Brightness-normalized Partial Least Squares Regression for hyperspectral data

Feilhauer, Hannes; Asner, Gregory P.; Martin, Robert E.; Schmidtlein, Sebastian

doi:10.1016/j.jqsrt.2010.03.007

Cited by 142 publications

(108 citation statements)

References 28 publications

Supporting

Mentioning

106

Contrasting

Unclassified

Order By: Relevance

“…Plant canopy reflectance is affected by either the observing conditions; variable viewing and illumination geometry; or variations in the target such as variable LAI or internal shade from the canopy structure. Feilhauer et al [39] showed that a brightness-normalised modification to the PLSR significantly improved the prediction of leaf chemistry from normal PLSR, but made little improvement on the effects of variable LAI and variable viewing angle. A further refinement of the model in the future could be to test this adapted algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…Direct comparison to results obtained from indices also prove PLSR to be more accurate [36,38]. PLSR applies a data compression within the regression and, as such, is a promising technique for quantitatively assessing vegetation characteristics, efficiently using the full spectral information of hyperspectral data [34,39]. It has become an established technique in vegetation remote sensing, used extensively for biochemical and biophysical modelling [36,37,40].…”

Section: Regression Modellingmentioning

confidence: 99%

“…Similar to Principal Component Regression (PCR), the information content of the intercorrelated bands is reduced to a few independent latent factors, or vectors. Most important, these latent vectors are not only generated to maximise information content in the spectral information as a PCA, but are also optimised for the response variable [39,43]. This may be expected to lead to better calibration in comparison to other linear empirical-statistical methods.…”

Section: Regression Modellingmentioning

confidence: 99%

See 2 more Smart Citations

Empirical Modelling of Vegetation Abundance from Airborne Hyperspectral Data for Upland Peatland Restoration Monitoring

2014

View full text Add to dashboard Cite

Abstract:Peatlands are important terrestrial carbon stores. Restoration of degraded peatlands to restore ecosystem services is a major area of conservation effort. Monitoring is crucial to judge the success of this restoration. Remote sensing is a potential tool to provide landscape-scale information on the habitat condition. Using an empirical modelling approach, this paper aims to use airborne hyperspectral image data with ground vegetation survey data to model vegetation abundance for a degraded upland blanket bog in the United Kingdom (UK), which is undergoing restoration. A predictive model for vegetation abundance of Plant Functional Types (PFT) was produced using a Partial Least Squares Regression (PLSR) and applied to the whole restoration site. A sensitivity test on the relationships between spectral data and vegetation abundance at PFT and single species level confirmed that PFT was the correct scale for analysis. The PLSR modelling allows selection of variables based upon the weighted regression coefficient of the individual spectral bands, showing which bands have the most influence on the model. These results suggest that the SWIR has less value for monitoring peatland vegetation from hyperspectral images than initially predicted. RMSE values for the validation data range between 10% and 16% cover, indicating that the models can be used as an operational tool, considering the subjective nature of existing vegetation survey results. These predicted coverage images are the first quantitative landscape scale monitoring results to be produced OPEN ACCESSRemote Sens. 2014, 6 717 for the site. High resolution hyperspectral mapping of PFTs has the potential to assess recovery of peatland systems at landscape scale for the first time.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Regression Modellingmentioning

confidence: 99%

Section: Regression Modellingmentioning

confidence: 99%

See 1 more Smart Citation

Empirical Modelling of Vegetation Abundance from Airborne Hyperspectral Data for Upland Peatland Restoration Monitoring

2014

View full text Add to dashboard Cite

show abstract

“…Following the preparation of the filtered 1-ha resolution spectra, we convolved the data to 10-nm bandwidth and applied a brightness-normalization adjustment (67). This reduced the contribution of varying leaf area index to chemometric determinations of foliar traits from remotely sensed data (68).…”

