Mapping plant species in mixed grassland communities using close range imaging spectroscopy

Lopatin, Javier; Kattenborn, Teja; Schmidtlein, Sebastian

doi:10.1016/j.rse.2017.08.031

Cited by 80 publications

(78 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When the separation of a species from other species with similar spectral characteristics is pursued, the high amount of intraspecific variance can hamper pixel‐based classification performances (Lopatin et al. ).…”

Section: Discussionmentioning

confidence: 99%

“…This bootstrap test has been applied in earlier studies following similar approaches (Lopatin et al. , ; Castillo‐Riffart et al. ; Araya‐López et al.…”

Section: Methodsmentioning

confidence: 99%

“…One drawback of very‐high spatial resolution imagery is the increase of spectral within‐class variability caused by canopy structure and shadows, which often hamper the separability of classes in pixel‐based studies (Lopatin et al. ). Shadows result from the obstruction of light, causing a decrease of reflectance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

Lopatin

Dološ

Kattenborn

2019

Remote Sens Ecol Conserv

Self Cite

View full text Add to dashboard Cite

Plant invasions can result in serious threats for biodiversity and ecosystem functioning. Reliable maps at very‐high spatial resolution are needed to assess invasions dynamics. Field sampling approaches could be replaced by unmanned aerial vehicles (UAVs) to derive such maps. However, pixel‐based species classification at high spatial resolution is highly affected by within‐canopy variation caused by shadows. Here, we studied the effect of shadows on mapping the occurrence of invasive species using UAV‐based data. MaxEnt one‐class classifications were applied to map Acacia dealbata, Ulex europaeus and Pinus radiata in central‐south Chile using combinations of UAV‐based spectral (RGB and hyperspectral), 2D textural and 3D structural variables including and excluding shaded canopy pixels during model calibration. The model accuracies in terms of area under the curve (AUC), Cohen's Kappa, sensitivity (true positive rate) and specificity (true negative rate) were examined in sunlit and shaded canopies separately. Bootstrapping was used for validation and to assess statistical differences between models. Our results show that shadows significantly affect the accuracies obtained with all types of variables. The predictions in shaded areas were generally inaccurate, leading to misclassification rates between 65% and 100% even when shadows were included during model calibration. The exclusion of shaded areas from model calibrations increased the predictive accuracies (especially in terms of sensitivity), decreasing false positives. Spectral and 2D textural information showed generally higher performances and improvements when excluding shadows from the analysis. Shadows significantly affected the model results obtained with any of the variables used, hence the exclusion of shadows is recommended prior to model calibration. This relatively easy pre‐processing step enhances models for classifying species occurrences using high‐resolution spectral imagery and derived products. Finally, a shadow simulation showed differences in the ideal acquisition window for each species, which is important to plan revisit campaigns.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This bootstrap test has been applied in earlier studies following similar approaches (Lopatin et al. , ; Castillo‐Riffart et al. ; Araya‐López et al.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

Lopatin

Dološ

Kattenborn

2019

Remote Sens Ecol Conserv

Self Cite

View full text Add to dashboard Cite

show abstract

“…leaf angle) cannot be captured. Although in situ canopy measurements do pick up both biochemical and physical plant properties, the mismatch between their spatial resolution and the small scale heterogeneity of herbaceous ecosystems often impedes species‐specific measurements (Lopatin, Fassnacht, Kattenborn, & Schmidtlein, ). Finally, experimental set‐ups enable individual species canopy measurements, but simplify natural field conditions where biotic and abiotic interactions might influence the species' characteristics.…”

Section: Introductionmentioning

confidence: 99%

A novel procedure for measuring functional traits of herbaceous species through field spectroscopy

et al. 2019

View full text Add to dashboard Cite

Collecting species‐level information on plant functional traits is highly relevant for understanding ecosystem functioning under global change. Measuring optical properties of plant species is a promising approach to retrieve such data, but standardized protocols are essential. Due to fine‐scale heterogeneity of many vegetation types, measuring the spectral response, as a proxy for functional traits, of individual plant species remains challenging using conventional approaches. Here we present a novel method for measuring the reflectance of individual species in situ. The procedure consists of measuring monospecific arrangements of plant individuals on a black, light absorbing table, preserving structural plant properties while avoiding the admixture of other species, soil or non‐photosynthetically active vegetation. To evaluate the feasibility of the approach, a case study was conducted on forbs, where we collected and compared the reflectance of 16 herbaceous species at different phenological stages, both using common field spectroscopy and by following our novel procedure. Our procedure accurately represented spectral and functional differences between species. Spectral shape, and to a lesser extent, amplitude differences between species were preserved (SAM: Mantel r = 0.69 and p = 0.001; Manhattan distance: Mantel r = 0.42 and p = 0.002). Moreover, the method was able to capture the pattern of functional traits present among the sampled species (Procrustes r = 0.81 and p = 0.001). The new method is promising for building databases of plant traits based on spectral libraries. It might, moreover, form a standardized procedure for field campaigns, especially in the context of mixed grasslands and forb systems where relatively small plants dominate the ecosystem.

show abstract

“…However, many researchers indicate that multispectral data such as Landsat and SPOT images produce general land cover classifications that are too broad to be utilized for identification of orchards species. Discrimination of subtle differences in species composition remains a major problem of these systems [8][9][10]. Consequently, the application of airborne imaging spectroscopy information in conjunction with field spectroscopy is essential in orchard discrimination at the species level [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Optimal Spectral Wavelengths for Discriminating Orchard Species Using Multivariate Statistical Techniques

et al. 2019

View full text Add to dashboard Cite

Sustainable management of orchard fields requires detailed information about the tree types, which is a main component of precision agriculture programs. To this end, hyperspectral imagery can play a major role in orchard tree species mapping. Efficient use of hyperspectral data in combination with field measurements requires the development of optimized band selection strategies to separate tree species. In this study, field spectroscopy (350 to 2500 nm) was performed through scanning 165 spectral leaf samples of dominant orchard tree species (almond, walnut, and grape) in Chaharmahal va Bakhtiyari province, Iran. Two multivariable methods were employed to identify the optimum wavelengths: the first includes three-step approach ANOVA, random forest classifier (RFC) and principal component analysis (PCA), and the second employs partial least squares (PLS). For both methods we determined whether tree species can be spectrally separated using discriminant analysis (DA) and then the optimal wavelengths were identified for this purpose. Results indicate that all species express distinct spectral behaviors at the beginning of the visible range (from 350 to 439 nm), the red edge and the near infrared wavelengths (from 701 to 1405 nm). The ANOVA test was able to reduce primary wavelengths (2151) to 792, which had a significant difference (99% confidence level), then the RFC further reduced the wavelengths to 118. By removing the overlapping wavelengths, the PCA represented five components (99.87% of variance) which extracted optimal wavelengths were: 363, 423, 721, 1064, and 1388 nm. The optimal wavelengths for the species discrimination using the best PLS-DA model (100% accuracy) were at 397, 515, 647, 1386, and 1919 nm.

show abstract

Mapping plant species in mixed grassland communities using close range imaging spectroscopy

Cited by 80 publications

References 32 publications

How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

A novel procedure for measuring functional traits of herbaceous species through field spectroscopy

Optimal Spectral Wavelengths for Discriminating Orchard Species Using Multivariate Statistical Techniques

Contact Info

Product

Resources

About