A Novel Machine Learning Approach to Estimate Grapevine Leaf Nitrogen Concentration Using Aerial Multispectral Imagery
Open Access
- 26 October 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (21), 3515
- https://doi.org/10.3390/rs12213515
Abstract
Assessment of the nitrogen status of grapevines with high spatial, temporal resolution offers benefits in fertilizer use efficiency, crop yield and quality, and vineyard uniformity. The primary objective of this study was to develop a robust predictive model for grapevine nitrogen estimation at bloom stage using high-resolution multispectral images captured by an unmanned aerial vehicle (UAV). Aerial imagery and leaf tissue sampling were conducted from 150 grapevines subjected to five rates of nitrogen applications. Subsequent to appropriate pre-processing steps, pixels representing the canopy were segmented from the background per each vine. First, we defined a binary classification problem using pixels of three vines with the minimum (low-N class) and two vines with the maximum (high-N class) nitrogen concentration. Following optimized hyperparameters configuration, we trained five machine learning classifiers, including support vector machine (SVM), random forest, XGBoost, quadratic discriminant analysis (QDA), and deep neural network (DNN) with fully-connected layers. Among the classifiers, SVM offered the highest F1-score (82.24%) on the test dataset at the cost of a very long training time compared to the other classifiers. Alternatively, QDA and XGBoost required the minimum training time with promising F1-score of 80.85% and 80.27%, respectively. Second, we transformed the classification into a regression problem by averaging the posterior probability of high-N class for all pixels within each of 150 vines. XGBoost exhibited a slightly larger coefficient of determination (R2 = 0.56) and lower root mean square error (RMSE) (0.23%) compared to other learning methods in the prediction of nitrogen concentration of all vines. The proposed approach provides values in (i) leveraging high-resolution imagery, (ii) investigating spatial distribution of nitrogen across a vine’s canopy, and (iii) defining spatial zones for nitrogen application and smart sampling.This publication has 44 references indexed in Scilit:
- Effect of light and nitrogen supply on internal C:N balance and control of root-to-shoot biomass allocation in grapevineEnvironmental and Experimental Botany, 2007
- A new technique for extracting the red edge position from hyperspectral data: The linear extrapolation methodRemote Sensing of Environment, 2006
- Nitrogen deficiency effects on plant growth, leaf photosynthesis, and hyperspectral reflectance properties of sorghumEuropean Journal of Agronomy, 2005
- Wide Dynamic Range Vegetation Index for Remote Quantification of Biophysical Characteristics of VegetationJournal of Plant Physiology, 2004
- Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regressionRemote Sensing of Environment, 2003
- Soil nitrogen utilisation for growth and gas exchange by grapevines in response to nitrogen supply and rootstockAustralian Journal of Grape and Wine Research, 2001
- Spectroscopic Determination of Leaf Biochemistry Using Band-Depth Analysis of Absorption Features and Stepwise Multiple Linear RegressionRemote Sensing of Environment, 1999
- Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leavesRemote Sensing of Environment, 1994
- The red edge position and shape as indicators of plant chlorophyll content, biomass and hydric status.International Journal of Remote Sensing, 1994
- Spectral Properties of PlantsApplied Optics, 1965