Spectral discrimination of giant reed (Arundo donax L.): A seasonal study in riparian areas

Fernandes, María Rosário; Aguiar, Francisca C.; Silva, João M. N.; Ferreira, Maria Teresa; Pereira, José M. C.

doi:10.1016/j.isprsjprs.2013.03.007

Cited by 42 publications

(28 citation statements)

References 46 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, greenness was found to be an important factor discriminating the invasive Arundo donax L. from adjacent riparian vegetation in Portugal, as it produced new fresh green leaves when water was available during the vegetative period [14]. Acacia longifolia, too, has a high growth rate and extended growth period [42,55], efficient nutrient acquisition [41] and high transpiration rates [45] while having a different leaf type (large phyllodes) compared to native species in this dune ecosystem [23,111].…”

Section: Interpretation Of the Relevant Vegetation Indices For Identimentioning

confidence: 99%

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

et al. 2016

View full text Add to dashboard Cite

Hyperspectral remote sensing is an effective tool to discriminate plant species, providing vast potential to trace plant invasions for ecological assessments. However, necessary baseline information for the use of remote sensing data is missing for many high-impact invaders. Furthermore, the identification of the suitable classification algorithms and spectral regions for successfully classifying species remains an open field of research. Here, we tested the separability of the invasive tree Acacia longifolia from adjacent exotic and native vegetation in a Natura 2000 protected Mediterranean dune ecosystem. We used continuous visible, near-infrared and short wave infrared (VNIR-SWIR) data as well as vegetation indices at the leaf and canopy level for classification, comparing five different classification algorithms. We were able to successfully distinguish A. longifolia from surrounding vegetation based on vegetation indices. At the leaf level, radial-basis function kernel Support Vector Machine (SVM) and Random Forest (RF) achieved both a high Sensitivity (SVM: 0.83, RF: 0.78) and a high Positive Predicted Value (PPV) (0.86, 0.83). At the canopy level, RF was the classifier with an optimal balance of Sensitivity (0.75) and PPV (0.75). The most relevant vegetation indices were linked to the biochemical parameters chlorophyll, water, nitrogen, and cellulose as well as vegetation cover, which is in line with biochemical and ecophysiological properties reported for A. longifolia. Our results highlight the potential to use remote sensing as a tool for an early detection of A. longifolia in Mediterranean coastal ecosystems.

show abstract

Section: Interpretation Of the Relevant Vegetation Indices For Identimentioning

confidence: 99%

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

et al. 2016

View full text Add to dashboard Cite

show abstract

“…For example, Fernandes et al (2013) found the visible and the mid infra-red region best at discriminating giant reed (Arundo donax L.) from adjacent vegetation. Abdel-Rahman et al (2014) found 50 bands located in the red edge (670-780 nm), blue (400-500nm) and green edge (500-600nm) of the electromagnetic spectrum of the AISA Eagle image best at detecting Sirex noctilio grey-attacked and lightning-struck pine trees.…”

Section: Discussionmentioning

confidence: 99%

“…Such conditions are best achieved at local noon time. This position permits attaining most of the reflected electromagnetic radiation (Cho et al 2008;Fernandes et al 2013;Mansour 2013;Olsson et al 2011;Rudolf et al 2015). However, not all measurements were taken using this protocol due to time constraint of the study that forced data acquisition outside of the ideal time.…”

Section: Study Areamentioning

confidence: 99%

Assessing the potential of remote sensing to discriminate invasive <i>Seriphium plumosum</i> from grass

Dubula¹,

Tefsamichael²,

Rampedi³

2016

SA J of Geomatics

View full text Add to dashboard Cite

show abstract

“…However, in the case of the Mediterranean forest, the classification results are more moderate, mainly due to the high density and the diversity of the species that coexist in the same space, or due to a lack of space between the trees. This causes overlaps between the crowns, which can generate erroneous spectral information [25,26].…”

Section: Introductionmentioning

confidence: 99%

Evaluation and Comparison of QuickBird and ADS40-SH52 Multispectral Imagery for Mapping Iberian Wild Pear Trees (Pyrus bourgaeana, Decne) in a Mediterranean Mixed Forest

Arenas‐Castro

Fernández-Haeger

Jordano-Barbudo

2014

Forests

View full text Add to dashboard Cite

Abstract:The availability of images with very high spatial and spectral resolution from airborne sensors or those aboard satellites is opening new possibilities for the analysis of fine-scale vegetation, such as the identification and classification of individual tree species. To evaluate the potential of these images, a study was carried out to compare the spatial, spectral and temporal resolution between QuickBird and ADS40-SH52 imagery, in order to discriminate and identify, within the mixed Mediterranean forest, individuals of the Iberian wild pear (Pyrus bourgaeana). This is a typical species of the Mediterranean forest, but its biology and ecology are still poorly known. The images were subjected to different correction processes and data were homogenized. Vegetation classes and individual trees were identified on the images, which were classified from two types of supervised classification (Maximum Likelihood and Support Vector Machines) on a pixel-by-pixel basis. The classification values were satisfactory. The classifiers were compared, and Support Vector Machines was the algorithm that provided the best results in terms of overall accuracy. The QuickBird image showed higher overall accuracy (86.16%) when the Support Vector Machines algorithm was applied. In addition, individuals of Iberian wild pear were discriminated with probability of over 55%, when the Maximum Likelihood algorithm was applied. From the perspective of improving the sampling effort, these results OPEN ACCESSForests 2014, 5 1305 are a starting point for facilitating research on the abundance, distribution and spatial structure of P. bourgaeana at different scales, in order to quantify the conservation status of this species.

show abstract

Spectral discrimination of giant reed (Arundo donax L.): A seasonal study in riparian areas

Cited by 42 publications

References 46 publications

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

Evaluation of Continuous VNIR-SWIR Spectra versus Narrowband Hyperspectral Indices to Discriminate the Invasive Acacia longifolia within a Mediterranean Dune Ecosystem

Assessing the potential of remote sensing to discriminate invasive <i>Seriphium plumosum</i> from grass

Evaluation and Comparison of QuickBird and ADS40-SH52 Multispectral Imagery for Mapping Iberian Wild Pear Trees (Pyrus bourgaeana, Decne) in a Mediterranean Mixed Forest

Contact Info

Product

Resources

About