The identification of tree species is an important issue in forest management. In recent years, many studies have explored this topic using hyperspectral, multispectral, and LiDAR data. In this study ...we analyzed two multi-sensor set-ups: 1) airborne high spatial resolution hyperspectral images combined with LiDAR data; and 2) high spatial resolution satellite multispectral images combined with LiDAR data. Two LiDAR acquisitions were considered: low point density (approx. 0.48points per m2) and high point density (approx. 8.6points per m2). The aims of this work were: i) to understand what level of classification accuracy can be achieved using a high spectral and spatial resolution multi-sensor data set-up (very high spatial and spectral resolution airborne hyperspectral images integrated with high point density LiDAR data), over a mountain area characterized by many species, both broadleaf and coniferous; ii) to understand the implications of a downgrading of the data characteristics (in terms of spectral resolution of spectral data and point density of LiDAR data), on species separability, with respect to the previous set-up; and iii) to understand the differences between high- and low-point density LiDAR acquisitions on tree species classification. The study region was a mountain area in the Southern Alps characterized by many tree species (7 species and a “non-forest” class), either coniferous or broadleaf. For each set-up a specific processing chain was adopted, from the pre-processing of the raw data to the classification (two classifiers were used: support vector machine and random forest). Different class definitions were tested, including general macro-classes, forest types, and finally single tree species. Experimental results showed that the set-up based on hyperspectral data was effective with general macro-classes, forest types, and single species, reaching high kappa accuracies (93.2%, 82.1% and 76.5%, respectively). The use of multispectral data produced a reduction in the classification accuracy, which was sharp for single tree species, and still high for forest types. Considering general macro-classes, the multispectral set-up was still very accurate (85.8%). Regarding LiDAR data, the experimental analysis showed that high density LiDAR data provided more information for tree species classification with respect to low density data, when combined with either hyperspectral or multispectral data.
► Hyperspectral data allow one to distinguish similar species. ► Downscaling the spectral resolution reduces the discrimination ability of the data. ► Multispectral data are effective for macro-classes discrimination. ► The addition of LiDAR data increase the classification accuracy. ► High point density LiDAR data allow higher class accuracy than low point density data.
Display omitted
•Sentinel-2 and PlanetScope used for the first time for grassland FVC estimation.•Vegetation indices enhance the band spectral separability of bright soils.•Best indices based on NIR ...and red for Sentinel-2, NIR and red-edge for PlanetScope.•High resolution necessary to effectively describe grassland FVC spatial variability.
Grassland fractional vegetation cover (FVC) accurate mapping on a large scale is crucial, since degraded grasslands contribute less to provisioning services, carbon storage, water purification, erosion control and biodiversity conservation. The spatial and temporal resolution of Sentinel-2 (S2) and PlanetScope (PS) data has never been explored for grassland FVC estimation so far and will enable researchers and agencies to quantify and map timelier and more precisely grassland processes. In this paper we compare FVC estimation models developed from Landsat-8 (L8), S2 and PS imagery. The reference grassland FVC dataset was obtained on the Paganella ski runs (46.15°N, 11.01°E, Italy) applying unsupervised classification to nadir grassland RGB photographs taken from 1.35 m above the soil. Fractional Response Models between reference FVC and 18 vegetation indices (VIs) extracted from satellite imagery were fitted and analysed. Then, leave-one-out cross validation and spatiotemporal change analysis were also performed. Our study confirms the robustness of the commonly used VIs based on the difference between NIR and the red wavelength region (R2 = 0.91 for EVI using S2 imagery) and indicate that VIs based on the red-edge spectral region are the best performing for PS imagery (R2 = 0.89 for RECI). Only medium to high spatial resolution imagery (S2 and PS) precisely mapped spatial patterns at the study site, since grasslands FVC varies at a fine scale. Previously available imagery at medium to low spatial and temporal resolution (e.g., L8) may still be interesting for analysis requiring long time-series of data.
