Centre de documentation
scientifique

Comparison of deep neural networks in detecting field grapevine diseases using transfer learning / Antonios Morellos in Remote sensing, vol 14 n° 18 (September-2 2022)  

Public [article]  inRemote sensing > vol 14 n° 18 (September-2 2022) . - n° 4648 Titre : Comparison of deep neural networks in detecting field grapevine diseases using transfer learning Type de document : Article/Communication Auteurs : Antonios Morellos, Auteur ; Xanthoula Eirini Pantazi, Auteur ; Charalampos Paraskevas, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4648 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de changement [Termes IGN] extraction de traits caractéristiques [Termes IGN] Grèce [Termes IGN] jeu de données [Termes IGN] maladie cryptogamique [Termes IGN] maladie phytosanitaire [Termes IGN] viticulture Résumé : (auteur) Plants diseases constitute a substantial threat for farmers given the high economic and environmental impact of their treatment. Detecting possible pathogen threats in plants based on non-destructive remote sensing and computer vision methods offers an alternative to existing laboratory methods and leads to improved crop management. Vine is an important crop that is mainly affected by fungal diseases. In this study, photos from healthy leaves and leaves infected by a fungal disease of vine are used to create disease identification classifiers. The transfer learning technique was employed in this study and was used to train three different deep convolutional neural network (DCNN) approaches that were compared according to their classification accuracy, namely AlexNet, VGG-19, and Inception v3. The above-mentioned models were trained on the open-source PlantVillage dataset using two training approaches: feature extraction, where the weights of the base deep neural network model were frozen and only the ones on the newly added layers were updated, and fine tuning, where the weights of the base model were also updated during training. Then, the created models were validated on the PlantVillage dataset and retrained using a custom field-grown vine photo dataset. The results showed that the fine-tuning approach showed better validation and testing accuracy, for all DCNNs, compared to the feature extraction approach. As far as the results of DCNNs are concerned, the Inception v3 algorithm outperformed VGG-19 and AlexNet in almost all the cases, demonstrating a validation performance of 100% for the fine-tuned strategy on the PlantVillage dataset and an accuracy of 83.3% for the respective strategy on a custom vine disease use case dataset, while AlexNet achieved 87.5% validation and 66.7% accuracy for the respective scenarios. Regarding VGG-19, the validation performance reached 100%, with an accuracy of 76.7%. Numéro de notice : A2022-768 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14184648 Date de publication en ligne : 17/09/2022 En ligne : https://doi.org/10.3390/rs14184648 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101794 [article]

Excelling the progenitors: Breeding for resistance to Dutch elm disease from moderately resistant and susceptible native stock / Jorge Dominguez in Forest ecology and management, vol 511 (May-15 2022)  

Public [article]  inForest ecology and management > vol 511 (May-15 2022) . - n° 120113 Titre : Excelling the progenitors: Breeding for resistance to Dutch elm disease from moderately resistant and susceptible native stock Type de document : Article/Communication Auteurs : Jorge Dominguez, Auteur ; David Macaya-Sanz, Auteur ; Luis Gil, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 120113 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] adaptation (biologie) [Termes IGN] conservation des ressources forestières [Termes IGN] Europe occidentale [Termes IGN] génétique forestière [Termes IGN] maladie cryptogamique [Termes IGN] maladie phytosanitaire [Termes IGN] phénologie [Termes IGN] Ulmus minor [Vedettes matières IGN] Foresterie Résumé : (auteur) Under the continuous pressure of Dutch elm disease (DED) in Europe, increasing the genetic diversity of Ulmus minor trees resistant to Ophiostoma novo-ulmi is a priority for the species conservation and reintroduction. In this work we screened 121 U. minor genotypes for resistance to O. novo-ulmi under field experimental conditions. The genotypes had been previously obtained through controlled crosses between two moderately resistant (dams) and one susceptible (sire) genotypes. After two years of artificial inoculations with O. novo-ulmi, transgressive resistance was present but not prevalent, and a moderate relation was found between tree growth and susceptibility. Heritability estimates of DED resistance endorse significant genetic control and higher estimates for experimental blocks with milder symptoms. Three genotypes excelled for their high DED resistance, showing average foliage wilting values below 30% after the two years of inoculations. The genetic fingerprint, leaf phenology and morphology, and ornamental traits of these three genotypes were evaluated to facilitate their identification and use by stakeholders. Nuclear microsatellite profiling displayed unique barcodes for each genotype, ensuring traceability of the plant material. Morphological and phenological traits of the three genotypes are quite similar and fall within the species standards. In base of these results, three new native genotypes are proposed as basic materials for elm reintroduction in Western Europe. Numéro de notice : A2022-260 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1016/j.foreco.2022.120113 Date de publication en ligne : 04/03/2022 En ligne : https://doi.org/10.1016/j.foreco.2022.120113 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100242 [article]

Five decades of ground flora changes in a temperate forest: The good, the bad and the ambiguous in biodiversity terms / K.J. Kirby in Forest ecology and management, vol 505 (February-1 2022)  

