1. Introduction
Crop disease infection is one of the main variables undermining the profitability and sustainability of farming operations, so monitoring plant health conditions on a timely basis is important for effective agricultural field management [
1]. For example, cotton as a significant crop is exceptionally susceptible to cotton root rot, a destructive soil-borne disease caused by the fungus
Phymatotrichopsis omnivora. This disease happens all over the southwestern and south-central US. Infected plants show early symptoms with the leaves turning yellow and orange and then changing to dark brown before the plants die with dry leaves attached to them [
2]. It is practically important to acquire timely cotton disease occurrence data over large areas so that preventive measures can be taken to improve cotton yield and quality [
3].
Remote sensing makes it conceivable to screen crop disease quickly on a large scale, which has the advantages of being timely, easy to use, extensive, nondestructive, and objective [
3]. Remote sensing has been utilized to recognize, screen and evaluate an assortment of diseases in various crops. Comprehensive reviews on the use of remote sensing for the detection of plant diseases are available [
4]. Among different types of remote sensing techniques, hyperspectral remote sensing is one of the most effective approaches to discern features that are difficult to detect in the spectrum, due to its high spectral resolution [
5]. Hyperspectral technology is broadly and effectively applied to monitor various types of stresses to crops [
6,
7].
Remote sensing has been effectively used to map disease occurrences in cotton fields [
8]. In previous studies, Iterative Self-Organizing Data Analysis (ISODATA) unsupervised classification applied to multispectral image data has been utilized to recognize root rot infested areas [
9]. With this strategy, the optimal number of spectral classes was determined based on the average transformed divergence for every classification map and the classes were then assigned to either root rot infested or non-infested zones [
10]. Although supervised techniques had similar performance for mapping cotton root rot, the two unsupervised strategies, ISODATA applied to multispectral imagery or to normalized difference vegetation index (NDVI) imagery, were recommended because they are easy to operate [
9].
The proper characterization and evaluation of disease dissemination and seriousness in near-real-time could give valuable information for decision-making with respect to the application of fungicide to the right location with the right amount at the right time in precision agriculture [
11]. Traditionally, the most common strategy for disease identification has been visual surveys by experienced producers who can recognize subtle changes in plant color or curl of plant leaves and scout the area of disease infestation in the field [
1,
12]. This type of ground investigation is time-consuming and labor-intensive, and it is also difficult to precisely estimate the infested areas and seriousness over a wide range [
13].
Based on remote sensing data, many forms of VIs have been used for crop disease detection, and empirical statistical models between VIs and disease severity levels can be established using discriminant analysis, linear regression analysis, support vector machine (SVM), and other statistical methods [
5,
14,
15]. However, most studies have used field leaf or canopy spectra for model building, but not much effort has been taken to monitor disease severity on landscape levels [
16]. Besides, empirical modeling still relies on manual field observation, and the accuracy may vary in different fields due to the influence of crop variety, sowing time, field conditions and so on, making it difficult to be applied in large-scale analysis [
17].
Vegetation indices (VIs) enable the evaluation and observation of changes in canopy biophysical properties, such as leaf area index (LAI), chlorophyll content, and photosynthetically active radiation (PAR) [
18]. It has been revealed that crop disease can severely influence the biophysical property values, which can explain why the severity level is significantly correlated to crop VI values [
19,
20]. However, there has not been any study that directly uses VIs to perform disease severity leveling without ground investigation. In addition, the value ranges of VIs and the crop growth conditions can vary greatly from field to field. Therefore, there is a high probability that the correlation between VI values and crop disease severity levels is not always significant, considering the above factors. Normalization, as a simple and effective data-processing method, has been utilized to eliminate the background differences for reflectance spectra [
21], and has also been a basic mode in the construction of VIs. However, it has not been applied to eliminate the interferences of field management and VI value ranges.
In this research, based on VI normalization, a novel model for automatic crop disease severity estimation was proposed (
Section 2). Airborne images of two fields with varying levels of cotton root rot and six typical VIs related to biomass, PAR, LAI, and chlorophyll contents were selected to conduct disease severity estimations using the newly proposed model (
Section 2 and
Section 3), and the validity of the results were evaluated from various perspectives (
Section 3 and
Section 4).
4. Discussion
Crop disease mapping based on image classification can estimate the infestation area but not the severity or the developing trend of the disease. The crop disease severity grading method proposed in this study can help fill this gap, as disease severity assessment has become increasingly important in agricultural disease and pest research. The existing research hierarchy for disease assessment is dependent on artificial ground surveys. Although satisfactory results could be obtained in selected fields, the site-specific models could not be easily extended to large scale applications. Therefore, a universal method for crop disease assessment, independent of ground survey, is highly demanded to fully make use of remote sensing in large area monitoring, which is also the aim of this research. With the help of this automatic method, ground surveys will not be necessary for many circumstances. When the user wants the accuracy to be further improved, the results of ground surveys can be incorporated to optimize the automatic disease severity grading model parameters. Another practical application of the methodology is to select the fields based on the VIs for limited scouting by trained individuals.
