Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Species-specific aboveground biomass estimation using semantic segmentation of UAV photogrammetric point clouds

  • Carbonell-Rivera, Juan Pedro|||0000-0002-6724-6780
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
  • Estornell Cremades, Javier|||0000-0003-0854-5358
  • Torralba, Jesús|||0000-0001-8644-8604
[EN] Accurate, species-specific estimation of aboveground biomass (AGB) at the individual plant level is essential for characterizing forest structure, supporting ecological and wildfire modelling, and enabling fine-scale carbon accounting. This study presents a methodological framework for estimating species-specific AGB at individual plant level in Mediterranean ecosystems using UAV-based digital aerial photogrammetry (UAV-DAP). High-resolution point clouds were processed through a multi-step workflow including object-based segmentation, thirteen species classification and AGB regression modeling. The overall accuracy of species classification across six study areas was 81.6%, with a maximum of 89.9%. The regression models for AGB estimation yielded an average R2 of 0.69 across all species, highlighting species such as Anthyllis cytisoides (R2 = 0.83, RMSE = 0.07 kg, n = 47), Juniperus oxycedrus (R2 = 0.83, RMSE = 3.17 kg, n = 32); or Pinus halepensis (R2 = 0.77, RMSE = 11.79 kg, n = 20). These findings demonstrate the potential of UAV-DAP for practical estimates of AGB. The study underscores UAV-DAP as a cost-effective tool for forest management, ecological monitoring, and biomass assessments, paving the way for broader applications in environmental science and resource management., This research has been supported by the grants BES-2017-081920 and PID2020-117808RB-C21 funded by MCIN/AEI/10.13039/501100011033 and by ESF Investing in your future.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Classification of Mediterranean Shrub Species from UAV Point Clouds

  • Carbonell-Rivera, Juan Pedro|||0000-0002-6724-6780
  • Torralba, Jesús|||0000-0001-8644-8604
  • Estornell Cremades, Javier|||0000-0003-0854-5358
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
  • Crespo-Peremarch, Pablo|||0000-0003-2241-4493
[EN] Modelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species¿ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the use of UAV-based digital aerial photogrammetry (UAV-DAP) point clouds to classify tree and shrub species in Mediterranean forests, and this information is key for the correct generation of wildfire models. In July 2020, two test sites located in the Natural Park of Sierra Calderona (eastern Spain) were analysed, registering 1036 vegetation individuals as reference data, corresponding to 11 shrub and one tree species. Meanwhile, photogrammetric flights were carried out over the test sites, using a UAV DJI Inspire 2 equipped with a Micasense RedEdge multispectral camera. Geometrical, spectral, and neighbour-based features were obtained from the resulting point cloud generated. Using these features, points belonging to tree and shrub species were classified using several machine learning methods, i.e., Decision Trees, Extra Trees, Gradient Boosting, Random Forest, and MultiLayer Perceptron. The best results were obtained using Gradient Boosting, with a mean cross-validation accuracy of 81.7% and 91.5% for test sites 1 and 2, respectively. Once the best classifier was selected, classified points were clustered based on their geometry and tested with evaluation data, and overall accuracies of 81.9% and 96.4% were obtained for test sites 1 and 2, respectively. Results showed that the use of UAV-DAP allows the classification of Mediterranean tree and shrub species. This technique opens a wide range of possibilities, including the identification of species as a first step for further extraction of structure and fuel variables as input for wildfire behaviour models., Grants BES-2017-081920 and PID2020-117808RB-C21 funded by MCIN/AEI/10.13039/5011 00011033 and by ESF Investing in your future.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Class3Dp: A supervised classifier of vegetation species from point clouds

  • Carbonell-Rivera, Juan Pedro|||0000-0002-6724-6780
  • Estornell Cremades, Javier|||0000-0003-0854-5358
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
  • Crespo-Peremarch, Pablo|||0000-0003-2241-4493
  • Torralba, Jesús|||0000-0001-8644-8604
  • Almonacid-Caballer, Jaime
[EN] Recognizing the species composition of an ecosystem is essential for conservation and land management. This study presents the software Class3Dp, a supervised classifier of vegetation species for coloured point clouds. Class3Dp is run through a graphical user interface (GUI) that allows for the selection of training samples from RGB or MS (multispectral) clouds and their classification based on geometric, spectral and neighbourhood features, along with different machine learning methods, obtaining the point cloud classified according to the classes (species) introduced. A case study is shown where a classification of ground and vegetation is carried out, obtaining an overall accuracy (OA) of 0.94 in the RGB classification and 0.95 in the MS. Points classified as vegetation were re-classified in the species Anthyllis cytisoides L., Chamaerops humilis L., Cistus monspeliensis L., Pistacia lentiscus L. and Quercus coccifera L., obtaining an OA of 0.86 in the RGB classification and 0.87 in the MS., This research has been supported by the grants BES-2017-081920 and PID2020-117808RB-C21 funded by MCIN/AEI/10.13039/501100011033 and by ESF Investing in your future. Funding for open access charge: Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

A review of the use of remote sensing for monitoring and quantifying carbon sequestration in marginal lands, Revisión sobre el uso de la teledetección en la monitorización y predicción del almacenamiento de carbono en tierras marginales

