Rating Iron Deficiency in Soybean Using Image Processing and Decision-Tree Based Models

C Igathinathane,Oveis Hassanijalilian,Sreekala Bajwa,John Nowatzki

doi:10.3390/rs12244143

C Igathinathane, Oveis Hassanijalilian + Show 2 more

Open Access

https://doi.org/10.3390/rs12244143

Copy DOI

Abstract

The most efficient way of soybean (Glycine max (L.) Merrill) iron deficiency chlorosis (IDC) management is to select a tolerant cultivar suitable for the specific growing condition. These cultivars are selected by field experts based on IDC visual ratings. However, this visual rating method is laborious, expensive, time-consuming, subjective, and impractical on larger scales. Therefore, a modern digital image-based method using tree-based machine learning classifier models for rating soybean IDC at plot-scale was developed. Data were collected from soybean IDC cultivar trial plots. Images were processed with MATLAB and corrected for light intensity by using a standard color board in the image. The three machine learning models used in this study were decision tree (DT), random forest (RF), and adaptive boosting (AdaBoost). Calculated indices from images, such as dark green color index (DGCI), canopy size, and pixel counts into DGCI ranges and IDC visual scoring were used as input and target variables to train these models. Metrics such as precision, recall, and f1-score were used to assess the performance of the classifier models. Among all three models, AdaBoost had the best performance (average f1-score = 0.75) followed by RF and DT the least. Therefore, a ready-to-use methodology of image processing with AdaBoost model for soybean IDC rating was recommended. The developed method can be easily adapted to smartphone applications or scaled-up using images from aerial platforms.

Highlights

The US is the second largest exporter of soybean and its product in the world with a crop value of over $39 billion in 2018 [1], and the Midwest is one of the biggest production regions
Based on average dark green color index (DGCI) values, most of the plots showed an increase in the average DGCI (Table 2), which is an indicator of improvement in their health status
Application of image processing in combination with machine learning was successful in rating iron deficiency chlorosis (IDC) as an alternative to visual rating by experts

Summary

Introduction

The US is the second largest exporter of soybean and its product in the world with a crop value of over $39 billion in 2018 [1], and the Midwest is one of the biggest production regions. Soybean production in general and in the Midwest can be declined by iron deficiency chlorosis (IDC). For efficient management of soybean IDC, measurement and assessment of the extent of the damage is the key step. The most common and current method employed IDC assessment is the manual visual scoring system by the field experts, where a higher score means increased incidence. This method, is laborious, expensive, and time-consuming, as well as subjective. A modern method of image processing from the actual field images was proposed, tested, and compared with manual rating in this study

Objectives

Methods

Results

Discussion

Conclusion