AUTHOR=Mandal Nandita , Adak Sujan , Das Deb K. , Sahoo Rabi N. , Mukherjee Joydeep , Kumar Andy , Chinnusamy Viswanathan , Das Bappa , Mukhopadhyay Arkadeb , Rajashekara Hosahatti , Gakhar Shalini 

TITLE=Spectral characterization and severity assessment of rice blast disease using univariate and multivariate models

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1067189

DOI=10.3389/fpls.2023.1067189

ISSN=1664-462X

ABSTRACT=Rice is the staple food of more than half of the population of the world and India as well. One of the major constraints in rice production is frequent occurrence of pests and diseases which often causes yield loss varying from 10 to 30% is the rice blast disease. Conventional approaches for disease assessment are time-consuming, expensive, and not real-time; alternately, sensor-based approach is rapid, non-invasive and can be scaled up in large areas with minimum time and effort.  In the present study, hyperspectral remote sensing for the characterization and severity assessment of rice blast disease was exploited. Field experiments were conducted with 20 genotypes of rice having sensitive and resistant cultivars grown under upland and lowland conditions at Almora, Uttarakhand, India. The severity of the rice blast was graded from 0 to 9 in accordance to International Rice Research Institute (IRRI).  Spectral observations in field were taken using a hand-held portable spectroradiometer in range of 350-2500 nm. The spectral discrimination of different disease severity levels was done using Jeffires–Matusita (J-M) distance separating almost all severity levels having value >1.92 except level 4 and 5. Evaluation of 26 existing spectral indices (r≥0.8) was done corresponding to blast severity levels and prediction models were also developed. The models were effective at predicting blast severity with the R2 values from 0.48 to 0.85. Further, the proposed ratio blast index (RBI) and normalized difference blast index (NDBI) were developed using all possible combinations of their correlations with severity level followed by their quantification to identify the best indices. The best spectral indices for rice blast were RBI (R1148, R1301) and NDBI (R1148, R1301) with R2 of 0.85 and 0.86, respectively. By exhaustive literature, multivariate models like support vector machine regression (SVR), partial least squares regression (PLSR), random forest (RF), and multivariate adaptive regression spline (MARS) were used to estimate blast severity. Among these, SVR was the best model with calibration R2=0.99; validation R2=0.94, RMSE=0.698, and RPD=4.08. The methodology developed paves way for early detection and large-scale monitoring and mapping using satellite remote sensors at farmers’ fields for developing better disease management options.