Centre dedocumentation
scientifique

Mask R-CNN and OBIA fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors / Emilio Guirado in Sensors, vol 21 n° 1 (January 2021)  

Public [article]  inSensors > vol 21 n° 1 (January 2021) . - n° 320 Titre : Mask R-CNN and OBIA fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors Type de document : Article/Communication Auteurs : Emilio Guirado, Auteur ; Javier Blanco-Sacristán, Auteur ; Emilio Rodríguez-Caballero, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 320 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] analyse d'image orientée objet [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbuste [Termes descripteurs IGN] capteur optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection de changement [Termes descripteurs IGN] image à très haute résolution [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] service écosystémique [Termes descripteurs IGN] surveillance de la végétation [Termes descripteurs IGN] zone aride Résumé : (auteur) Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands. Numéro de notice : A2021-157 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/s21010320 date de publication en ligne : 05/01/2021 En ligne : https://doi.org/10.3390/s21010320 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97072 [article]

Shrub biomass estimates in former burnt areas using Sentinel 2 images processing and classification / Jose Aranha in Forests, vol 11 n° 5 (May 2020)  

Public [article]  inForests > vol 11 n° 5 (May 2020) . - 19 p. Titre : Shrub biomass estimates in former burnt areas using Sentinel 2 images processing and classification Type de document : Article/Communication Auteurs : Jose Aranha, Auteur ; Teresa Enes, Auteur ; Ana Calvão, Auteur ; Hélder Viana, Auteur Année de publication : 2020 Article en page(s) : 19 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] arbuste [Termes descripteurs IGN] biomasse [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] gestion forestière [Termes descripteurs IGN] image proche infrarouge [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] incendie de forêt [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] Normalized Difference Vegetation Index [Termes descripteurs IGN] Portugal [Termes descripteurs IGN] signature spectrale [Termes descripteurs IGN] sous-bois [Termes descripteurs IGN] système d'information géographique [Termes descripteurs IGN] zone sinistrée Résumé : (auteur) Shrubs growing in former burnt areas play two diametrically opposed roles. On the one hand, they protect the soil against erosion, promote rainwater infiltration, carbon sequestration and support animal life. On the other hand, after the shrubs’ density reaches a particular size for the canopy to touch and the shrubs’ biomass accumulates more than 10 Mg ha−1, they create the necessary conditions for severe wild fires to occur and spread. The creation of a methodology suitable to identify former burnt areas and to track shrubs’ regrowth within these areas in a regular and a multi temporal basis would be beneficial. The combined use of geographical information systems (GIS) and remote sensing (RS) supported by dedicated land survey and field work for data collection has been identified as a suitable method to manage these tasks. The free access to Sentinel images constitutes a valuable tool for updating the GIS project and for the monitoring of regular shrubs’ accumulated biomass. Sentinel 2 VIS-NIR images are suitable to classify rural areas (overall accuracy = 79.6% and Cohen’s K = 0.754) and to create normalized difference vegetation index (NDVI) images to be used in association to allometric equations for the shrubs’ biomass estimation (R2 = 0.8984, p-value Numéro de notice : A2020-654 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/f11050555 date de publication en ligne : 14/05/2020 En ligne : https://doi.org/10.3390/f11050555 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96116 [article]

What Is threatening forests in protected areas? A global assessment of deforestation in protected areas, 2001–2018 / Christopher M. Wade in Forests, vol 11 n° 5 (May 2020)  