Public [article]  inForest ecology and management > vol 505 (February-1 2022) . - n° 119896 Titre : Five decades of ground flora changes in a temperate forest: The good, the bad and the ambiguous in biodiversity terms Type de document : Article/Communication Auteurs : K.J. Kirby, Auteur ; D.R. Bazely, Auteur ; E.A. Goldberg, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 119896 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse diachronique [Termes IGN] biomasse forestière [Termes IGN] Brachypodium (genre) [Termes IGN] Cervidae [Termes IGN] composition floristique [Termes IGN] dépérissement [Termes IGN] détection de changement [Termes IGN] eutrophisation [Termes IGN] flore forestière [Termes IGN] forêt tempérée [Termes IGN] Fraxinus excelsior [Termes IGN] gestion forestière [Termes IGN] maladie phytosanitaire [Termes IGN] richesse floristique [Termes IGN] Royaume-Uni [Termes IGN] Tracheophyta [Vedettes matières IGN] Foresterie Résumé : (auteur) We explore how the ground flora of a temperate woodland (Wytham Woods, southern England) changed in terms of species-richness, cover and biomass over five decades; what the drivers of change were; and possible future change as a consequence of the decline in Fraxinus excelsior as a canopy dominant. Vascular plants were recorded from 164 permanent, 10x10 m plots, distributed as a 141 m grid, in 1974, 1991, 1999, 2012, and 2018. Species presence and frequency/abundance in each plot were estimated and used to model biomass changes. Changes in species-richness, vegetation composition and structure were analysed. Stands opened out by thinning or which became denser through tree growth gained or lost species respectively, particularly non-woodland species. Deer pressure favoured the spread of Brachypodium sylvaticum and reduced Rubus fruticosus. No obvious impacts of climate change, eutrophication or of invasive species were detected in the plot records although other signs suggest these are starting to affect the flora. Just 12 out of 235 species contributed 47% of all species occurrences, 82% of the vegetation cover and 87% of the modelled biomass. We conclude that the ground flora is highly variable over decadal timescales, but the patterns of change observed differ according to the measures used (species richness, cover, biomass, etc). Site level drivers in the short-term swamped effects of slower acting regional/global drivers. Legacy effects were seen in the greater richness of specialists in the older woodland. While some impacts can be mitigated by management, others are largely beyond control at the site level. Numéro de notice : A2022-041 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET Nature : Article DOI : 10.1016/j.foreco.2021.119896 Date de publication en ligne : 02/12/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119896 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99389 [article]

Tree mortality caused by Diplodia shoot blight on Pinus sylvestris and other mediterranean pines / Maria Caballol in Forest ecology and management, vol 505 (February-1 2022)  

Public [article]  inForest ecology and management > vol 505 (February-1 2022) . - n° 119935 Titre : Tree mortality caused by Diplodia shoot blight on Pinus sylvestris and other mediterranean pines Type de document : Article/Communication Auteurs : Maria Caballol, Auteur ; Maia Ridley, Auteur ; Michele Colangelo, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 119935 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] dendrochronologie [Termes IGN] dépérissement [Termes IGN] endophyte [Termes IGN] épidémie [Termes IGN] Espagne [Termes IGN] grêle [Termes IGN] houppier [Termes IGN] maladie cryptogamique [Termes IGN] mortalité [Termes IGN] Pinus halepensis [Termes IGN] Pinus nigra [Termes IGN] Pinus pinea [Termes IGN] Pinus sylvestris [Termes IGN] santé des forêts [Termes IGN] sécheresse [Vedettes matières IGN] Végétation et changement climatique Résumé : (auteur) Diplodia shoot blight is an emergent forest disease in Europe caused by Diplodia sapinea. The short-term impacts of the pathogen on tree physiology are well known, but its capacity to cause mortality has been poorly documented. We compared the survival of four pine species affected by Diplodia shoot blight following a hailstorm: Pinus sylvestris, P. nigra, P. pinea and P. halepensis. In the case of P. sylvestris, survival in the hail-affected sites was compared with survival in other sites affected by Diplodia shoot blight with no hailstorm records. Mortality and crown condition were recorded over two years. Dendrochronological analyses were conducted to assess growth responses to drought and to test the influence of radial growth before the outbreak of Diplodia shoot blight on survival. The endophytic community, as well as the abundance of D. sapinea, was quantified by metabarcoding and qPCR respectively, and were correlated with crown damage. Crown damage was the best predictor of mortality across species. Pinus sylvestris experienced a much higher rate of mortality than P. nigra, P. pinea and P. halepensis. Two years after the outbreak, P. halepensis was the only species that could recover crown condition. Mortality was found to be unrelated to radial growth prior the outbreak. Drought responses did not correlate with mortality differences across pine species or sites. In the case of P. sylvestris, mortality was initially higher amongst diseased trees in areas affected by hailstorms than in sites not affected by hailstorms, however it tended to equalise after two years. Amongst P. sylvestris trees, crown damage correlated with a higher abundance of the pathogen. Signs of competition amongst endophytes were observed between non-defoliated and defoliated Scots pine trees following hailstorms. Our study shows that D. sapinea can cause a significant mortality to P. sylvestris. The legacy effects of crown damage can last for at least two years after an outbreak. During this time, crown damage is a good predictor of survival, and can help managers decide which trees remove after an outbreak. Numéro de notice : A2022-042 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1016/j.foreco.2021.119935 Date de publication en ligne : 23/12/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119935 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99400 [article]

