Search

Identifying and characterizing vascular plants in time and space is required in various disciplines, e.g. in forestry, conservation and agriculture. Remote sensing emerged as a key technology revealing both spatial and temporal vegetation patterns. Harnessing the ever growing streams of remote sensing data for the increasing demands on vegetation assessments and monitoring requires efficient, accurate and flexible methods for data analysis. In this respect, the use of deep learning methods is trend-setting, enabling high predictive accuracy, while learning the relevant data features independently in an end-to-end fashion. Very recently, a series of studies have demonstrated that the deep learning method of Convolutional Neural Networks (CNN) is very effective to represent spatial patterns enabling to extract a wide array of vegetation properties from remote sensing imagery. This review introduces the principles of CNN and distils why they are particularly suitable for vegetation remote sensing. The main part synthesizes current trends and developments, including considerations about spectral resolution, spatial grain, different sensors types, modes of reference data generation, sources of existing reference data, as well as CNN approaches and architectures. The literature review showed that CNN can be applied to various problems, including the detection of individual plants or the pixel-wise segmentation of vegetation classes, while numerous studies have evinced that CNN outperform shallow machine learning methods. Several studies suggest that the ability of CNN to exploit spatial patterns particularly facilitates the value of very high spatial resolution data. The modularity in the common deep learning frameworks allows a high flexibility for the adaptation of architectures, whereby especially multi-modal or multi-temporal applications can benefit. An increasing availability of techniques for visualizing features learned by CNNs will not only contribute to interpret but to learn from such models and improve our understanding of remotely sensed signals of vegetation. Although CNN has not been around for long, it seems obvious that they will usher in a new era of vegetation remote sensing.

Xylella fastidiosa (Xf) is a harmful plant pathogenic bacterium, able to infect over 500 plant species worldwide. Successful eradication and containment strategies for harmful pathogens require large-scale monitoring techniques for the detection of infected hosts, even when they do not display visual symptoms. Although a previous study using airborne hyperspectral and thermal imagery has shown promising results for the early detection of Xf-infected olive (Olea europaea) trees, further work is needed when adopting these techniques for large scale monitoring using multispectral cameras on board airborne platforms and satellites. We used hyperspectral and thermal imagery collected during a two-year airborne campaign in a Xf-infected area in southern Italy to assess the performance of spectrally constrained machine-learning algorithms for this task. The algorithms were used to assess multispectral bandsets, selected from the original hyperspectral imagery, that were compatible with large-scale monitoring from unmanned platforms and manned aircraft. In addition, the contribution of solar–induced chlorophyll fluorescence (SIF) and the temperature-based Crop Water Stress Index (CWSI) retrieved from hyperspectral and thermal imaging, respectively, were evaluated to quantify their relative importance in the algorithms used to detect Xf infection. The detection performance using support vector machine algorithms decreased from ∼80% (kappa, κ = 0.42) when using the original full hyperspectral dataset including SIF and CWSI to ∼74% (κ = 0.36) when the optimal set of six spectral bands most sensitive to Xf infection were used in addition to the CWSI thermal indicator. When neither SIF nor CWSI were used, the detection yielded less than 70% accuracy (decreasing κ to very low performance, 0.29), revealing that tree temperature was more important than chlorophyll fluorescence for the Xf detection. This work demonstrates that large-scale Xf monitoring can be supported using airborne platforms carrying multispectral and thermal cameras with a limited number of spectral bands (e.g., six to 12 bands with 10 nm bandwidths) as long as they are carefully selected by their sensitivity to the Xf symptoms. More precisely, the blue (bands between 400 and 450 nm to derive the NPQI index) and thermal (to derive CWSI from tree temperature) were the most critical spectral regions for their sensitivity to Xf symptoms in olive., Data collection was partially supported by the European Union’s Horizon 2020 research and innovation program through grants to the POnTE (Pest Organisms threatening Europe; grant 635646 from European Union’s Horizon 2020 Framework Research Programme) and XF-ACTORS (Xylella fastidiosa Active Containment Through a Multidisciplinary-Oriented Research Strategy; grant 727987 from European Union’s Horizon 2020 Framework Research Programme) projects. A. Hornero was supported by a research fellowship DTC GEO 29 “Detection of global photosynthesis and forest health from space” from the Science Doctoral Training Centre (Swansea University, UK).