Public [article]  inForests > vol 11 n° 5 (May 2020) . - 14 p. Titre : What Is threatening forests in protected areas? A global assessment of deforestation in protected areas, 2001–2018 Type de document : Article/Communication Auteurs : Christopher M. Wade, Auteur ; Kemen G. Austin, Auteur ; James Cajka, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : 14 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] aire protégée [Termes descripteurs IGN] Amérique du nord [Termes descripteurs IGN] analyse diachronique [Termes descripteurs IGN] arbuste [Termes descripteurs IGN] biodiversité [Termes descripteurs IGN] Brésil [Termes descripteurs IGN] Congo [Termes descripteurs IGN] couvert forestier [Termes descripteurs IGN] déboisement [Termes descripteurs IGN] gaz à effet de serre [Termes descripteurs IGN] habitat forestier [Termes descripteurs IGN] indicateur de service écosystémique [Termes descripteurs IGN] Indonésie [Termes descripteurs IGN] protection des forêts [Termes descripteurs IGN] risque environnemental [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) The protection of forests is crucial to providing important ecosystem services, such as supplying clean air and water, safeguarding critical habitats for biodiversity, and reducing global greenhouse gas emissions. Despite this importance, global forest loss has steadily increased in recent decades. Protected Areas (PAs) currently account for almost 15% of Earth’s terrestrial surface and protect 5% of global tree cover and were developed as a principal approach to limit the impact of anthropogenic activities on natural, intact ecosystems and habitats. We assess global trends in forest loss inside and outside of PAs, and land cover following this forest loss, using a global map of tree cover loss and global maps of land cover. While forests in PAs experience loss at lower rates than non-protected forests, we find that the temporal trend of forest loss in PAs is markedly similar to that of all forest loss globally. We find that forest loss in PAs is most commonly—and increasingly—followed by shrubland, a broad category that could represent re-growing forest, agricultural fallows, or pasture lands in some regional contexts. Anthropogenic forest loss for agriculture is common in some regions, particularly in the global tropics, while wildfires, pests, and storm blowdown are a significant and consistent cause of forest loss in more northern latitudes, such as the United States, Canada, and Russia. Our study describes a process for screening tree cover loss and agriculture expansion taking place within PAs, and identification of priority targets for further site-specific assessments of threats to PAs. We illustrate an approach for more detailed assessment of forest loss in four case study PAs in Brazil, Indonesia, Democratic Republic of Congo, and the United States. Numéro de notice : A2020-655 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.3390/f11050539 date de publication en ligne : 12/05/2020 En ligne : https://doi.org/10.3390/f11050539 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96119 [article]

Testing the generality of below-ground biomass allometry across plant functional types / Keryn I. Paul in Forest ecology and management, vol 432 (15 January 2019)  

Public [article]  inForest ecology and management > vol 432 (15 January 2019) . - pp 102 - 114 Titre : Testing the generality of below-ground biomass allometry across plant functional types Type de document : Article/Communication Auteurs : Keryn I. Paul, Auteur Année de publication : 2019 Article en page(s) : pp 102 - 114 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Végétation [Termes descripteurs IGN] Acacia (genre) [Termes descripteurs IGN] allométrie [Termes descripteurs IGN] arbuste [Termes descripteurs IGN] Australie [Termes descripteurs IGN] biomasse souterraine [Termes descripteurs IGN] bois sur pied [Termes descripteurs IGN] diamètre des arbres [Termes descripteurs IGN] écosystème forestier [Termes descripteurs IGN] Eucalyptus (genre) [Termes descripteurs IGN] forêt tropicale [Termes descripteurs IGN] modèle fonctionnel [Termes descripteurs IGN] Pinus radiata [Termes descripteurs IGN] puits de carbone [Termes descripteurs IGN] sous-bois Résumé : (auteur) Accurate quantification of below-ground biomass (BGB) of woody vegetation is critical to understanding ecosystem function and potential for climate change mitigation from sequestration of biomass carbon. We compiled 2054 measurements of planted and natural individual tree and shrub biomass from across different regions of Australia (arid shrublands to tropical rainforests) to develop allometric models for prediction of BGB. We found that the relationship between BGB and stem diameter was generic, with a simple power-law model having a BGB prediction efficiency of 72–93% for four broad plant functional types: (i) shrubs and Acacia trees, (ii) multi-stemmed mallee eucalypts, (iii) other trees of relatively high wood density, and; (iv) a species of relatively low wood density, Pinus radiata D. Don. There was little improvement in accuracy of model prediction by including variables (e.g. climatic characteristics, stand age or management) in addition to stem diameter alone. We further assessed the generality of the plant functional type models across 11 contrasting stands where data from whole-plot excavation of BGB were available. The efficiency of model prediction of stand-based BGB was 93%, with a mean absolute prediction error of only 6.5%, and with no improvements in validation results when species-specific models were applied. Given the high prediction performance of the generalised models, we suggest that additional costs associated with the development of new species-specific models for estimating BGB are only warranted when gains in accuracy of stand-based predictions are justifiable, such as for a high-biomass stand comprising only one or two dominant species. However, generic models based on plant functional type should not be applied where stands are dominated by species that are unusual in their morphology and unlikely to conform to the generalised plant functional group models. Numéro de notice : A2019-003 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2018.08.043 date de publication en ligne : 15/09/2018 En ligne : https://doi.org/10.1016/j.foreco.2018.08.043 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91596 [article]

