Applicability of parametric and nonparametric regression models for retrieval of crop canopy parameters for winter rapeseed and wheat crops using Sentinel-2 multispectral data

Dessislava Ganeva; Eugenia Roumenina; Georgi Jelev; Marin Banov; Veneta Krasteva; Victor Kolchakov

doi:10.1117/12.2533651

27 June 2019 Applicability of parametric and nonparametric regression models for retrieval of crop canopy parameters for winter rapeseed and wheat crops using Sentinel-2 multispectral data

Dessislava Ganeva, Eugenia Roumenina, Georgi Jelev, Marin Banov, Veneta Krasteva, Victor Kolchakov

Author Affiliations +

Proceedings Volume 11174, Seventh International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2019); 111740J (2019) https://doi.org/10.1117/12.2533651
Event: Seventh International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2019), 2019, Paphos, Cyprus

Abstract

Parametric and nonparametric regression methods have been proven to successfully retrieve crop canopy parameters. However, once those models are calibrated for certain crops or geographical place their applicability to other crops and places is still unclear and it is an important consideration in an operational context. The tested models are parametric with two or three bands Vegetation Indices and different fitting functions and nonparametric linear and non-linear kernel based. The studied crop canopy parameters are aboveground fresh and dry biomass, vegetation fraction, mean plant height and nitrogen concentration in biomass. For calibration of the models, in-situ data from winter rapeseed and wheat crops with bare soil pixel added and remote sensing data from Sentinel-2 is used. In this study two different scenarios are considered in order to determine the applicability of both types of models for rapeseed and wheat crop parameters retrieval: 1) When applying models to the crop and period they are calibrated for: only the models for wheat before and after winter period give very good results for all studies parameters. Gaussian Processes Regression and its Variational Heteroscedastic variant with dimensionality reduction are the best performing for most of the parameters’ retrieval. Three bands Vegetation Index are the best parametric methods; 2) When applying the models to the crop and period they are not calibrated for: no model gives satisfactory results for any of the studied parameters.

Citation Download Citation

Dessislava Ganeva, Eugenia Roumenina, Georgi Jelev, Marin Banov, Veneta Krasteva, and Victor Kolchakov "Applicability of parametric and nonparametric regression models for retrieval of crop canopy parameters for winter rapeseed and wheat crops using Sentinel-2 multispectral data", Proc. SPIE 11174, Seventh International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2019), 111740J (27 June 2019); https://doi.org/10.1117/12.2533651

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available