In this paper, we propose an analysis on the joint effect of hyperspectral and light detection and ranging (LIDAR) data for the classification of complex forest areas. In greater detail, we present: ...1) an advanced system for the joint use of hyperspectral and LIDAR data in complex classification problems; 2) an investigation on the effectiveness of the very promising support vector machines (SVMs) and Gaussian maximum likelihood with leave-one-out-covariance algorithm classifiers for the analysis of complex forest scenarios characterized from a high number of species in a multisource framework; and 3) an analysis on the effectiveness of different LIDAR returns and channels (elevation and intensity) for increasing the classification accuracy obtained with hyperspectral images, particularly in relation to the discrimination of very similar classes. Several experiments carried out on a complex forest area in Italy provide interesting conclusions on the effectiveness and potentialities of the joint use of hyperspectral and LIDAR data and on the accuracy of the different classification techniques analyzed in the proposed system. In particular, the elevation channel of the first LIDAR return was very effective for the separation of species with similar spectral signatures but different mean heights, and the SVM classifier proved to be very robust and accurate in the exploitation of the considered multisource data.
Photosynthesis is the process by which plants harvest sunlight to produce sugars from carbon dioxide and water. It is the primary source of energy for all life on Earth; hence it is important to ...understand how this process responds to climate change and human impact. However, model-based estimates of gross primary production (GPP, output from photosynthesis) are highly uncertain, in particular over heavily managed agricultural areas. Recent advances in spectroscopy enable the space-based monitoring of sun-induced chlorophyll fluorescence (SIF) from terrestrial plants. Here we demonstrate that spaceborne SIF retrievals provide a direct measure of the GPP of cropland and grassland ecosystems. Such a strong link with crop photosynthesis is not evident for traditional remotely sensed vegetation indices, nor for more complex carbon cycle models. We use SIF observations to provide a global perspective on agricultural productivity. Our SIF-based crop GPP estimates are 50-75% higher than results from state-of-the-art carbon cycle models over, for example, the US Corn Belt and the Indo-Gangetic Plain, implying that current models severely underestimate the role of management. Our results indicate that SIF data can help us improve our global models for more accurate projections of agricultural productivity and climate impact on crop yields. Extension of our approach to other ecosystems, along with increased observational capabilities for SIF in the near future, holds the prospect of reducing uncertainties in the modeling of the current and future carbon cycle.
An international data science challenge, called National Ecological Observatory Network-National Institute of Standards and Technology data science evaluation, was set up in autumn 2017 with the goal ...to improve the use of remote sensing data in ecological applications. The competition was divided into three tasks: (1) individual tree crown (ITC) delineation, for identifying the location and size of individual trees; (2) alignment between field surveyed trees and ITCs delineated on remote sensing data; and (3) tree species classification. In this paper, the methods and results of team Fondazione Edmund Mach (FEM) are presented. The ITC delineation (Task 1 of the challenge) was done using a region growing method applied to a near-infrared band of the hyperspectral images. The optimization of the parameters of the delineation algorithm was done in a supervised way on the basis of the Jaccard score using the training set provided by the organizers. The alignment (Task 2) between the delineated ITCs and the field surveyed trees was done using the Euclidean distance among the position, the height, and the crown radius of the ITCs and the field surveyed trees. The classification (Task 3) was performed using a support vector machine classifier applied to a selection of the hyperspectral bands and the canopy height model. The selection of the bands was done using the sequential forward floating selection method and the Jeffries Matusita distance. The results of the three tasks were very promising: team FEM ranked first in the data science competition in Task 1 and 2, and second in Task 3. The Jaccard score of the delineated crowns was 0.3402, and the results showed that the proposed approach delineated both small and large crowns. The alignment was correctly done for all the test samples. The classification results were good (overall accuracy of 88.1%, kappa accuracy of 75.7%, and mean class accuracy of 61.5%), although the accuracy was biased toward the most represented species.
•Forest windthrows mapping through the use of high spatial and multispectral satellite images.•Influence and relevance of temporal, spectral and spatial resolutions for windthrows ...mapping.•Dependency/independency of acquisition conditions for an accurate detection of windthrows.•Automatic windthrow mapping with two-dimensional Change Vector Analysis.