  • Carbonell-Rivera, Juan Pedro|||0000-0002-6724-6780
  • Estornell Cremades, Javier|||0000-0003-0854-5358
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
  • Torralba, Jesús|||0000-0001-8644-8604
  • Abad, Alfonso
  • Felten, Bettina
[EN] In recent years, Remote Sensing (RS) and its derived products have been used as a key tool for the detection, monitoring, management and future use of Marginal Lands (ML). Currently, there is no single, universally accepted definition of the term and there is a wide variety of synonyms. In this paper, we conduct a compilation of synonyms and meanings that encompass the term, as well as propose a definition. To reach this objective, an overview of the state of the art of ML is done, visualising trends by science maps, based on bibliographic data of established research journals, found in Google Scholar, Web of Science (WoS) and Scopus search engines. The bibliographic review carried out shows that the study of ML has traditionally been carried out with an ad hoc basis focused on the objective to be achieved, this aspect and other knowledge gaps are discussed to analyse the global study of ML. Due to the broad spectrum of uses in which ML have been studied, the work has been focused on RS for monitoring and characterizing ML, focusing on two different aspects: (i) satellite monitoring of marginal lands; and (ii) determining carbon sequestration potential of marginal lands using remote sensing., [ES] En los últimos años, la teledetección y sus productos derivados se han utilizado como herramienta clave para la detección, seguimiento, gestión y uso futuro de las tierras marginales (ML). Actualmente, no existe una definición única y universalmente aceptada del término y existe una gran variedad de sinónimos. En este artículo llevamos a cabo una recopilación de sinónimos y significados que engloban el término, además de proponer una definición universal. Para alcanzar este objetivo, se realiza un resumen del estado del arte de las ML, visualizando las tendencias mediante mapas científicos, basadas en datos bibliográficos de revistas de investigación consolidadas, encontradas en los buscadores Google Scholar, Web of Science (WoS) y Scopus. La revisión bibliográfica realizada muestra que el estudio de las ML se ha realizado tradicionalmente con una base ad hoc centrada en el objetivo a alcanzar. Se discute este aspecto y otras lagunas de conocimiento para analizar el estudio global de las tierras marginales. Debido al amplio espectro de usos en que se han estudiado las tierras marginales, los trabajos se han centrado en la teledetección para su seguimiento y caracterización, centrándose en dos aspectos diferentes: (i) el seguimiento por satélite de las tierras marginales; y (ii) determinación de su potencial en el almacenamiento de carbono mediante teledetección., This work was supported by the Spanish Ministerio de Economía, Industria y Competitividad through the scholarship for Training of Research Staff BES-2017-081920 and the European Commission through the H2020-MSCA-RISE-2018 MAIL project under Grant Agreement 823805.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Relationships of Fire Rate of Spread with Spectral and Geometric Features Derived from UAV-Based Photogrammetric Point Clouds

  • Carbonell-Rivera, Juan Pedro|||0000-0002-6724-6780
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
  • Torralba, Jesús|||0000-0001-8644-8604
  • Estornell Cremades, Javier|||0000-0003-0854-5358
  • Moran, Christopher J.
  • Seielstad, Carl A.
  • Parsons, Russell A.
  • Hoff, Valentijn
[EN] Unmanned aerial vehicles (UAVs) equipped with RGB, multispectral, or thermal cameras have demonstrated their potential to provide high-resolution data before, during, and after wildfires and prescribed burns. Pre-burn point clouds generated through the photogrammetric processing of UAV images contain geometrical and spectral information of vegetation, while active fire imagery allows for deriving fire behavior metrics. This paper focuses on characterizing the relationship between the fire rate of spread (RoS) in prescribed burns and a set of independent geometrical, spectral, and neighborhood variables extracted from UAV-derived point clouds. For this purpose, different flights were performed before and during the prescribed burning in seven grasslands and open forest plots. Variables extracted from the point cloud were interpolated to a grid, which was sized according to the RoS semivariogram. Random Forest regressions were applied, obtaining up to 0.56 of R2 in the different plots studied. Geometric variables from the point clouds, such as planarity and the spectral normalized blue¿red difference index (NBRDI), are related to fire RoS. In analyzing the results, the minimum value of the eigenentropy (Eigenentropy_MIN), the mean value of the planarity (Planarity_MEAN), and percentile 75 of the NBRDI (NBRDI_P75) obtained the highest feature importance. Plot-specific analyses unveiled distinct combinations of geometric and spectral features, although certain features, such as Planarity_MEAN and the mean value of the grid obtained from the standard deviation of the distance between points (Dist_std_MEAN), consistently held high importance across all plots. The relationships between pre-burning UAV data and fire RoS can complement meteorological and topographic variables, enhancing wildfire and prescribed burn models., This research was primarily supported by grants BES-2017-081920 and PID2020-117808RBC21 from MCIN/AEI/10.13039/501100011033 and ESF Investing in your future. Additional support was provided by the US National Science Foundation under Grant No. OIA-2119689 and the Strategic Environmental Research and Development Program (SERDP), grant number RC20-1025.