Spectroscopy-based chemometrics combined machine learning modeling predicts cashew foliar macro- and micronutrients.

Precision nutrient management in orchard crops needs precise, accurate, and real-time information on the plant's nutritional status. This is limited by the fact that it requires extensive leaf sampling and chemical analysis when it is to be done over more extensive areas like field- or landscape scale. Thus, rapid, reliable, and repeatable means of nutrient estimations are needed. In this context, lab-based remote sensing or spectroscopy has been explored in the current study to predict the foliar nutritional status of the cashew crop. Novel spectral indices (normalized difference and simple ratio), chemometric modeling, and partial least square regression (PLSR) combined machine learning modeling of the visible near-infrared hyperspectral data were employed to predict macro- and micronutrients content of the cashew leaves. The full dataset was divided into calibration (70 % of the full dataset) and validation (30 % of the full dataset) datasets. An independent validation dataset was used for the validation of the algorithms tested. The approach of spectral indices yielded very poor and unreliable predictions for all eleven nutrients. Among the chemometric models tested, the performance of the PLSR was the best, but still, the predictions were not acceptable. The PLSR combined machine learning modeling approach yielded acceptable to excellent predictions for all the nutrients except sulphur and copper. The best predictions were observed when PLSR was combined with Cubist for nitrogen, phosphorus, potassium, manganese, and zinc; support vector machine regression for calcium, magnesium, iron, copper, and boron; elastic net for sulphur. The current study showed hyperspectral remote sensing-based models could be employed for non-destructive and rapid estimation of cashew leaf macro- and micro-nutrients. The developed approach is suggested to employ within the operational workflows for site-specific and precision nutrient management of the cashew orchards.

Soil quality assessment of coastal salt-affected acid soils of India.

Soil salinity and acidity are some of the major causes of land degradation and have a negative impact on agricultural productivity. Assessing soil quality (SQ) of soils affected by soil salinity and acidity is required for their sustainable utilization for agricultural production. The aim of the present study was to evaluate the SQ of the salt-affected acid soils of the Indian West Coastal region using the additive and weighted soil quality indices (SQIs). The SQIs were developed using a total dataset (TDS) and a minimum dataset (MDS). The TDS comprised of 15 different soil properties as electrical conductivity (EC), pH, bulk density, soil available nitrogen (N), phosphorus (P), potassium (K), sulfur (S), boron (B), iron (Fe), manganese (Mn), copper (Cu), zinc (Zn) and exchangeable calcium (Ca), magnesium (Mg), and sodium (Na) measured on 300 soil samples (depth 0-0.15 m). Based on principal component analysis and correlation analysis, an MDS with soil properties like soil pH, EC, Na, Cu, Mn, and BD was formed. Using two approaches (additive and weighted), two datasets (TDS and MDS), and two scoring methods (linear and non-linear), eight SQIs were developed. The MDS-based linear weighted and non-linear weighted SQI found suitable to evaluate SQ of salt-affected acid soils and SQI had a significant and negative correlation of - 0.83 and - 0.70 (p < 0.01) with EC, respectively. Thus, it is clear that the SQ considerably reduces with an increase in soil salinity. The performance of the MDS-based SQIs was better than the TDS to discriminate different soil salinity classes. The agreement between the linear and non-linear scoring method of SQI had a linear relationship with a coefficient of determination (R2) of 0.91-0.96. Thus, assessing the SQ of salt-affected acid soils using MDS, linear scoring, and weighted approach of the soil quality indexing could save the time and cost involved.