Spectral-Based Classification of Plant Species Groups and Functional Plant Parts in Managed Permanent Grassland
Open Access
- 26 February 2022
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 14 (5) , 1154
Abstract
Grassland vegetation typically comprises the species groups grasses, herbs, and legumes. These species groups provide different functional traits and feed values. Therefore, knowledge of the botanical composition of grasslands can enable improved site-specific management and livestock feeding. A systematic approach was developed to analyze vegetation of managed permanent grassland using hyperspectral imaging in a laboratory setting. In the first step, hyperspectral images of typical grassland plants were recorded, annotated, and classified according to species group and plant parts, that is, flowers, leaves, and stems. In the second step, three different machine learning model types—multilayer perceptron (MLP), random forest (RF), and partial least squares discriminant analysis (PLS-DA)—were trained with pixel-wise spectral information to discriminate different species groups and plant parts in individual models. The influence of radiometric data calibration and specific data preprocessing steps on the overall model performance was also investigated. While the influence of proper radiometric calibration was negligible in our setting, specific preprocessing variants, including smoothening and derivation of the spectrum, were found to be beneficial for classification accuracy. Compared to extensively preprocessed data, raw spectral data yielded no statistically decreased performance in most cases. Overall, the MLP models outperformed the PLS-DA and RF models and reached cross-validation accuracies of 96.8% for species group and 88.6% for plant part classification. The obtained insights provide an essential basis for future data acquisition and data analysis of grassland vegetation.Keywords
Funding Information
- Österreichische Forschungsförderungsgesellschaft (854182)
This publication has 54 references indexed in Scilit:
- Mapping the spatial distribution of botanical composition and herbage mass in pastures using hyperspectral imagingGrassland Science, 2012
- Applying Neural Networks to Hyperspectral and Multispectral Field Data for Discrimination of Cruciferous Weeds in Winter CropsThe Scientific World Journal, 2012
- Inversion of a radiative transfer model for estimating vegetation LAI and chlorophyll in a heterogeneous grasslandRemote Sensing of Environment, 2008
- Development of Near Infrared Reflectance Spectroscopy Calibrations to Estimate Legume Content of Multispecies Legume–Grass MixturesAgronomy Journal, 2005
- Narrow band vegetation indices overcome the saturation problem in biomass estimationInternational Journal of Remote Sensing, 2004
- Evaluating an image analysis system for mapping white clover pasturesActa Agriculturae Scandinavica, Section B — Soil & Plant Science, 2004
- Monitoring grass swards using imaging spectroscopyGrass and Forage Science, 2003
- Avoiding false local minima by proper initialization of connectionsIEEE Transactions on Neural Networks, 1992
- Describing and Quantifying Growth Stages of Perennial Forage GrassesAgronomy Journal, 1991
- High resolution derivative spectra in remote sensingRemote Sensing of Environment, 1990