Growth Stage Classification and Harvest Scheduling of Snap Bean Using Hyperspectral Sensing: A Greenhouse Study

Jan van Aardt,Amirhossein Hassanzadeh,Sean P. Murphy,Sarah J. Pethybridge

doi:10.3390/rs12223809

Jan van Aardt, Amirhossein Hassanzadeh + Show 2 more

Open Access

https://doi.org/10.3390/rs12223809

Copy DOI

Abstract

The agricultural industry suffers from a significant amount of food waste, some of which originates from an inability to apply site-specific management at the farm-level. Snap bean, a broad-acre crop that covers hundreds of thousands of acres across the USA, is not exempt from this need for informed, within-field, and spatially-explicit management approaches. This study aimed to assess the utility of machine learning algorithms for growth stage and pod maturity classification of snap bean (cv. Huntington), as well as detecting and discriminating spectral and biophysical features that lead to accurate classification results. Four major growth stages and six main sieve size pod maturity levels were evaluated for growth stage and pod maturity classification, respectively. A point-based in situ spectroradiometer in the visible-near-infrared and shortwave-infrared domains (VNIR-SWIR; 400–2500 nm) was used and the radiance values were converted to reflectance to normalize for any illumination change between samples. After preprocessing the raw data, we approached pod maturity assessment with multi-class classification and growth stage determination with binary and multi-class classification methods. Results from the growth stage assessment via the binary method exhibited accuracies ranging from 90–98%, with the best mathematical enhancement method being the continuum-removal approach. The growth stage multi-class classification method used raw reflectance data and identified a pair of wavelengths, 493 nm and 640 nm, in two basic transforms (ratio and normalized difference), yielding high accuracies (~79%). Pod maturity assessment detected narrow-band wavelengths in the VIS and SWIR region, separating between not ready-to-harvest and ready-to-harvest scenarios with classification measures at the ~78% level by using continuum-removed spectra. Our work is a best-case scenario, i.e., we consider it a stepping-stone to understanding snap bean harvest maturity assessment via hyperspectral sensing at a scalable level (i.e., airborne systems). Future work involves transferring the concepts to unmanned aerial system (UAS) field experiments and validating whether or not a simple multispectral camera, mounted on a UAS, could incorporate < 10 spectral bands to meet the need of both growth stage and pod maturity classification in snap bean production.

Highlights

Snap bean is one of the largest sources of broad-acre crop income in the United States, and is planted from California to New York [1]
Most spectral imaging systems are categorized as either of(tihmeamgiunlgtissppeeccttrraolsaconpdyh)ytpyepressp, ewctirtahl the former define types, with the former defined as broader,lantotenr-caosnctiognutoauinsibnagnndasrarnodwt,hceonlattitgeurous spectral cove as containing narrow, contiguous spectral coverage [6]
A reflectance index based on the 500 nm, 678 nm, and 700 nm bands, was identified as a quantitative measure that could explain both maturity measures. It is with studies such as these in mind, that we developed a detailed experimental setup to evaluate our ability to assess growth stages and optimal harvest scheduling, with snap bean as a proxy crop

Summary

Introduction

Snap bean is one of the largest sources of broad-acre crop income in the United States, and is planted from California to New York [1]. 2020, 12, x is our lack of understanding, developing, and adopt snap bean was disposed of unsold in 2017 [1]. One of the contriebxuatminpglefabcetionrgs ctoroopvgerroalwl “thfosotadgleoasss”sessment, e.g., whe is our lack of understanding, developing, and adopting site-sppeecsitfiiccidcersopanmdanfeargtielimzeernst., Pwrietchisoionne agriculture, or s example being crop growth stage assessment, e.g., when and whperroevtoidsecmheadnualgeetmheenhtairnvpesutt,sotrhaapt pcolyuld maximize outp pesticides and fertilizers. The electromagnetic energy incident on crops results in a uniqwuheiscpheicstrcaalllcehdaraascpteercitzraatliosing,nwahtuicrhe i(sor spectral respons called a spectral signature (or spectral response), associated with eictohveerrvteygpeeta, toior nthaes pghenyesrioallocgoivcearl tsytaptee, of a plant [25]. Its biocahletmeriecdalacnodmipnotsuitrinonimispaaltcetrsetdhaensdpeinctral response [26]

Objectives

Methods

Results

Discussion

Conclusion