Spectral VIs, an effective dimension-reduction technique using only a limited number of bands strongly correlated to vegetation health, can be very useful in fulfilling the task of detecting the severity level of crop diseases. Due to the influence of planting time, management practice, and other variable crop growing conditions, different fields tend to have varying levels of VIs and there are normally no uniform thresholds for all fields. Therefore, unified threshold segmentation cannot be used for classification. The symptom expression in cotton plants due to disease infection is also a complex phenomenon impacted by factors such as cultivar type, prevailing weather and soil conditions. Therefore, it is indeed important to take the regional field conditions and management practices into consideration for various fields before crop disease grading. In addition, there are great variations in the ranges of VIs, which make it difficult to compare the values of different VIs directly. Normalization, a commonly used statistical method, has been proven to be capable of eliminating the influences of optical geometrics, terrain and other effects [
34]. In fact, one basic assumption in this study is that normalization can eliminate the effects of field conditions among different fields and the range variations of different VIs. The fundamental idea of this methodology is that spectral differences between healthy plants and those infected with diseases can be uncovered and amplified by normalizing the data into zero-mean and unit-variance vectors [
35]. Because the wavelengths are standardized before disease severity grading, the impacts of different ecological conditions, crop type, illumination, or sensor-specific effects can be reduced [
12,
36]. The histogram results proved that the basic assumption of this study was valid.
On the basis of the above assumption and research background, a novel crop disease grading method was proposed in this study, including the specific steps of crop classification, VI normalization, and disease grading. Two cotton fields infested with cotton root rot were selected as the experimental fields, and the grading results were evaluated from the spatial dimension, spectral dimension and statistical parameters. The performance of the six different VIs was generally consistent with each other, indicating that this disease grading method was applicable for most VIs. This is because cotton root rot can lead to the decline of chlorophyll and LAI, while VIs have been proved to be closely related to these physicochemical parameters [
37]. The VIs, such as the NDVI and GNDVI, are standardized indices that utilize typical features of vegetation spectra, that is, low reflectance in the red domain due to chlorophyllabsorption and high reflectance plateau in the NIR region attributed to scattering caused by inner leaf structure. More specifically, subtle differences among the VIs could be observed, and EVI had the ideal result with the best contrast. RedEdge indices have been proven to be good indicators for crop diseases [
32], but the grading results of RedEdge concentrated in the high-value area in this study, which was not very accurate. However, the results between the different fields were still comparable. The other VIs had similar but satisfactory results. It is noteworthy that some of the VI values used are already normalized values, so they cannot have a large standard deviation. In future research, more VIs, especially those without normalization in their calculation formulas, should be selected and evaluated by this method. In this study, only one set of airborne hyperspectral images taken from two experimental fields on one date was selected. In future studies, time series of remotely sensed datasets across large geographic regions will be collected to verify the effectiveness of this method.
In this study, the VI maps were calculated from the hyperspectral images to allow the calculation of spectral indices containing narrow bands and to prove the validity of the grading method through comparisons of continuous spectral curves for different grades. In fact, some studies have shown that broadband VIs can also achieve as good results as those from narrowband VIs [
37]. Additionally, VIs derived from hyperspectral data may have more difficulty in distinguishing crop diseases when atmospheric conditions are poor compared to those from multispectral data [
12]. As a result, there is a high possibility that the grading methodology proposed in this study could be applied to airborne or satellite multispectral images. In addition, the image data used in this study only covered the visible to NIR wavelengths, lacking shortwave infrared bands. Infection of disease or pest in crops can lead to water stress symptoms and increased reflectance in the shortwave infrared region [
38]. Therefore, VIs containing shortwave infrared bands can be considered in future research for better results.
Spatial resolution has a great impact on the accuracy of crop disease classification, which is an essential step for the automatic disease grading method proposed. The spatial resolution of the manned aircraft data used is at submeter or meter level, which has been proved to be effective for crop disease monitoring in practice. However, the high cost of acquiring manned aircraft datasets makes it difficult to be used in every country or region. In recent years, unmanned aircraft vehicle (UAV) remote sensing has become a research hotspot in the field of precision agriculture [
39,
40]. It can obtain high-resolution data at a centimeter level, but its high resolution also brings interference information, such as soil and weeds. Satellite remote sensing data can cover large areas at extremely low cost, but the spatial resolutions of commonly used satellite sensors are usually much coarser, which will lead to the problem of mixed pixels. The best spatial resolution for crop disease grading needs to be further studied and validated.
Crop classification based on remote sensing has been able to achieve very high accuracy, but symptom discrimination of different stresses from airborne or satellite imagery is still a great challenge and remains to be further studied. Various stress factors, for example, drought, pests and nutrient insufficiencies, also cause a decrease in chlorophyll content, which in turn causes a blue shift in the red edge and other spectral feature parameters [
41,
42,
43]. Since the remote sensing signal is not unique to a specific factor [
16], for the early recognition of crop disease using remote sensing, field scouts can help to confirm the cause for the spectral signal at that location. Alternatively, if the fields are known to be infested with a specific disease, such as cotton root rot in this study, then a map of severity levels can be created. In future research, this grading method will be evaluated for the analysis of other crops, diseases and insect pests. Thus, using the database of various reference datasets corresponding to different crops as well as stress factors makes it conceivable to precisely identify the crop species and stress severity in the crops.