Search

Early prediction of pest occurrences can enhance crop production, reduce input costs, and minimize environmental damage. Advances in machine learning algorithms facilitate the development of efficient pest alert systems. Furthermore, ensemble algorithms help in the utilization of several models rather than being dependent on a single model. This study introduces a dynamic ensemble model with absolute log error (ALE) and logistic error functions using four machine learning models—artificial neural networks (ANNs), support vector regression (SVR), k-nearest neighbors (kNN), and random forests (RF). Various abiotic factors such as minimum and maximum temperature, rainfall, and morning and evening relative humidity were incorporated into the model as exogenous variables. The proposed algorithms were compared with fixed-weighted and unweighted ensemble methods, and candidate machine learning models, using the pest population data for yellow stem borer (YSB) from two regions of India. Error metrics include the root mean square log error (RMSLE), root relative square error (RRSE), and median absolute error (MDAE), along with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) algorithm. This study concluded that the proposed dynamic ensemble algorithm demonstrated better predictive accuracy in forecasting YSB infestation in rice crops.

Climate change has a considerable influence on agricultural output, raising farmers’ production risk. Nevertheless, the risk can be mitigated by selecting stable genotypes. In countries such as India, where significant proportions of farmers are smallholders or operate on marginal land, the minimization of risk is of paramount importance. Existing methods of stability measures often result in low-yielding varieties. Consequently, there is a need to develop more effective stability strategy to solve this problem without reducing yield. In light of the preceding, the Rank Based Stability Index (RSI) has been proposed for choosing genotypes based on the rank of interaction residuals to mitigate the influence of climatic changes without compromising yield. Through statistical analyses, the RSI approach demonstrates its ability to discern stable genotypes resilient to environmental fluctuations. By evaluating genotype performance across multiple environments and seasons, RSI identifies cultivars with consistent yield performance, thus offering a valuable tool for enhancing crop resilience and ensuring food security. The effectiveness of the proposed RSI approach for selecting stable genotypes from groundnut (Arachis hypogaea L.) data has been notably demonstrated in comparison to other methods. RSI emerges as a promising methodology for genotype selection in groundnut, offering a robust framework for mitigating the influence of climatic changes on crop yields.

Denoising is an integral part of the data pre-processing pipeline that often works in conjunction with model development for enhancing the quality of data, improving model accuracy, preventing overfitting, and contributing to the overall robustness of predictive models. Algorithms based on a combination of wavelet with deep learning, machine learning, and stochastic model have been proposed. The denoised series are fitted with various benchmark models, including long short-term memory (LSTM), support vector regression (SVR), artificial neural network (ANN), and autoregressive integrated moving average (ARIMA) models. The effectiveness of a wavelet-based denoising approach was investigated on monthly wholesale price data for three major spices (turmeric, coriander, and cumin) for various markets in India. The predictive performance of these models is assessed using root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The wavelet LSTM model with Haar filter at level 6 emerged as a robust choice for accurate price predictions across all spices. It was found that the wavelet LSTM model had a significant gain in accuracy than the LSTM model by more than 30% across all accuracy metrics. The results clearly highlighted the efficacy of a wavelet-based denoising approach in enhancing the accuracy of price forecasting.

In this paper, stock price data has been predicted using several state-of-the-art methodologies such as stochastic models, machine learning techniqus, and deep learning algorithms. An efficient decomposition method resonating with these Machine Intelligence (MI) models has been embedded with boosting ensemble method. Finally a Model Confidence Set (MCS) based algorithm has been proposed for forecasting stock price data. Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) decomposed orthogonal subseries have been predicted using Random Forests (RFs). Then Kernel Ridge Regression (KRR) model is used to combine those predictions to form a hybrid predictor. In addition, improvement in prediction performance has been observed using kernel functions. Adaptive Boosting (AdaBoost) has been found stimulating prediction accuracy of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models. CEEMDAN has also increased the performance of AdaBoost. Nevertheless, combination of forecasts observed from various methodologies is a good approach for improving the result. Despite optimizing the weights for the combination of all the models, a heuristic MCS-based snuffing of the least important models prior averaging is conceded as a potent approach. MCS rescinds insignificant models based on the out-of-sample forecasting or in-sample prediction performance prior to equally average the superior models. The proposed methodologies have been compared to the existing standalone techniques using several validation measures. However, CEEMDAN with Support Vector Regression (CCEMDAN_SVR) model has been found to be the best predictor in the current scenario.

