Automatic Estimation of Crop Disease Severity Levels Based on Vegetation Index Normalization

Abstract

The timely monitoring of crop disease development is very important for precision agriculture applications. Remote sensing-based vegetation indices (VIs) can be good indicators of crop disease severity, but current methods are mainly dependent on manual ground survey results. Based on VI normalization, an automated crop disease severity grading method without the use of ground surveys was proposed in this study. This technique was applied to two cotton fields infested with different levels of cotton root rot in south Texas in the United States, where airborne hyperspectral imagery was collected. Six typical VIs were calculated from the hyperspectral imagery and their histograms indicated that VI normalization could eliminate the influences of variable field conditions and the VI value range variations, allowing a potentially broader scope of application. According to the analysis of the obtained results from the spectral dimension, spatial dimension and descriptive statistics, the disease grading results were in general agreement with previous ground survey results, proving the validity of the disease severity grading method. Although satisfactory results could be achieved from different types of VI, there is still room for further improvement through the exploration of more VIs. With the advantages of independence of ground surveys and potential universal applicability, the newly proposed crop disease grading method will be of great significance for crop disease monitoring over large geographical areas.

Functional Hyperspectral Imaging by High-Related Vegetation Indices to Track the Wide-Spectrum Trichoderma Biocontrol Activity Against Soil-Borne Diseases of Baby-Leaf Vegetables

“…They have been used for grading wheat powdery mildew disease severity trough satellite-acquired scenes (Gröll et al, 2007 ; Feng et al, 2016 ; Ma et al, 2018 ). Recently, SAVI has been applied for the field estimation of the severity of cotton root rot caused by the fungus Phymatotrichopsis omnivora (Zhao et al, 2020 ), while OSAVI has been used to sense Fusarium Head Blight on wheat by computing Sentinel-2 multispectral data (Liu L. et al, 2020 ). Similarly to our findings, OSAVI has been found highly correlated with Rhizoctonia crown and root rot severity on sugar beet assessed with a non-imaging remote sensing approach (Reynolds et al, 2012 ).…”

Effectiveness of Super-Resolution Technique on Vegetation Indices

“…The estimation of VI was aided by spatial, spectral, and temporal knowledge from images. [45] Hyperspectral imagery A system for grading the severity of crop diseases using vegetation indices rather than field surveys was suggested.…”

“…The distinctiveness of the proposed technique from the conventional techniques can be elucidated in two forms-(i) data used and (ii) methodology adopted. (i) Data used: It is seen that the works of literature [38][39][40][41][42][43][44][45][46][47] use multispectral, hyperspectral, radar, and optical images. The proposed technique uses pan-sharpened versions of the multispectral images, which are available in the portals [1][2][3][4] .…”

A review on South Asian wheat blast: The present status and future perspective

“…The handheld sensor has a small footprint (narrow field of view), but can upscale at satellite spatial resolution, as the reflectance intensity at different wavelengths (channels) of both the sensors resemble each other; thus the spectral data could provide valuable information on crop disease diagnosis and monitoring. The difference or ratio of reflected light at each spectrum (often called vegetation indices) is providing valuable information in detecting diseased canopies (Figure 3b) in a crop field (Zhao et al ., 2020). Remote sensing tools can be used for early disease monitoring and forecasting over a large area, providing a means whereby control measures could be taken to prevent the infestation of the wheat blast.…”