Abstract

In this study we evaluated various spectral inputs for retrieval of forest chlorophyll content (Cab) and leaf area index (LAI) from high spectral and spatial resolution airborne imaging spectroscopy data collected for two forest study sites in the Czech Republic (beech forest at Štítná nad Vláří and spruce forest at Bílý Kříž). The retrieval algorithm was based on a machine learning method – support vector regression (SVR). Performance of the four spectral inputs used to train SVR was evaluated: a) all available hyperspectral bands, b) continuum removal (CR) 645 – 710 nm, c) CR 705 – 780 nm, and d) CR 680 – 800 nm. Spectral inputs and corresponding SVR models were first assessed at the level of spectral databases simulated by combined leaf-canopy radiative transfer models PROSPECT and DART. At this stage, SVR models using all spectral inputs provided good performance (RMSE for Cab < 10 μg cm<sup>−2</sup> and for LAI < 1.5), with consistently better performance for beech over spruce site. Since application of trained SVRs on airborne hyperspectral images of the spruce site produced unacceptably overestimated values, only the beech site results were analysed. The best performance for the Cab estimation was found for CR bands in range of 645 – 710 nm, whereas CR bands in range of 680 – 800 nm were the most suitable for LAI retrieval. The CR transformation reduced the across-track bidirectional reflectance effect present in airborne images due to large sensor field of view.

Highlights

  • Leaf chlorophyll content (Cab) and canopy leaf area index (LAI) are important plant functional traits that reflect on actual ecophyisiological and phenological status of vegetation and can be retrieved from remotely sensed reflectance (Darvishzadeh et al, 2008; le Maire et al, 2008; Sampson et al, 2003; Verrelst et al, 2012)

  • CR regions expanding into the red wavelengths (i.e. CR 645-710 and 680-780), where chlorophyll a and b molecules absorb most of the incident light, are more relevant for Cab retrieval than CR 705-800

  • In this study we tested the machine learning approaches, namely support vector regressions, for the quantitative estimation of forest biochemical and structural properties using various spectral inputs derived from hyperspectral data of two contrasting forest stands: broadleaf, European beech and coniferous, Norway spruce forest

Read more

Summary

Introduction

Leaf chlorophyll content (Cab) and canopy leaf area index (LAI) are important plant functional traits that reflect on actual ecophyisiological and phenological status of vegetation and can be retrieved from remotely sensed reflectance (Darvishzadeh et al, 2008; le Maire et al, 2008; Sampson et al, 2003; Verrelst et al, 2012). Simulated spectral databases that cover broad range of combinations of the key input parameters can help to develop and test new and more robust retrieval algorithms or to evaluate confounding effects of forest background and architecture on the estimated parameters (Malenovský et al, 2013). These retrieval algorithms can be based on minimization of a cost function (Rivera et al, 2013) or using advanced statistical methods of machine learning algorithms. We considered two types of spectral inputs for the SVR-based retrievals of Cab and LAI: all available hyperspectral bands and continuum-removed bands.

Objectives
Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.