Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R² ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R² ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R² ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

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 and one of them is rice blast which often causes yield loss varying from 10 to 30%. 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 followed by spectral discrimination of different disease severity levels using Jeffires–Matusita (J-M) distance. Then, evaluation of 26 existing spectral indices (r≥0.8) was done corresponding to blast severity levels and linear regression prediction models were also developed. 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. Thereafter, multivariate models like support vector machine regression (SVM), partial least squares (PLS), random forest (RF), and multivariate adaptive regression spline (MARS) were also used to estimate blast severity. Jeffires–Matusita distance was separating almost all severity levels having values >1.92 except levels 4 and 5. The 26 prediction models were effective at predicting blast severity with R² values from 0.48 to 0.85. The best developed spectral indices for rice blast were RBI (R1148, R1301) and NDBI (R1148, R1301) with R² of 0.85 and 0.86, respectively. Among multivariate models, SVM was the best model with calibration R²=0.99; validation R²=0.94, RMSE=0.7, and RPD=4.10. 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.

The advent of high-spatial-resolution hyperspectral imagery from unmanned aerial vehicles (UAVs) made a breakthrough in the detailed retrieval of crop traits for precision crop-growth monitoring systems. Here, a hybrid approach of radiative transfer modelling combined with a machine learning (ML) algorithm is proposed for the retrieval of the leaf area index (LAI) and canopy chlorophyll content (CCC) of wheat cropland at the experimental farms of ICAR-Indian Agricultural Research Institute (IARI), New Delhi, India. A hyperspectral image captured from a UAV platform with spatial resolution of 4 cm and 269 spectral bands ranging from 400 to 1000 nm was processed for the retrieval of the LAI and CCC of wheat cropland. The radiative transfer model PROSAIL was used for simulating spectral data, and eight machine learning algorithms were evaluated for hybrid model development. The ML Gaussian process regression (GPR) algorithm was selected for the retrieval of crop traits due to its superior accuracy and lower associated uncertainty. Simulated spectra were sampled for training GPR models for LAI and CCC retrieval using dimensionality reduction and active learning techniques. LAI and CCC biophysical maps were generated from pre-processed hyperspectral data using trained GPR models and validated against in situ measurements, yielding R² values of 0.889 and 0.656, suggesting high retrieval accuracy. The normalised root mean square error (NRMSE) values reported for LAI and CCC retrieval are 8.579% and 14.842%, respectively. The study concludes with the development of optimized GPR models tailored for UAV-borne hyperspectral data for the near-real-time retrieval of wheat traits. This workflow can be upscaled to farmers’ fields, facilitating efficient crop monitoring and management.