To investigate the interdependence between Indian onion markets in terms of price volatility, the present study was conducted in four different vital onion markets in India, viz. Mumbai, Nashik, Delhi and Bengaluru. The long term monthly data, from March, 2003 to September, 2015 was collected from the website of agmarknet.nic.in. We have employed the VEC-MGARCH model to estimate mean and volatility spillover simultaneously among the different markets and also examined the nature of dynamic correlation using the DCC model. The presence of mean and volatility spillover was found between the markets. This type of significant interaction between the volatility of different markets is highly useful for cross market hedging and for sharing of common information by market participants. The empirical results also suggest for a very close observation on different market behavioral pattern since, “news” in one market may impact other market through the number of interdependencies. Key words: Dynamic conditional correlations, Market behavior, Price volatility spillover

CRISPR-Cas9 system is one of the recent most used genome editing techniques. Despite having a high capacity to alter the precise target genes and genomic regions that the planned guide RNA (or sgRNA) complements, the off-target effect still exists. But there are already machine learning algorithms for people, animals, and a few plant species. In this paper, an effort has been made to create models based on three machine learning-based techniques [namely, artificial neural networks (ANN), support vector machines (SVM), and random forests (RF)] for the prediction of the CRISPR-Cas9 cleavage sites that will be cleaved by a particular sgRNA. The plant dataset was the sole source of inspiration for all of these machine learning-based algorithms. 70% of the on-target and off-target dataset of various plant species that was gathered was used to train the models. The remaining 30% of the data set was used to evaluate the model’s performance using a variety of evaluation metrics, including specificity, sensitivity, accuracy, precision, F1 score, F2 score, and AUC. Based on the aforementioned machine learning techniques, eleven models in all were developed. Comparative analysis of these produced models suggests that the model based on the random forest technique performs better. The accuracy of the Random Forest model is 96.27%, while the AUC value was found to be 99.21%. The SVM-Linear, SVM-Polynomial, SVM-Gaussian, and SVM-Sigmoid models were trained, making a total of six ANN-based models (ANN1-Logistic, ANN1-Tanh, ANN1-ReLU, ANN2-Logistic, ANN2-Tanh, and ANN-ReLU) and Support Vector Machine models (SVM-Linear, SVM-Polynomial, SVM-Gaussian However, the overall performance of Random Forest is better among all other ML techniques. ANN1-ReLU and SVM-Linear model performance were shown to be better among Artificial Neural Network and Support Vector Machine-based models, respectively.

Harnessing the potential yields of evergreen perennial crops like tea (Camellia sinensis L.) essentially requires the application of optimum doses of nutrients based on the soil test reports. In the present study, the soil pH, organic carbon (OC), available potassium as K2O (AK), and available sulphur (AS) of 7300 soil samples from 115 tea estates spread over the Dooars ranging from 88°52’E to 89°86’E longitude and 26°45’N to 27°00’N latitude of West Bengal, India have been documented. About 54% of soil samples were found within the optimum range of soil pH (4.50-5.50) for tea cultivation. The overall range of OC was found from 0.28% to 6.00% of which, 94% of the analyzed samples were within the range of satisfactory to excellent level of OC i.e. (>0.80% to 6.00%). Around 36.3% of soil samples were found to have high AK (>100 mg kg-1) but 37.1% of soils were found to have high AS content (>40 mg kg-1). The nutrient index status of soil pH was low in Dam Dim, Chulsa, Nagrakata, Binnaguri, and Jainti sub-districts. Soils from five sub-districts had a high nutrient index (2.47 to 2.83) for soil organic carbon. However, it existed in the medium index (1.69 and 2.22) for Dalgaon and Kalchini sub-districts. Only Nagrakata sub-district soil samples were in the high nutrient index (2.65) for AK. All analyzed samples showed a medium nutrient index (1.97 to 2.27) for AS. The result indicated that soil pH was significantly negatively correlated with soil OC (-0.336) and AK (-0.174). However, the soil OC was significantly positive correlated with AK (0.258) and AS (0.100). It could be concluded that a balanced fertilizer application would be needed as a part of the soil improvement program through soil chemical tests for sustainable tea cultivation.

