieving an F1-score of 76.40%. In addition, different combinations of width between feature extraction branches were analyzed in this study. The results revealed an optimal performance of the model at initial channel numbers of the optical imaging branch and SAR image branch of 32 and 8, respectively. The prediction results demonstrated the effectiveness of the proposed method in accurately predicting forest changes and suppressing cloud interferences to some extent. Numéro de notice : A2022-772 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs14195046 Date de publication en ligne : 10/10/2022 En ligne : https://doi.org/10.3390/rs14195046 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101800
in Remote sensing > vol 14 n° 19 (October-1 2022) . - n° 5046[article]Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning / J.F. Roberts in Computers & geosciences, vol 167 (October 2022)
[article]
Titre : Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning Type de document : Article/Communication Auteurs : J.F. Roberts, Auteur ; R. Mwangi, Auteur ; F. Mukabi, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 105192 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage automatique
[Termes IGN] carte thématique
[Termes IGN] déboisement
[Termes IGN] détection de changement
[Termes IGN] image Sentinel-MSI
[Termes IGN] informatique en nuage
[Termes IGN] Kenya
[Termes IGN] langage de programmation
[Termes IGN] observation de la Terre
[Termes IGN] Python (langage de programmation)
[Termes IGN] surveillance forestièreRésumé : (auteur) Monitoring forest cover change from Earth observation data streams in near-real-time presents a challenge for automated change detection by way of a continuously updated big dataset. Even though deforestation is a significant global problem, forest cover changes in pairs of subsequent images happen relatively infrequently. Detecting a change can require the download and processing of tens, hundreds or even thousands of images. In geoscientific applications of Earth observation, machine learning algorithms are increasingly used. Once trained, a machine learning model can be applied to new images automatically. This paper introduces the open-access Python 3 package Pyeo - “Python for Earth Observation”. Pyeo provides a set of portable, extensible and modular Python functions for the automation of machine learning applications from Earth observation data streams, including automated search and download functionality, pre-processing and atmospheric correction, re-projection, creation of thematic base layers and machine learning classification or regression. Pyeo enables users to train their own machine learning models and then apply the models to newly downloaded imagery over their area of interest. This paper describes in detail how Pyeo works, its requirements, benefits, and a description of the libraries used. An application to the automated forest cover change detection in a region in Kenya is given. Pyeo can be used on cloud computing architectures such as Amazon Web Services, Microsoft Azure and Google Colab to provide scalable applications and processing solutions for the geosciences. Numéro de notice : A2022-706 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.cageo.2022.105192 Date de publication en ligne : 09/07/2022 En ligne : https://doi.org/10.1016/j.cageo.2022.105192 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101575
in Computers & geosciences > vol 167 (October 2022) . - n° 105192[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)PermalinkSynthèse des résultats de la littérature scientifique sur les peuplements mélangés / Jordan Bello in Rendez-vous techniques, n° 76 (automne 2022)PermalinkComparison of deep neural networks in detecting field grapevine diseases using transfer learning / Antonios Morellos in Remote sensing, vol 14 n° 18 (September-2 2022)PermalinkIncreasing and widespread vulnerability of intact tropical rainforests to repeated droughts / Shengli Tao in Proceedings of the National Academy of Sciences of the United States of America PNAS, vol 119 n° 37 (2022)PermalinkRegional climate moderately influences species-mixing effect on tree growth-climate relationships and drought resistance for beech and pine across Europe / Géraud de Streel in Forest ecology and management, vol 520 (September-15 2022)PermalinkTree regeneration in models of forest dynamics – Suitability to assess climate change impacts on European forests / Louis A. König in Forest ecology and management, vol 520 (September-15 2022)PermalinkAssessing the impact of forest structure disturbances on the arboreal movement and energetics of orangutans : An agent-based modeling approach / Kirana Widyastuti in Frontiers in Ecology and Evolution, vol 2022 ([01/09/2022])PermalinkBenchmarking laser scanning and terrestrial photogrammetry to extract forest inventory parameters in a complex temperate forest / Daniel Kükenbrink in International journal of applied Earth observation and geoinformation, vol 113 (September 2022)PermalinkClassification of pine wilt disease at different infection stages by diagnostic hyperspectral bands / Niwen Li in Ecological indicators, vol 142 (September 2022)PermalinkEffect of riparian soil moisture on bacterial, fungal and plant communities and microbial decomposition rates in boreal stream-side forests / M.J. Annala in Forest ecology and management, vol 519 (September-1 2022)Permalink