Automatic Detection of Regions in Spinach Canopies Responding to Soil Moisture Deficit Using Combined Visible and Thermal Imagery

Shan-E-Ahmed Raza,Graham J J Clarkson,Andrew J Thompson,Gail Taylor,Hazel K Smith,John Clarkson,Nasir M Rajpoot,Roeland M H Merks

doi:10.1371/journal.pone.0097612

Shan-E-Ahmed Raza, Graham J J Clarkson + Show 6 more

Open Access

https://doi.org/10.1371/journal.pone.0097612

Copy DOI

Abstract

Thermal imaging has been used in the past for remote detection of regions of canopy showing symptoms of stress, including water deficit stress. Stress indices derived from thermal images have been used as an indicator of canopy water status, but these depend on the choice of reference surfaces and environmental conditions and can be confounded by variations in complex canopy structure. Therefore, in this work, instead of using stress indices, information from thermal and visible light imagery was combined along with machine learning techniques to identify regions of canopy showing a response to soil water deficit. Thermal and visible light images of a spinach canopy with different levels of soil moisture were captured. Statistical measurements from these images were extracted and used to classify between canopies growing in well-watered soil or under soil moisture deficit using Support Vector Machines (SVM) and Gaussian Processes Classifier (GPC) and a combination of both the classifiers. The classification results show a high correlation with soil moisture. We demonstrate that regions of a spinach crop responding to soil water deficit can be identified by using machine learning techniques with a high accuracy of 97%. This method could, in principle, be applied to any crop at a range of scales.

Highlights

Infrared thermometers have been used in the past by researchers to determine temperature differences in both individual plants and their canopies for irrigation scheduling purposes
Our results show that by combining information from thermal and visible light images and using machine learning techniques, canopies which are experiencing water deficits can be identified with high accuracy – more than 97%
The purpose of this study was to test a new dimension of automated classification methods for the detection of regions of a crop canopy that are responding to soil water deficit and to go beyond the restrictions of commonly used statistical approaches

Summary

Introduction

Infrared thermometers have been used in the past by researchers to determine temperature differences in both individual plants and their canopies for irrigation scheduling purposes. Under soil water deficits beyond a critical threshold, plants tend to close their stomata, and the rate of transpiration is reduced. This reduction in transpiration leads to an associated increase in leaf temperature. It widens the range of temperature variation within the canopy which can be detected using infrared thermometry or by the use of thermal imagers [4]. Leaf energy balance equation was rearranged to derive thermal indices based on ‘wet’ and ‘dry’ reference surfaces [10,11], using the ‘Crop Water Stress Index’ (CWSI) [5,6], making stomatal conductance more straightforward to calculate from leaf temperatures. There is a debate within the scientific community as to the ideal choice of reference surfaces and much work has been undertaken to find the best choice for reference surfaces and in what conditions they must be used [12]

Objectives

Methods

Results

Conclusion