In general, statistical models for estimation of heritability follow certain assumptions, i.e. random components including the error follow a normal distribution and are identically independently distributed. But in the practical situation, sometimes these assumptions are violated. Thus, from the perspective of plant and animal breeding programs, estimating various genetic variances and inferring their inheritance based on estimations of various genetic parameters is studied. In the present study, estimation of heritability for the half-sib model is considered with correlated error, and sire and error follow a range of different distributions like normal, Cauchy, beta, and t- distribution. Two error structures AR(1) and AR(2) was considered and observations for correlated and uncorrelated cases were generated using a one-way classification model. The developed procedure was applied using the generated observations using simulation. Various heritability ranges, such as high and low (0.5, 0.1), Half-sib AR(1), varied sample sizes (100 and 500), and various correlations of errors between AR(1) and AR, were used to obtain the data (2). ρ= -1 to +1. It was noticed that correlated errors a significant effect on heritability estimation and are highly affected by the distribution it follows.

The objective of present study was to investigate the efficiency of Autoregressive fractionally integrated moving average model with exogenous input (ARFIMAX) in forecasting price of Indian mustard [Brassica juncea (L.) Czern. & Coss]. The daily modal price and arrival data of mustard for two major markets of India, viz. Bharatpur and Agra were collected during 2008–2018 from AGMARKNET and used for the present investigation. It was observed that each of the price series under consideration is stationary but autocorrelation function of both the series decay in a hyperbolic pattern. This indicates possible presence of long memory in the price data. Moreover, the significant result of correlation between price and arrival indicate that arrival data could be used as exogenous variable to model and forecast the price for both markets. Accordingly, Autoregressive fractionally integrated moving average (ARFIMA) and ARFIMAX models were applied to obtain the forecasts. The forecast evaluation was carried out with the help of Relative mean absolute percentage error (RMAPE) and Root mean square error (RMSE). The residuals of the fitted models were used for diagnosis checking as well as to investigate the adequacy of developed model. To this end, a comparative study has also been made between the fitted ARFIMAX model and ARFIMA model for both in-sample and out-of-sample data to identify the best fitted model in order to forecast future prices. The model has demonstrated a good performance in terms of explained variability and predicting power.

Seasonal production, weather abnormalities, and high perishability introduce a high degree of volatility to potato prices. Price volatility is said to be asymmetric when positive and negative shocks of the same magnitude affect it in a dissimilar way. GARCH is a symmetric model, and it cannot capture asymmetric price volatility. EGARCH, APARCH, and GJR-GARCH models are popularly used to capture asymmetric price volatility. In this paper, an attempt is made to model the price volatility of the weekly wholesale modal price of potatoes for the Agra, Ahmedabad, Bengaluru, Delhi, Kolkata, and Mumbai markets using the above-mentioned models. The News Impact Curves (NICs) are derived from the fitted models, which confirmed the presence of asymmetry in the price volatility. To this end, NICs are used to describe the degree of asymmetry in volatility present in different markets.

Wavelet decomposition in signal processing has been widely used in the literature. The popularity of machine learning (ML) algorithms is increasing day by day in agriculture, from irrigation scheduling and yield prediction to price prediction. It is quite interesting to study wavelet-based stochastic and ML models to appropriately choose the most suitable wavelet filters to predict agricultural commodity prices. In the present study, some popular wavelet filters, such as Haar, Daubechies (D4), Coiflet (C6), best localized (BL14), and least asymmetric (LA8), were considered. Daily wholesale price data of onions from three major Indian markets, namely Bengaluru, Delhi, and Lasalgaon, were used to illustrate the potential of different wavelet filters. The performance of wavelet-based models was compared with that of benchmark models. It was observed that, in general, the wavelet-based combination models outperformed other models. Moreover, wavelet decomposition with the Haar filter followed by application of the random forest (RF) model gave better prediction accuracy than other combinations as well as other individual models.