Plant pathogens cause significant losses to agricultural yields and increasingly threaten food security1, ecosystem integrity and societies in general2–5. Xylella fastidiosa is one of the most dangerous plant bacteria worldwide, causing several diseases with profound impacts on agriculture and the environment6. Primarily occurring in the Americas, its recent discovery in Asia and Europe demonstrates that X. fastidiosa’s geographic range has broadened considerably, positioning it as a reemerging global threat that has caused socioeconomic and cultural damage7,8. X. fastidiosa can infect more than 350 plant species worldwide9, and early detection is critical for its eradication8. In this article, we show that changes in plant functional traits retrieved from airborne imaging spectroscopy and thermography can reveal X. fastidiosa infection in olive trees before symptoms are visible. We obtained accuracies of disease detection, confirmed by quantitative polymerase chain reaction, exceeding 80% when high-resolution fluorescence quantified by three-dimensional simulations and thermal stress indicators were coupled with photosynthetic traits sensitive to rapid pigment dynamics and degradation. Moreover, we found that the visually asymptomatic trees originally scored as affected by spectral plant-trait alterations, developed X. fastidiosa symptoms at almost double the rate of the asymptomatic trees classified as not affected by remote sensing. We demonstrate that spectral plant-trait alterations caused by X. fastidiosa infection are detectable previsually at the landscape scale, a critical requirement to help eradicate some of the most devastating plant diseases worldwide.

Grasslands are one of the ecosystems that have been strongly affected by anthropogenic impacts. The state-of-the-art in monitoring changes in grassland species composition is to conduct repeated plot-based vegetation surveys that assess the occurrence and cover of plants. These plot-based surveys are typically limited to comparably small areas and the quality of the cover estimates depends strongly on the experience and performance of the surveyors. Here, we investigate the possibility of a semi-automated, image-based method for cover estimates, by analyzing the applicability of very high spatial resolution hyperspectral data to classify grassland species at the level of individuals. This individual-oriented approach is seen as an alternative to community-oriented remote sensing depicting canopy reflectance as the total of mixed species reflectance. An AISA + imaging spectrometer mounted on a scaffold was used to scan 1 m 2 grassland plots and assess the impact of four sources of variation on the predicted species cover: (1) the spatial resolution of the scans, (2) complexity, i.e. species number and structural diversity, (3) the species cover and (4) the share of functional types (graminoids and forbs). Classifications were conducted using a support vector machine classification with a linear kernel, obtaining a median Kappa of ~ 0.8. Species cover estimations reached median r 2 and root mean square errors (RMSE) of ~ 0.6 and ~ 6.2% respectively. We found that the spatial resolution and diversity level (mainly structural diversity) were the most important sources of variation affecting the performance of the proposed approach. A spatial resolution below 1 cm produced relatively good models for estimating species-specific coverages (r 2 = ~ 0.6; RMSE = ~ 7.5%) while predictions using pixel sizes over that threshold failed in this individual-oriented approach (r 2 = ~ 0.17; RMSE = ~ 20.7%). Areas with low inter-species overlap were better suited than areas with frequent inter-species overlap. We conclude that the application of very high resolution hyperspectral remote sensing in environments with low structural heterogeneity is suited for individual-oriented mapping of grassland plant species.

Question Do spatial gradients of plant strategies correspond to patterns of plant traits obtained from a physically based model and hyperspectral imagery? It has been shown before that reflectance can be used to map plant strategies according to the established CSR scheme. So far, these approaches were based on empirical links and lacked transferability. Therefore, we test if physically-based derivations of plant traits may help in finding gradients in traits that are linked to strategies. Location A raised bog and minerotrophic fen complex, Murnauer Moos, Germany. Methods Spatial distributions of plant traits were modelled by adopting an inversion of the PROSAIL radiative transfer model on airborne hyperspectral imagery. The traits are derived from reflectance without making use of field data but only of known links between reflectance and traits. We tested whether previously found patterns in CSR plant strategies were related to the modelled traits. Results The results confirm close relationships between modelled plant traits and C, S and R strategies that were previously found in the field. The modelled plant traits explained different dimensions of the CSR-space. Leaf Area Index (LAI) and the reciprocal of Specific Leaf Area appeared to be good candidates for reproducing CSR scores as community traits using remote sensing. LAI has not been used in previous studies to allocate plant strategies. Conclusions Combining RTMs and the CSR model is a promising approach for establishing a robust link between airborne or spaceborne imagery and plant functioning. The demonstrated potential to map traits with close relation to CSR gradients using only our understanding of the relation between traits and reflectance is a step forward towards an operational use of the CSR model in remote sensing. This article is protected by copyright. All rights reserved.

