Background: Price forecasting of perishable crop like vegetables has importance implications to the farmers, traders as well as consumers. Timely and accurate forecast of the price helps the farmers switch between the alternative nearby markets to sale their produce and getting good prices. The farmers can use the information to make choices around the timing of marketing. For forecasting price of agricultural commodities, several statistical models have been applied in past but those models have their own limitations in terms of assumptions.Methods: In recent times, Machine Learning (ML) techniques have been much successful in modeling time series data. Though, numerous empirical studies have shown that ML approaches outperform time series models in forecasting time series, but their application in forecasting vegetables prices in India is scared. In the present investigation, an attempt has been made to explore efficient ML algorithms e.g. Generalized Neural Network (GRNN), Support Vector Regression (SVR), Random Forest (RF) and Gradient Boosting Machine (GBM) for forecasting wholesale price of Brinjal in seventeen major markets of Odisha, India.Results: An empirical comparison of the predictive accuracies of different models with that of the usual stochastic model i.e. Autoregressive integrated moving average (ARIMA) model is carried out and it is observed that ML techniques particularly GRNN performs better in most of the cases. The superiority of the models is established by means of Model Confidence Set (MCS), and other accuracy measures such as Mean Error (ME), Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Prediction Error (MAPE). To this end, Diebold-Mariano test is performed to test for the significant differences in predictive accuracy of different models.Conclusions: Among the machine learning techniques, GRNN performs better in all the seventeen markets as compared to other techniques. RF performs at par with GRNN in four markets. The accuracies of other techniques such as SVR, GBM and ARIMA are not up to the mark.

The distribution pattern and fractionation of arsenic (As) in three soil profiles from tea (Camellia sinensis L.) gardens located in Karbi-Anglong (KA), Cachar (CA) and Karimganj (KG) districts in the state of Assam, India, were investigated depth-wise (0-10, 10-30, 30-60 and 60-100 cm). DTPA-extractable As was primarily restricted to surface horizons. Arsenic speciation study showed the presence of higher As(V) concentrations in the upper horizon and its gradual decrease with the increase in soil depths, following a decrease of Eh. As fractionation by sequential extraction in all the soil profiles showed that arsenic concentrations in the three most labile fractions (i.e., water-soluble, exchangeable and carbonate-bound fractions) were generally low. Most arsenic in soils was nominally associated with the organic and Fe-Mn oxide fractions, being extractable in oxidizing or reducing conditions. DTPA-extractable As (assumed to represent plant-available As) was found to be strongly correlated to the labile pool of As (i.e. the sum of the first three fractions). The statistical comparison of means (two-sample t-test) showed the presence of significant differences between the concentrations of As(III) and As(V) for different soil locations, depths and fractions. The risk assessment code (RAC) was found to be below the pollution level for all soils. The measurement of arsenic uptake by different parts of tea plants corroborated the hypothesis that roots act as a buffer and hold back contamination from the aerial parts.