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).

Land cover is of fundamental importance to many environmental applications and serves as critical baseline information for many large scale models e.g. in developing future scenarios of land use and climate change. Although there is an ongoing movement towards the development of higher resolution global land cover maps, medium resolution land cover products (e.g. GLC2000 and MODIS) are still very useful for modelling and assessment purposes. However, the current land cover products are not accurate enough for many applications so we need to develop approaches that can take existing land covers maps and produce a better overall product in a hybrid approach. This paper uses geographically weighted regression (GWR) and crowdsourced validation data from Geo-Wiki to create two hybrid global land cover maps that use medium resolution land cover products as an input. Two different methods were used: (a) the GWR was used to determine the best land cover product at each location; (b) the GWR was only used to determine the best land cover at those locations where all three land cover maps disagree, using the agreement of the land cover maps to determine land cover at the other cells. The results show that the hybrid land cover map developed using the first method resulted in a lower overall disagreement than the individual global land cover maps. The hybrid map produced by the second method was also better when compared to the GLC2000 and GlobCover but worse or similar in performance to the MODIS land cover product depending upon the metrics considered. The reason for this may be due to the use of the GLC2000 in the development of GlobCover, which may have resulted in areas where both maps agree with one another but not with MODIS, and where MODIS may in fact better represent land cover in those situations. These results serve to demonstrate that spatial analysis methods can be used to improve medium resolution global land cover information with existing products.