Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression

By Moses Azong Cho, Andrew K. Skidmore, Fabio Corsi, Sipke E. van Wieren, I. Sobhan. International Journal of Applied Earth Observation and Geoinformation, 2007

397 citations recorded by the source corpus.

Subfields: Ecological Modeling, Ecology, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/84f10074d07d9f8eae8b6be9298cf1d3d8d69e29

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

In Ecology

In Global and Planetary Change

Citations in the corpus

An investigation into robust spectral indices for leaf chlorophyll estimation (2011, background): “Furthermore, broadband NDVIs asymptotically approach a saturation level after a leaf area index (LAI) of approximately 4 (Seller, 1985; Mutanga and Skidmore, 2004; Cho et al., 2007).”
Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat (2010, background): “It s also employed in remote sensing for studying vegetation and oil characteristics (Cho et al., 2007; Hansen and Schjoerring, 2003; arifteh et al., 2007; Nguyen and Lee, 2006).”
A comparison of three methods for estimating leaf area index of paddy rice from optimal hyperspectral bands (2011, neutral): “However, instead of first decomposing the spectra into a set of eigenvectors and scores and regressing them against the response variables as a separate step, PLS regression uses information from the response variable during the decomposition process (Cho et al. 2007).”
Water-removed spectra increase the retrieval accuracy when estimating savanna grass nitrogen and phosphorus concentrations (2011, methodology): “The leave-one-out cross validation, as defined by the lowest root mean square error (RMSE), was used to determine the optimal number of factors or latent variables to be used for model development (Cho et al. 2007; Viscarra Rossel 2008; Darvishzadeh et al. 2008a).”
Combining leaf physiology, hyperspectral imaging and partial least squares-regression (PLS-R) for grapevine water status assessment (2015, background): “…studies, which demonstrate the superiority of indices that are targeted for specific variables or species over non-specific formulations (e.g., Cho et al., 2007; Fu et al., 2014; Hansen and Schjoerring, 2003; Huang et al., 2004; Li et al., 2014., 2008; Ramoelo et al., 2013; Yi et al., 2014).”
Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties - A review (2015, methodology): “Cho et al. (2007) and Im et al. (2009) applied PLSR to estimate bio-geophysical properties of crops (LAI, stem biomass and leaf nutrient concentrations), while Wolter et al. (2009) applied PLS to map forest structural variables (canopy diameter, tree height, crown closure).”
LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements (2008, methodology): “, 2004; Nguyen and Lee, 2006) and biophysical properties (Atzberger et al., 2003b; Cho et al., 2007; Hansen and Schjoerring, 2003; Naesset et al., 2005).”
High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm (2012, methodology): “An × 8 pixels window (i.e. 16 m × 16 m) was used to collect vegetaion image spectra from each band (n = 8) using ArcGIS 10 software. n 8 × 8 pixels window was used in order to avoid including pixls located outside the plot (20 m × 20 m) (Cho et al., 2007).”