Centre de documentation
scientifique

Tree height-growth trajectory estimation using uni-temporal UAV laser scanning data and deep learning / Stefano Puliti in Forestry, an international journal of forest research, vol 96 n° 1 (January 2023)  

Public [article]  inForestry, an international journal of forest research > vol 96 n° 1 (January 2023) . - pp 37 - 48 Titre : Tree height-growth trajectory estimation using uni-temporal UAV laser scanning data and deep learning Type de document : Article/Communication Auteurs : Stefano Puliti, Auteur ; J. Paul McLean, Auteur ; Nicolas Cattaneo, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 37 - 48 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] Betula pendula [Termes IGN] croissance des arbres [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Fraxinus excelsior [Termes IGN] hauteur des arbres [Termes IGN] image captée par drone [Termes IGN] Norvège [Termes IGN] semis de points Résumé : (auteur) Information on tree height-growth dynamics is essential for optimizing forest management and wood procurement. Although methods to derive information on height-growth information from multi-temporal laser scanning data already exist, there is no method to derive such information from data acquired at a single point in time. Drone laser scanning data (unmanned aerial vehicles, UAV-LS) allows for the efficient collection of very dense point clouds, creating new opportunities to measure tree and branch architecture. In this study, we examine if it is possible to measure the vertical positions of branch whorls, which correspond to nodes, and thus can in turn be used to trace the height growth of individual trees. We propose a method to measure the vertical positions of whorls based on a single-acquisition of UAV-LS data coupled with deep-learning techniques. First, single-tree point clouds were converted into 2D image projections, and a YOLOv5 (you-only-look-once) convolutional neural network was trained to detect whorls based on a sample of manually annotated images. Second, the trained whorl detector was applied to a set of 39 trees that were destructively sampled after the UAV-LS data acquisition. The detected whorls were then used to estimate tree-, plot- and stand-level height-growth trajectories. The results indicated that 70 per cent (i.e. precision) of the measured whorls were correctly detected and that 63 per cent (i.e. recall) of the detected whorls were true whorls. These results translated into an overall root-mean-squared error and Bias of 8 and −5 cm for the estimated mean annual height increment. The method’s performance was consistent throughout the height of the trees and independent of tree size. As a use case, we demonstrate the possibility of developing a height-age curve, such as those that could be used for forecasting site productivity. Overall, this study provides proof of concept for new methods to analyse dense aerial point clouds based on image-based deep-learning techniques and demonstrates the potential for deriving useful analytics for forest management purposes at operationally-relevant spatial-scales. Numéro de notice : A2023-100 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1093/forestry/cpac026 Date de publication en ligne : 05/07/2022 En ligne : https://doi.org/10.1093/forestry/cpac026 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102418 [article]

Above-ground biomass change estimation using national forest inventory data with Sentinel-2 and Landsat / Stefano Puliti in Remote sensing of environment, vol 265 (November 2021)  

Public [article]  inRemote sensing of environment > vol 265 (November 2021) . - n° 112644 Titre : Above-ground biomass change estimation using national forest inventory data with Sentinel-2 and Landsat Type de document : Article/Communication Auteurs : Stefano Puliti, Auteur ; Johannes Breidenbach, Auteur ; Johannes Schumacher, Auteur ; Marius Hauglin, Auteur ; T.F. Klingenberg, Auteur ; Rasmus Astrup, Auteur Année de publication : 2021 Article en page(s) : n° 112644 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse diachronique [Termes IGN] biomasse aérienne [Termes IGN] estimation statistique [Termes IGN] forêt boréale [Termes IGN] image Landsat [Termes IGN] image Sentinel-MSI [Termes IGN] inventaire forestier étranger (données) [Termes IGN] Norvège [Termes IGN] Picea abies [Termes IGN] Pinus sylvestris [Termes IGN] puits de carbone [Termes IGN] surveillance forestière Résumé : (auteur) This study aimed at estimating total forest above-ground net change (ΔAGB; Gg) over five years (2014–2019) based on model-assisted estimation utilizing freely available satellite imagery. The study was conducted for a boreal forest area (approx. 1.4 Mha) in Norway where bi-temporal national forest inventory (NFI), Sentinel-2, and Landsat data were available. Biomass change was modelled based on a direct approach. The precision of estimates using only the NFI data in a basic expansion estimator was compared to four different alternative model-assisted estimates using 1) Sentinel-2 or Landsat data, and 2) using bi- or uni-temporal remotely sensed data. We found that spaceborne optical data improved the precision of the purely field-based estimates by a factor of up to three. The most precise estimates were found for the model-assisted estimation using bi-temporal Sentinel-2 (standard error; SE = 1.7 Gg). However, the decrease in precision when using Landsat data was small (SE = 1.92 Gg). We also found that ΔAGB could be precisely estimated when remotely sensed data were available only at the end of the monitoring period. We conclude that satellite optical data can considerably improve ΔAGB estimates, when repeated and coincident field data are available. The free availability, global coverage, frequent update, and long-term time horizon make data from programs such as Sentinel-2 and Landsat a valuable data source for consistent and durable monitoring of forest carbon dynamics. Numéro de notice : A2021-938 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112644 Date de publication en ligne : 25/08/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112644 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99746 [article]

Value of airborne laser scanning and digital aerial photogrammetry data in forest decision making / Annika S. Kangas in Silva fennica, vol 52 n° 1 ([01/02/2018])  

Public [article]  inSilva fennica > vol 52 n° 1 [01/02/2018] Titre : Value of airborne laser scanning and digital aerial photogrammetry data in forest decision making Type de document : Article/Communication Auteurs : Annika S. Kangas, Auteur ; Terje Gobakken, Auteur ; Stefano Puliti, Auteur ; Marius Hauglin, Auteur ; Erik Naesset, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] aide à la décision [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Finlande [Termes IGN] image aérienne [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] inventaire forestier étranger (données) [Termes IGN] Norvège [Termes IGN] qualité des données [Termes IGN] volume en bois [Vedettes matières IGN] Inventaire forestier Résumé : (Auteur) Airborne laser scanning (ALS) has been the main method for acquiring data for forest management planning in Finland and Norway in the last decade. Recently, digital aerial photogrammetry (DAP) has provided an interesting alternative, as the accuracy of stand-based estimates has been quite close to that of ALS while the costs are markedly smaller. Thus, it is important to know if the better accuracy of ALS is worth the higher costs for forest owners. In many recent studies, the value of forest inventory information in the harvest scheduling has been examined, for instance through cost-plus-loss analysis. Cost-plus-loss means that the quality of the data is accounted for in monetary terms through calculating the losses due to errors in the data in the forest management planning context. These costs are added to the inventory costs. In the current study, we compared the losses of ALS and DAP at plot level. According to the results, the data produced using DAP are as good as data produced using ALS from a decision making point of view, even though ALS is slightly more accurate. ALS is better than DAP only if the data will be used for more than 15 years before acquiring new data, and even then the difference is quite small. Thus, the increased errors in DAP do not significantly affect the results from a decision making point of view, and ALS and DAP data can be equally well recommended to the forest owners for management planning. The decision of which data to acquire, can thus be made based on the availability of the data on first hand and the costs of acquiring it on the second hand. Numéro de notice : A2018-498 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14214/sf.9923 Date de publication en ligne : 24/01/2018 En ligne : https://doi.org/10.14214/sf.9923 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91187 [article]