Browsing by Subject "TREE SPECIES CLASSIFICATION"

Sort by: Order: Results:

Now showing items 1-7 of 7
  • Korpela, Ilkka (2017)
    Forest inventories comprise observations, models and sampling. Airborne LiDAR has established its role in providing observations of canopy geometry and topography. These data are input for estimation of important forest properties to support forestry-related decision-making. A major deficiency in forest remote sensing is tree species identification. This study examines the option of using multi-footprint airborne LiDAR data. Features of such sensor design exist in recently introduced multispectral laser scanners. The first objective was to acquire radiometrically normalized, multi-footprint (11, 22, 44 and 59 cm) waveform (WF) data that characterize 1064nm backscatter reflectance on the interval scale. The second objective was to analyze and validate the data quality in order to draw the correct conclusions about the effect of footprint size on WFs from natural and man-made targets. The experiment was carried out in Finland. Footprint variation was generated by acquiring data at different flying heights and by adjusting the transmitted power. The LiDAR campaign was successful and the data were of sufficient quality, except for a 1 dB trend due to the atmosphere. Significant findings were made conceming the magnitude of atmospheric losses, the linearity of the amplitude scale and the bandwidth characteristics of the receiver, the stability of the transmitter, the precision of the amplitude data and the transmission losses in canopies and power lines, as well as the response of WF attributes to footprint size in forest canopies. Multi-footprint data are a promising approach although the tree species-specific signatures were weak. (C) 2016 Elsevier Inc. All rights reserved.
  • Viinikka, Arto; Hurskainen, Pekka; Keski-Saari, Sarita; Kivinen, Sonja; Tanhuanpää, Topi; Mäyrä, Janne; Poikolainen, Laura; Vihervaara, Petteri; Kumpula, Timo (2020)
    Sustainable forest management increasingly highlights the maintenance of biological diversity and requires up-to-date information on the occurrence and distribution of key ecological features in forest environments. European aspen (Populus tremulaL.) is one key feature in boreal forests contributing significantly to the biological diversity of boreal forest landscapes. However, due to their sparse and scattered occurrence in northern Europe, the explicit spatial data on aspen remain scarce and incomprehensive, which hampers biodiversity management and conservation efforts. Our objective was to study tree-level discrimination of aspen from other common species in northern boreal forests using airborne high-resolution hyperspectral and airborne laser scanning (ALS) data. The study contained multiple spatial analyses: First, we assessed the role of different spectral wavelengths (455-2500 nm), principal component analysis, and vegetation indices (VI) in tree species classification using two machine learning classifiers-support vector machine (SVM) and random forest (RF). Second, we tested the effect of feature selection for best classification accuracy achievable and third, we identified the most important spectral features to discriminate aspen from the other common tree species. SVM outperformed the RF model, resulting in the highest overall accuracy (OA) of 84% and Kappa value (0.74). The used feature set affected SVM performance little, but for RF, principal component analysis was the best. The most important common VI for deciduous trees contained Conifer Index (CI), Cellulose Absorption Index (CAI), Plant Stress Index 3 (PSI3), and Vogelmann Index 1 (VOG1), whereas Green Ratio (GR), Red Edge Inflection Point (REIP), and Red Well Position (RWP) were specific for aspen. Normalized Difference Red Edge Index (NDRE) and Modified Normalized Difference Index (MND705) were important for coniferous trees. The most important wavelengths for discriminating aspen from other species included reflectance bands of red edge range (724-727 nm) and shortwave infrared (1520-1564 nm and 1684-1706 nm). The highest classification accuracy of 92% (F1-score) for aspen was achieved using the SVM model with mean reflectance values combined with VI, which provides a possibility to produce a spatially explicit map of aspen occurrence that can contribute to biodiversity management and conservation efforts in boreal forests.