The estimation of various forest inventory attributes from high spatial resolution airborne remote sensing data has been widely examined and proved to be successful at the experimental level. Nevertheless, the operational use of these data in automated procedures to support forest inventories and forest management is still limited to a small number of cases. The reasons for this are high data costs, limited availability of remote sensing data over large areas and resistance from practitioners. In this review the main aim is to stimulate debate about spaceborne very high resolution stereo-imagery (VHRSI) as an alternative to airborne remote sensing data by presenting: (1) a case study on the retrieval of stand density, aboveground biomass and tree species using a set of easy-to-calculate variables obtained from VHRSI data combined with image processing and nonparametric classification and modelling approaches; and (2) the results of an expert opinion survey on the potential of VHRSI as compared with Light Detection and Ranging (LiDAR), hyperspectral and airborne digital imagery to derive a range of forest inventory attributes. In the case study, stand density was estimated with r² = 0.71 and RMSE = 156 trees (rel./norm. RMSE = 24.9 per cent/12.4 per cent), biomass with r² = 0.64 and RMSE of 36.7 t/ha (rel./norm. RMSE = 20.0 per cent/12.8 per cent) while tree species classifications with five species reached overall accuracies of 84.2 per cent (kappa = 0.81). These results were comparable to earlier studies in the same test site, obtained with more expensive airborne acquisitions. Expert opinions were more diverse for VHRSI and aerial photographs (Shannon index values of 0.94 and 0.97) than for LiDAR and hyperspectral data (Shannon index values 0.69 and 0.88). In our opinion, this reflects the current state-of-the-art in the application of VHRSI for automatically retrieving forest inventory attributes. The number of studies using these data is still limited, and the full potential of these datasets is not yet completely explored. Compared with LiDAR and hyperspectral data, which both mostly received high scores for forest inventory products matching the sensor systems’ strengths, VHRSI and aerial photographs received more homogeneous scores indicating their potential as multi-purpose instruments to collect forest inventory information. In summary, considering the simpler acquisition, reasonable price and the comparably easy data format and handling of VHRSI compared with other sensor types, we recommend further research on the application of these data for supporting operational forest inventories.

With consumer-grade unmanned aerial vehicles (UAVs) on the rise, which enable easy, time-flexible, and cost-effective acquisition of very high-resolution RGB data, the mapping of forest tree species using solely RGB imagery is of high interest, as it does not rely on sophisticated sensors, does not require extensive calibration and preprocessing and, therefore, enables the application by a wide audience. In combination with convolutional neural networks (CNNs), which particularly exploit spatial patterns and, therefore, highly benfit from very high-resolution remote sensing, this offers great potential for accurately mapping forest tree species.Here, we present the findings of our recent study, in which we used very high-resolution RGB imagery from UAVs in combination with CNNs for the mapping of forest tree species. In this study, we used multicopter UAVs to obtain very high-resolution (In this contribution, we will give an outlook on how the combination of UAV imagery and CNNs can be integrated with multitemporal satellite imagery (Sentinel-1 and Sentinel-2) in order to extrapolate the UAV-based tree species maps to larger areas.

The widely established CSR-model quantitatively groups plants according to their ecological response, i.e. competitiveness, stress-toleration and ruderality. These plant strategies are allocated using plant traits. We assess the potential of canopy traits derived by imaging spectroscopy and inverted radiative transfer models for allocating CSR-scores. Our findings indicate that plant traits (LAI, Cab, Car and SLA) are valuable ‘soft traits’ to map plant strategies.

This chapter reviews the use of airborne LiDAR data for the segmentation of forest to tree objects. The benefit obtained by LiDAR data is typically related to the use of the third dimension, i.e. the height data. Forest and stand objects may be segmented based on physical criteria, for example height and density information, while a further delineation to different timber types would require leaf-off data or an additional data source such as spectral images. Most forest applications of the LiDAR data are based on using digital surface models, but especially tree-level segmentation may benefit from a combination of raster and point data, and can be performed solely on point data. Finally, there are several established techniques for tree shape reconstruction based on the segmented point data.