Toward Maturity Assessment of SNAP Bean Crops: A Best-Case Greenhouse Scenario
Authors:
- 26 September 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5278-5281
Abstract
Precision agriculture applications, which include spatially-explicit irrigation scheduling, nutrient application, and disease management, could greatly benefit from accurate assessment of crop physiological stages. Such an identification strategy could contribute to improved timing of crop management interventions and improved yields. Snap bean as a crop, valued at over $400 million dollars annually in the USA, is an example crop that require accurate maturity stage classification, especially in context of disease management and harvest scheduling. This study aimed to assess growth classification of snap bean crop via machine learning approaches over four major maturity stages, namely vegetative growth, budding, flowering, and pod formation using hyperspectral data, in a greenhouse setting. Our classification results show high discrimination (mean-per-class accuracy = 0.69-0.82) in a one-vs-rest fashion with both parametric and non-parametric classifiers, such as logistic regression, naïve Bayes, random forest, and perceptron. These results show promise for potential extension to remote sensing solutions that would allow growers to better manage their crops.Keywords
This publication has 12 references indexed in Scilit:
- Advances in Non-Destructive Early Assessment of Fruit Ripeness towards Defining Optimal Time of Harvest and Yield Prediction—A ReviewPlants, 2018
- Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression ModelsRemote Sensing, 2017
- Extraction of Plant Physiological Status from Hyperspectral Signatures Using Machine Learning MethodsRemote Sensing, 2014
- The Estimated Amount, Value, and Calories of Postharvest Food Losses at the Retail and Consumer Levels in the United StatesSSRN Electronic Journal, 2014
- Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gapsBiosystems Engineering, 2013
- Crop Stage Classification of Hyperspectral Data Using Unsupervised TechniquesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- In situ Determination of Growing Stages and Harvest Time of Tomato ( Lycopersicon Esculentum ) Fruits Using Fiber-Optic Visible—Near-Infrared (Vis-NIR) SpectroscopyApplied Spectroscopy, 2011
- HIGH SPECTRAL RESOLUTION REMOTE SENSING OF FOREST CANOPY LIGNIN, NITROGEN, AND ECOSYSTEM PROCESSESEcological Applications, 1997
- Remote sensing of foliar chemistryRemote Sensing of Environment, 1989
- Smoothing and Differentiation of Data by Simplified Least Squares Procedures.Analytical Chemistry, 1964