  • Kuzmin, Anton; Korhonen, Lauri; Kivinen, Sonja; Hurskainen, Pekka; Korpelainen, Pasi; Tanhuanpää, Topi; Maltamo, Matti; Vihervaara, Petteri; Kumpula, Timo (2021)
    European aspen (Populus tremula L.) is a keystone species for biodiversity of boreal forests.Large-diameter aspens maintain the diversity of hundreds of species, many of which are threatened in Fennoscandia. Due to a low economic value and relatively sparse and scattered occurrence of aspen in boreal forests, there is a lack of information of the spatial and temporal distribution of aspen, which hampers efficient planning and implementation of sustainable forest management practices and conservation efforts. Our objective was to assess identification of European aspen at the individual tree level in a southern boreal forest using high-resolution photogrammetric point cloud (PPC) and multispectral (MSP) orthomosaics acquired with an unmanned aerial vehicle (UAV). The structure-from-motion approach was applied to generate RGB imagery-based PPC to be used for individual tree-crown delineation. Multispectral data were collected using two UAV cameras:Parrot Sequoia and MicaSense RedEdge-M. Tree-crown outlines were obtained from watershed segmentation of PPC data and intersected with multispectral mosaics to extract and calculate spectral metrics for individual trees. We assessed the role of spectral data features extracted from PPC and multispectral mosaics and a combination of it, using a machine learning classifier—Support Vector Machine (SVM) to perform two different classifications: discrimination of aspen from the other species combined into one class and classification of all four species (aspen, birch, pine, spruce) simultaneously. In the first scenario, the highest classification accuracy of 84% (F1-score) for aspen and overall accuracy of 90.1% was achieved using only RGB features from PPC, whereas in the second scenario, the highest classification accuracy of 86 % (F1-score) for aspen and overall accuracy of 83.3% was achieved using the combination of RGB and MSP features. The proposed method provides a new possibility for the rapid assessment of aspen occurrence to enable more efficient forest management as well as contribute to biodiversity monitoring and conservation efforts in boreal forests.
  • Forsius, Martin; Kujala, Heini; Minunno, Francesco; Holmberg, Maria; Leikola, Niko; Mikkonen, Ninni; Autio, Iida; Paunu, Ville-Veikko; Tanhuanpää, Topi; Hurskainen, Pekka; Mäyrä, Janne; Kivinen, Sonja; Keski-Saari, Sarita; Kosenius, Anna-Kaisa; Kuusela, Saija; Virkkala, Raimo; Viinikka, Arto; Vihervaara, Petteri; Akujarvi, Anu; Bäck, Jaana; Karvosenoja, Niko; Kumpula, Timo; Kuzmin, Anton; Mäkelä, Annikki; Moilanen, Atte; Ollikainen, Markku; Pekkonen, Minna; Peltoniemi, Mikko; Poikolainen, Laura; Rankinen, Katri; Rasilo, Terhi; Tuominen, Sakari; Valkama, Jari; Vanhala, Pekka; Heikkinen, Risto K (2021)
    The challenges posed by climate change and biodiversity loss are deeply interconnected. Successful co-managing of these tangled drivers requires innovative methods that can prioritize and target management actions against multiple criteria, while also enabling cost-effective land use planning and impact scenario assessment. This paper synthesises the development and application of an integrated multidisciplinary modelling and evaluation framework for carbon and biodiversity in forest systems. By analysing and spatio-temporally modelling carbon processes and biodiversity elements, we determine an optimal solution for their co-management in the study landscape. We also describe how advanced Earth Observation measurements can be used to enhance mapping and monitoring of biodiversity and ecosystem processes. The scenarios used for the dynamic models were based on official Finnish policy goals for forest management and climate change mitigation. The development and testing of the system were executed in a large region in southern Finland (Kokemäenjoki basin, 27,024 km2) containing highly instrumented LTER (Long-Term Ecosystem Research) stations; these LTER data sources were complemented by fieldwork, remote sensing and national data bases. In the study area, estimated total net emissions were currently 4.2 TgCO2eq a−1, but modelling of forestry measures and anthropogenic emission reductions demonstrated that it would be possible to achieve the stated policy goal of carbon neutrality by low forest harvest intensity. We show how this policy-relevant information can be further utilized for optimal allocation of set-aside forest areas for nature conservation, which would significantly contribute to preserving both biodiversity and carbon values in the region. Biodiversity gain in the area could be increased without a loss of carbon-related benefits.
  • Molinier, Matthieu; Lopez-Sanchez, Carlos A.; Toivanen, Timo; Korpela, Ilkka; Corral-Rivas, Jose J.; Tergujeff, Renne; Häme, Tuomas (2016)
    Due to the high cost of traditional forest plot measurements, the availability of up-to-date in situ forest inventory data has been a bottleneck for remote sensing image analysis in support of the important global forest biomass mapping. Capitalizing on the proliferation of smartphones, citizen science is a promising approach to increase spatial and temporal coverages of in situ forest observations in a cost-effective way. Digital cameras can be used as a relascope device to measure basal area, a forest density variable that is closely related to biomass. In this paper, we present the Relasphone mobile application with extensive accuracy assessment in two mixed forest sites from different biomes. Basal area measurements in Finland ( boreal zone) were in good agreement with reference forest inventory plot data on pine ( R-2 = 0.75, RMSE = 5.33 m(2)/ha), spruce ( R-2 = 0.75, RMSE = 6.73 m(2)/ha) and birch ( R-2 = 0.71, RMSE = 4.98 m(2)/ha), with total relative RMSE ( %) = 29.66%. In Durango, Mexico ( temperate zone), Relasphone stem volume measurements were best for pine ( R-2 = 0.88, RMSE = 32.46 m(3)/ha) and total stem volume ( R-2 = 0.87, RMSE = 35.21 m(3)/ha). Relasphone data were then successfully utilized as the only reference data in combination with optical satellite images to produce biomass maps. The Relasphone concept has been validated for future use by citizens in other locations.