Section: Methodsmentioning

confidence: 99%

Large-scale climatic and geophysical controls on the leaf economics spectrum

Asner

Knapp

Anderson

et al. 2016

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

109

View full text Add to dashboard Cite

Leaf economics spectrum (LES) theory suggests a universal tradeoff between resource acquisition and storage strategies in plants, expressed in relationships between foliar nitrogen (N) and phosphorus (P), leaf mass per area (LMA), and photosynthesis. However, how environmental conditions mediate LES trait interrelationships, particularly at large biospheric scales, remains unknown because of a lack of spatially explicit data, which ultimately limits our understanding of ecosystem processes, such as primary productivity and biogeochemical cycles. We used airborne imaging spectroscopy and geospatial modeling to generate, to our knowledge, the first biospheric maps of LES traits, here centered on 76 million ha of Andean and Amazonian forest, to assess climatic and geophysical determinants of LES traits and their interrelationships. Elevation and substrate were codominant drivers of leaf trait distributions. Multiple additional climatic and geophysical factors were secondary determinants of plant traits. Anticorrelations between N and LMA followed general LES theory, but topo-edaphic conditions strongly mediated and, at times, eliminated this classic relationship. We found no evidence for simple P-LMA or N-P trade-offs in forest canopies; rather, we mapped a continuum of N-P-LMA interactions that are sensitive to elevation and temperature. Our results reveal nested climatic and geophysical filtering of LES traits and their interrelationships, with important implications for predictions of forest productivity and acclimation to rapid climate change.Amazon basin | functional biogeography | leaf traits | plant traits | tropical forests

show abstract

“…PLS regression reduces the full spectrum to a smaller number of independent factors and takes into account the covariance between the response variable and the predictor variables during the dimensionality reduction process, which makes it superior to other methods like principal components analysis, which only takes into account the variance in the predictor variables [44,45]. This reduction process also helps avoid the problem of overfitting due to the presence of many more predictor variables (wavelengths) than dependent variables (chemical concentration), which is the case with IS data.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Macronutrients at the Canopy Level Using Spaceborne Imaging Spectroscopy and LiDAR Data in a Mixedwood Boreal Forest

et al. 2015

View full text Add to dashboard Cite

Information on foliar macronutrients is required in order to understand plant physiological and ecosystem processes such as photosynthesis, nutrient cycling, respiration and cell wall formation. The ability to measure, model and map foliar macronutrients (nitrogen (N), phosphorus (P), potassium (K), calcium (Ca) and magnesium (Mg)) at the forest canopy level provides information on the spatial patterns of ecosystem processes (e.g., carbon exchange) and provides insight on forest condition and stress. Imaging spectroscopy (IS) has been used particularly for modeling N, using airborne and satellite imagery mostly in temperate and tropical forests. However, there has been very little research conducted at these scales to model P, K, Ca, and Mg and few studies have focused on boreal forests. We report results of a study of macronutrient modeling using spaceborne IS and airborne light OPEN ACCESSRemote Sens. 2015, 7 9046 detection and ranging (LiDAR) data for a mixedwood boreal forest canopy in northern Ontario, Canada. Models incorporating Hyperion data explained approximately 90% of the variation in canopy concentrations of N, P, and Mg; whereas the inclusion of LiDAR data significantly improved the prediction of canopy concentration of Ca (R 2 = 0.80). The combined used of IS and LiDAR data significantly improved the prediction accuracy of canopy Ca and K concentration but decreased the prediction accuracy of canopy P concentration. The results indicate that the variability of macronutrient concentration due to interspecific and functional type differences at the site provides the basis for the relationship observed between the remote sensing measurements (i.e., IS and LiDAR) and macronutrient concentration. Crown closure and canopy height are the structural metrics that establish the connection between macronutrient concentration and IS and LiDAR data, respectively. The spatial distribution of macronutrient concentration at the canopy scale mimics functional type distribution at the site. The ability to predict canopy N, P, K, Ca and Mg in this study using only IS, only LiDAR or their combination demonstrates the excellent potential for mapping these macronutrients at canopy scales across larger geographic areas into the next decade with the launch of new IS satellite missions and by using spaceborne LiDAR data.

show abstract

Brightness-normalized Partial Least Squares Regression for hyperspectral data

Cited by 142 publications

References 28 publications

Empirical Modelling of Vegetation Abundance from Airborne Hyperspectral Data for Upland Peatland Restoration Monitoring

Empirical Modelling of Vegetation Abundance from Airborne Hyperspectral Data for Upland Peatland Restoration Monitoring

Large-scale climatic and geophysical controls on the leaf economics spectrum

Prediction of Macronutrients at the Canopy Level Using Spaceborne Imaging Spectroscopy and LiDAR Data in a Mixedwood Boreal Forest

Contact Info

Product

Resources

About