Wind disturbances represent the main source of damage in European forests, affecting them directly (windthrows) or indirectly due to secondary damages (insect outbreaks and forest fires). The assessment of windthrows damages is very important to establish adequate management plans and remote sensing can be very useful for this purpose. Many types of optical remote sensing data are available with different spectral, spatial and temporal resolutions, and many options are possible for data acquisition, i.e. immediately after the event or after a certain time. The objective of this study is to compare the windthrows mapping capabilities of two multispectral satellite constellations (i.e. Sentinel-2 and PlanetScope) characterized by very different spectral, spatial and temporal resolutions, and to evaluate the impact of the acquisition conditions on the mapping results. The analysed area, with an extent of 732 km2, is located in the Trentino-South Tyrol region (Italy) which was affected by the Vaia storm on the 27th-30th of October 2018, causing serious forest damages. The change vector analysis technique was used to detect the windthrows. For each data source, two pairs of images were considered: 1) pre- and post- event images acquired as close as possible to the event; 2) pre- and post- event images acquired at optimal conditions, i.e. at similar phenological state and similar illumination conditions. The results obtained with the two satellite constellations are very similar despite their different resolutions. Data acquired in optimal conditions allowed having the best detection rate (accuracy above 80 %), while data acquired just after the event showed many limitations. Improved spatial resolution (PlanetScope data) allows for a better delineation of the borders of the windthrow areas and of the detection of smaller windthrow patches.
We upscaled FLUXNET observations of carbon dioxide, water, and energy fluxes to the global scale using the machine learning technique, model tree ensembles (MTE). We trained MTE to predict site‐level ...gross primary productivity (GPP), terrestrial ecosystem respiration (TER), net ecosystem exchange (NEE), latent energy (LE), and sensible heat (H) based on remote sensing indices, climate and meteorological data, and information on land use. We applied the trained MTEs to generate global flux fields at a 0.5° × 0.5° spatial resolution and a monthly temporal resolution from 1982 to 2008. Cross‐validation analyses revealed good performance of MTE in predicting among‐site flux variability with modeling efficiencies (MEf) between 0.64 and 0.84, except for NEE (MEf = 0.32). Performance was also good for predicting seasonal patterns (MEf between 0.84 and 0.89, except for NEE (0.64)). By comparison, predictions of monthly anomalies were not as strong (MEf between 0.29 and 0.52). Improved accounting of disturbance and lagged environmental effects, along with improved characterization of errors in the training data set, would contribute most to further reducing uncertainties. Our global estimates of LE (158 ± 7 J × 1018 yr−1), H (164 ± 15 J × 1018 yr−1), and GPP (119 ± 6 Pg C yr−1) were similar to independent estimates. Our global TER estimate (96 ± 6 Pg C yr−1) was likely underestimated by 5–10%. Hot spot regions of interannual variability in carbon fluxes occurred in semiarid to semihumid regions and were controlled by moisture supply. Overall, GPP was more important to interannual variability in NEE than TER. Our empirically derived fluxes may be used for calibration and evaluation of land surface process models and for exploratory and diagnostic assessments of the biosphere.
Insect outbreaks affect forests, causing the deaths of trees and high economic loss. In this study, we explored the detection of European spruce bark beetle (Ips typographus, L.) outbreaks at the ...individual tree crown level using multispectral satellite images. Moreover, we explored the possibility of tracking the progression of the outbreak over time using multitemporal data. Sentinel-2 data acquired during the summer of 2020 over a bark beetle–infested area in the Italian Alps were used for the mapping and tracking over time, while airborne lidar data were used to automatically detect the individual tree crowns and to classify tree species. Mapping and tracking of the outbreak were carried out using a support vector machine classifier with input vegetation indices extracted from the multispectral data. The results showed that it was possible to detect two stages of the outbreak (i.e., early, and late) with an overall accuracy of 83.4%. Moreover, we showed how it is technically possible to track the evolution of the outbreak in an almost bi-weekly period at the level of the individual tree crowns. The outcomes of this paper are useful from both a management and ecological perspective: it allows forest managers to map a bark beetle outbreak at different stages with a high spatial accuracy, and the maps describing the evolution of the outbreak could be used in further studies related to the behavior of bark beetles.