Effect of tea pruning litter biochar (TPLBC) on arsenic (As), cadmium (Cd) and chromium (Cr) content in made tea and successive tea infusions were investigated in a greenhouse experiment with two tea cultivars (TV23 and S.3A/3). Made tea prepared from TV23 and S.3A/3 clone, a decrease in the concentration of As, Cd, and Cr by 36.73%, 16.22%, 13.96%, and 36.63%, 27.78%, 10.54%, respectively over control on the application of the highest dose of TPLBC (500 kg TPLBC ha−1). Irrespective of treatments, studied element concentrations were significantly higher (p ≤ 0.05) in the first infusion and lower in the third. Considering Ten g made tea consumption per person per day, the maximum average daily intakes of As, Cd and Cr in a higher dose of TPLBC were far below the tolerable weekly intake prescribed by the World Health Organization. As hazard quotient values of selected elements were ≪ 1, no significant adverse health consequences are expected for tea consumers.

  The Bayesian model was applied for analyzing the first lactation in Karan Fries cattle. First lactation data of production (305-day or less milk yield and daily milk yield) were collected from the history-cum pedigree sheet and daily milk yield registers of the division of Dairy Cattle Breeding (DCB), National Dairy Research Institute (NDRI), Karnal. In the Bayesian paradigm, MCMC methods are applied to solve complex mathematical problems to estimate a large number of unknown parameters. Assuming linear mixed model and using the different prior set up, diagnostic of MCMC (Markov Chain Monte Carlo) was carried out graphically as well as by Heidelberg stationarity test. Variance estimates of the random effects (VA) and residual variance estimation (VR) and Variance estimate location effects i.e. fixed effects were calculated along with effective sample size. Finally, heritability (h2) estimates for First lactation 305 days or less milk yield (FL305DMY) was estimated along with its credible interval.

BackgroundPrice 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.MethodsIn 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.ResultsAn 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.ConclusionsAmong 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 COVID-19 pandemic has impacted almost all the sectors including agriculture in the country. The present paper investigates the impact of COVID-19 induced lockdown on both wholesale and retail prices of major pulses in India. The daily wholesale and retail price data on five major pulses namely Lentil, Moong, Arhar, Urad and Gram are collected for five major markets in India namely Delhi, Mumbai, Kolkata, Chennai and Hyderabad during the period January, 2019 to September, 2020 from Ministry of Consumer Affairs, Food & Public Distribution, Government of India. The Government of India declared nationwide lockdown since March, 24, to May, 31, 2020 in different phases in order to restrict the spread of the infection due to COVID-19. To see the impact of lockdown on price and price volatility, time series model namely Autoregressive integrated moving average (ARIMA) model with error following Generalized autoregressive conditional heteroscedastic (GARCH) model incorporating exogenous variable as lockdown dummy in both mean as well variance equations. It is observed that in almost all the markets, lockdown has significant impact on price of the pulses whereas in few cases, it has significant impact on price volatility.

Plant disease has long been one of the major threats to world food security due to reduction in the crop yield and quality. Accurate and precise diagnosis of plant diseases has been a significant challenge. Cost-effective automated computational systems for disease diagnosis would facilitate advancements in agriculture. The objective of this paper is to explore computer vision based Artificial Intelligence method for automating the identification of yellow rust disease and improve the accuracy of plant disease identification. The dataset of 2000 images of wheat leaf were collected in the real life experimental conditions of ICAR-Indian Agricultural Research Institute, New Delhi in the crop season during January-April, 2019. Based on our experiment, we propose a deep learning-based approach to detect healthy leaves and yellow rust infected leaves in the wheat crop. The experiments are implemented in python with PyCharm IDE, utilizing the Keras deep learning library backend with TensorFlow. The proposed model achieves 97.3% testing accuracy and 98.42% as the training accuracy. The accuracy of the developed model can be improved further by training it with larger size of the dataset in future. In future, accuracy of computer vision based AI models can be improved by using the larger size training datasets. Also, these models can be used for providing automatic advisory services to the farmers, thereby, adding much needed assistance to the overloaded extension experts.