Response of Swiss forests to management and climate change in the last 60 years / Meinrad Küchler in Annals of Forest Science [en ligne], vol 72 n° 3 (May 2015)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 72 n° 3 (May 2015) . - pp 311 - 320 Titre : Response of Swiss forests to management and climate change in the last 60 years Type de document : Article/Communication Auteurs : Meinrad Küchler, Auteur ; Helen Küchler, Auteur ; Angéline Bedolla, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 311 - 320 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Végétation [Termes descripteurs IGN] analyse diachronique [Termes descripteurs IGN] arbuste [Termes descripteurs IGN] changement climatique [Termes descripteurs IGN] espèce végétale [Termes descripteurs IGN] forêt [Termes descripteurs IGN] herbe [Termes descripteurs IGN] inventaire forestier étranger (données) [Termes descripteurs IGN] plantation forestière [Termes descripteurs IGN] recensement [Termes descripteurs IGN] Suisse [Termes descripteurs IGN] sylviculture [Termes descripteurs IGN] température Résumé : (auteur) Context : Forest vegetation is forecasted to shift upslope several hundred metres by 2100 due to climate warming. However, only a small number of detailed assessments in selected regions have confirmed a climate response on the part of forest vegetation. Aims : This study aimed to analyse the relative contributions of temperature and other factors to range shifts in forest vegetation by comparing old and revisited relevés in Swiss forests. Methods : In order to investigate such range shifts, we revisited 451 relevé plots in forests in all parts of Switzerland. Collected data comprise two independent samples, one dating from the 1950s (age 60 sample) on 126 plots and the other dating from the 1990s (age 15 sample) on 325 plots. We defined an indicator value for elevation to estimate the upslope and downslope range shifts of forest species. The influence of different site factors on range shifts was assessed by variance partitioning using Landolt’s (2010) averaged species indicator values. Vegetation changes were analysed by balancing both increasing and decreasing frequencies of plant species. Results : Our findings show significant differences between the two survey periods, where the averaged species indicator for elevation varied greatly in both the age-60 and the age-15 samples. In addition, a significant upslope shift in the herbaceous forest layer (herbs and tree regeneration) of about 10 m per decade since the mid-twentieth century is evident. Downslope shifts were detected in the shrub/tree layer at lower elevations, which may be explained by factors other than climate warming. Conclusions : To date, the impact of global warming on tree species composition in Swiss forests has been weaker in comparison to the effects arising from forest management and land use change. Understorey vegetation, however, shows a strong signal of upslope shift that may be explained most adequately by a combination of climate change and other factors. Numéro de notice : 2015-453 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1007/s13595-014-0409-x date de publication en ligne : 29/07/2014 En ligne : https://doi.org/10.1007/s13595-014-0409-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=77109 [article]

Influence of a dense, low-height shrub species on the accuracy of a lidar-derived DEM / Samuel B. Gould in Photogrammetric Engineering & Remote Sensing, PERS, vol 79 n° 5 (May 2013)  

Permalink

Small-footprint Lidar estimations of sagebrush canopy characteristics / J. Mitchell in Photogrammetric Engineering & Remote Sensing, PERS, vol 77 n° 5 (May 2011)  

Permalink