Remote sensing hyperspectral sensors are important and powerful instruments for addressing classification problems in complex forest scenarios, as they allow one a detailed characterization of the ...spectral behavior of the considered information classes. However, the processing of hyperspectral data is particularly complex both from a theoretical viewpoint e.g. problems related to the Hughes phenomenon (Hughes, 1968) and from a computational perspective. Despite many previous investigations that have been presented in the literature on feature reduction and feature extraction in hyperspectral data, only a few studies have analyzed the role of spectral resolution on the classification accuracy in different application domains. In this paper, we present an empirical study aimed at understanding the relationship among spectral resolution, classifier complexity, and classification accuracy obtained with hyperspectral sensors for the classification of forest areas. We considered two different test sets characterized by images acquired by an AISA Eagle sensor over 126 bands with a spectral resolution of 4.6 nm, and we subsequently degraded its spectral resolution to 9.2, 13.8, 18.4, 23, 27.6, 32.2 and 36.8 nm. A series of classification experiments were carried out with bands at each of the degraded spectral resolutions, and bands selected with a feature selection algorithm at the highest spectral resolution (4.6 nm). The classification experiments were carried out with three different classifiers: Support Vector Machine, Gaussian Maximum Likelihood with Leave-One-Out-Covariance estimator, and Linear Discriminant Analysis. From the experimental results, important conclusions can be made about the choice of the spectral resolution of hyperspectral sensors as applied to forest areas, also in relation to the complexity of the adopted classification methodology. The outcome of these experiments are also applicable in terms of directing the user towards a more efficient use of the current instruments (e.g. programming of the spectral channels to be acquired) and classification techniques in forest applications, as well as in the design of future hyperspectral sensors.
The simulation of gross primary production (GPP) at various spatial and temporal scales remains a major challenge for quantifying the global carbon cycle. We developed a light use efficiency model, ...called EC-LUE, driven by only four variables: normalized difference vegetation index (NDVI), photosynthetically active radiation (PAR), air temperature, and the Bowen ratio of sensible to latent heat flux. The EC-LUE model may have the most potential to adequately address the spatial and temporal dynamics of GPP because its parameters (i.e., the potential light use efficiency and optimal plant growth temperature) are invariant across the various land cover types. However, the application of the previous EC-LUE model was hampered by poor prediction of Bowen ratio at the large spatial scale. In this study, we substituted the Bowen ratio with the ratio of evapotranspiration (ET) to net radiation, and revised the RS-PM (Remote Sensing-Penman Monteith) model for quantifying ET. Fifty-four eddy covariance towers, including various ecosystem types, were selected to calibrate and validate the revised RS-PM and EC-LUE models. The revised RS-PM model explained 82% and 68% of the observed variations of ET for all the calibration and validation sites, respectively. Using estimated ET as input, the EC-LUE model performed well in calibration and validation sites, explaining 75% and 61% of the observed GPP variation for calibration and validation sites respectively.
Global patterns of ET and GPP at a spatial resolution of 0.5° latitude by 0.6° longitude during the years 2000–2003 were determined using the global MERRA dataset (Modern Era Retrospective-Analysis for Research and Applications) and MODIS (Moderate Resolution Imaging Spectroradiometer). The global estimates of ET and GPP agreed well with the other global models from the literature, with the highest ET and GPP over tropical forests and the lowest values in dry and high latitude areas. However, comparisons with observed GPP at eddy flux towers showed significant underestimation of ET and GPP due to lower net radiation of MERRA dataset. Applying a procedure to correct the systematic errors of global meteorological data would improve global estimates of GPP and ET. The revised RS-PM and EC-LUE models will provide the alternative approaches making it possible to map ET and GPP over large areas because (1) the model parameters are invariant across various land cover types and (2) all driving forces of the models may be derived from remote sensing data or existing climate observation networks.