  • Calders, Kim; Adams, Jennifer; Armston, John; Bartholomeus, Harm; Bauwens, Sebastien; Bentley, Lisa Patrick; Chave, Jerome; Danson, F. Mark; Demol, Miro; Disney, Mathias; Gaulton, Rachel; Moorthy, Sruthi M. Krishna; Levick, Shaun R.; Saarinen, Ninni; Schaaf, Crystal; Stovall, Atticus; Terryn, Louise; Wilkes, Phil; Verbeeck, Hans (2020)
    Terrestrial laser scanning (TLS) was introduced for basic forest measurements, such as tree height and diameter, in the early 2000s. Recent advances in sensor and algorithm development have allowed us to assess in situ 3D forest structure explicitly and revolutionised the way we monitor and quantify ecosystem structure and function. Here, we provide an interdisciplinary focus to explore current developments in TLS to measure and monitor forest structure. We argue that TLS data will play a critical role in understanding fundamental ecological questions about tree size and shape, allometric scaling, metabolic function and plasticity of form. Furthermore, these new developments enable new applications such as radiative transfer modelling with realistic virtual forests, monitoring of urban forests and larger scale ecosystem monitoring through long-range scanning. Finally, we discuss upscaling of TLS data through data fusion with unmanned aerial vehicles, airborne and spaceborne data, as well as the essential role of TLS in validation of spaceborne missions that monitor ecosystem structure.
  • Mäyrä, Janne; Keski-Saari, Sarita; Kivinen, Sonja; Tanhuanpää, Topi; Hurskainen, Pekka; Kullberg, Peter; Poikolainen, Laura; Viinikka, Arto; Tuominen, Sakari; Kumpula, Timo; Vihervaara, Petteri (2021)
    During the last two decades, forest monitoring and inventory systems have moved from field surveys to remote sensing-based methods. These methods tend to focus on economically significant components of forests, thus leaving out many factors vital for forest biodiversity, such as the occurrence of species with low economical but high ecological values. Airborne hyperspectral imagery has shown significant potential for tree species classification, but the most common analysis methods, such as random forest and support vector machines, require manual feature engineering in order to utilize both spatial and spectral features, whereas deep learning methods are able to extract these features from the raw data. Our research focused on the classification of the major tree species Scots pine, Norway spruce and birch, together with an ecologically valuable keystone species, European aspen, which has a sparse and scattered occurrence in boreal forests. We compared the performance of three-dimensional convolutional neural networks (3D-CNNs) with the support vector machine, random forest, gradient boosting machine and artificial neural network in individual tree species classification from hyperspectral data with high spatial and spectral resolution. We collected hyperspectral and LiDAR data along with extensive ground reference data measurements of tree species from the 83 km2 study area located in the southern boreal zone in Finland. A LiDAR-derived canopy height model was used to match ground reference data to aerial imagery. The best performing 3D-CNN, utilizing 4 m image patches, was able to achieve an F1-score of 0.91 for aspen, an overall F1-score of 0.86 and an overall accuracy of 87%, while the lowest performing 3D-CNN utilizing 10 m image patches achieved an F1-score of 0.83 and an accuracy of 85%. In comparison, the support-vector machine achieved an F1-score of 0.82 and an accuracy of 82.4% and the artificial neural network achieved an F1-score of 0.82 and an accuracy of 81.7%. Compared to the reference models, 3D-CNNs were more efficient in distinguishing coniferous species from each other, with a concurrent high accuracy for aspen classification. Deep neural networks, being black box models, hide the information about how they reach their decision. We used both occlusion and saliency maps to interpret our models. Finally, we used the best performing 3D-CNN to produce a wall-to-wall tree species map for the full study area that can later be used as a reference prediction in, for instance, tree species mapping from multispectral satellite images. The improved tree species classification demonstrated by our study can benefit both sustainable forestry and biodiversity conservation.