Understory plant community responses to widespread spruce mortality in a subalpine forest / Trevor A. Carter in Journal of vegetation science, vol 33 n° 1 (January 2022)  

Public [article]  inJournal of vegetation science > vol 33 n° 1 (January 2022) . - 15 p. Titre : Understory plant community responses to widespread spruce mortality in a subalpine forest Type de document : Article/Communication Auteurs : Trevor A. Carter, Auteur ; Paula J. Fornwalt, Auteur ; Katleen A. Dwire, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : 15 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Abies alba [Termes IGN] forêt subalpine [Termes IGN] insecte nuisible [Termes IGN] Leaf Area Index [Termes IGN] maladie phytosanitaire [Termes IGN] mortalité [Termes IGN] Picea abies [Termes IGN] régression linéaire [Termes IGN] semis (sylviculture) [Termes IGN] sous-étage [Termes IGN] Wyoming (Etats-Unis) [Vedettes matières IGN] Foresterie Résumé : (auteur) Aims: Spruce beetles (Dendroctonus rufipennis) are causing widespread spruce (Picea spp.) mortality in subalpine forests in western North America. Spruce beetles are changing forest structure and composition by killing a dominant overstory species, but we know little about how the understory community responds to the increase in resource availability brought about by spruce mortality, what mechanisms drive its response, or how its response affects other forest properties and processes. Location: Glacier Lakes Ecosystem Experiments Site, Medicine Bow Mountains, Wyoming, USA. Methods: We measured understory community cover and richness in 75 permanent plots during and 10 years after an epidemic spruce beetle outbreak, and measured trait values for 46 common understory species. We used linear regression to determine how the understory community has changed over time and along a gradient of spruce mortality, and to evaluate the relative support for two mechanisms contributing to species responses. Results: Understory cover nearly doubled between sampling periods and increased the most where spruce mortality was most severe. Understory richness doubled and showed a weak positive trend with spruce mortality. Understory species with the largest increases in cover were the most frequent across the landscape before the disturbance, were the tallest at maturity and had the lowest leaf turgor loss points. Fir seedling density decreased over time, with decreases lessening with increases in understory cover. Changes in spruce seedling density were not predicted by changes in understory cover. Conclusions: Our findings highlight some of the diverse ways in which understory communities can be altered by spruce beetle outbreaks, and how the direction and magnitude of change can depend on the amount of spruce mortality as well as on priority effects and traits of pre-disturbance species. Our findings also highlight how understory community changes can have implications for other forest properties and processes, such as tree regeneration and forest recovery. Numéro de notice : A2022-173 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1111/jvs.13109 Date de publication en ligne : 14/12/2021 En ligne : https://doi.org/10.1111/jvs.13109 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99809 [article]

National scale mapping of larch plantations for Wales using the Sentinel-2 data archive / Suvarna M. Punalekar in Forest ecology and management, vol 501 (December-1 2021)  

Permalink

Early detection of pine wilt disease using deep learning algorithms and UAV-based multispectral imagery / Run Yu in Forest ecology and management, vol 497 (October-1 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 (July-15 2021)  

Permalink

Modeling size-density trajectories of even-aged ash (Fraxinus excelsior L.) stands in France. A baseline to assess the impact of Chalara ash dieback / Noël Le Goff in Annals of Forest Science, vol 78 n° 1 (March 2021)  

Permalink

Diagnostics of Plant Diseases / Dmitry Kurouski (2021)  

Permalink

Ensemble learning methods on the space of covariance matrices : application to remote sensing scene and multivariate time series classification / Sara Akodad (2021)  

Permalink

Qualification des données LiDAR GEDI pour le suivi de l’impact climatique sur la forêt de Südharz / Iris Jeuffrard (2021) 

Permalink

Suivi des vignes par télédétection de proximité : le deep learning au service de l’agriculture de précision / Sami Beniaouf (2021) 

Permalink

The Impact of ash dieback on veteran trees in Southwestern Sweden / Vikki Bengtsson in Baltic forestry, vol 27 n° 1 ([01/01/2021])  

Permalink

Detection of Xylella fastidiosa infection symptoms with airborne multispectral and thermal imagery: Assessing bandset reduction performance from hyperspectral analysis / T. Poblete in ISPRS Journal of photogrammetry and remote sensing, vol 162 (April 2020)  

Permalink