In recent years, deep learning techniques have become very popular in the field of image recognition and classification. Image-based diagnosis of diseases in crops using deep learning techniques has become trendy in the current scientific community. In this study, a deep convolutional neural network (CNN) model has been developed to identify the images of maydis leaf bight (MLB) (Cochliobolus heterostrophus) disease of maize (Zea mays L.) crop. A total of 1547 digital images of maize leaves (596 healthy and 951 infected with maydis leaf blight disease) have been collected from different agricultural farms using hand-held camera and smartphones. The images have been collected from the experimental plots of BCKV, West Bengal and ICAR-IARI, New Delhi during 2018-19. The architectural framework of popular state-of-the network 'GoogleNet' has been used to build the deep CNN model. The developed model has been successfully trained, validated and tested on the above-mentioned dataset. The trained model has achieved an overall accuracy of 99.14% on the separate test dataset.

The onion crop is widely seen as the poor man's vegetable, has the power to change electoral results (Anonymous 2019). In India Onion (Allium cepa) is cultivated in an area of 12.7 lakh ha and produces 215.64 lakh ton. In Uttar Pradesh it is cultivated in an area of 0.25 lakh ha producing 4.23 lakh ton. The study was done during 2020 at IARI, New Delhi. Development of appropriate price forecasting mechanism and dissemination among the farmers would help alleviate problems faced by the farmers and consumers alike. The average price of onion throughout the year, during the study period of 2015-2020, has been fluctuating between ₹ 900-2200/quintal. The ARIMA (0,1,2)(1,0,0) [52] and ARFIMA(3,0,0)-sGARCH (1,1) model were found to be best fit model. However, on the basis of MAPE, MSE, RMSE and Theil's U statistics it was observed that the ARMA-GARCH model outperformed the ARIMA model.

Agricultural time-series data concerning production, prices, export and import of several agricultural commodities is published by Indian government along with other private agricultural sectors every year. The analysis of these factors is necessary to formulate and apply several policies regarding food acquisition and its distribution, quality and quantity of import and export products, pricing structure, MSP of agricultural commodities etc. Box - Jenkins's Autoregressive integrated moving average (ARIMA) model is broadly utilized in the field of time-series. In the field of time-series analysis, it is assumed by most of the researchers that the data points of different time lags do not depend on each other, i.e. absence of long memory process. But in agriculture, market price data exhibits that the observation are dependent on distant past. This is the possible indication of long memory process or long range dependency in the mean model. Autoregressive fractionally integrated autoregressive moving average (ARFIMA) model is generally used to portray the characteristic features of the long memory time series models as well as for the forecasting purposes. In this study wavelet decomposition is used for increasing the forecasting accuracy of the ARFIMA model. Daily wholesale data of wheat of Rewari market of Haryana for the period of January, 2010 to November, 2017 is used for the demonstration of our approach.

Crop phenology monitoring is a necessary action for precision agriculture. Sentinel-1 and Sentinel-2 satellites provide us with the opportunity to monitor crop phenology at a high spatial resolution with high accuracy. The main objective of this study was to examine the potential of the Sentinel-1 and Sentinel-2 data and their combination for monitoring sugarcane phenological stages and evaluate the temporal behaviour of Sentinel-1 parameters and Sentinel-2 indices. Seven machine learning models, namely logistic regression, decision tree, random forest, artificial neural network, support vector machine, naïve Bayes, and fuzzy rule based systems, were implemented, and their predictive performance was compared. Accuracy, precision, specificity, sensitivity or recall, F score, area under curve of receiver operating characteristic and kappa value were used as performance metrics. The research was carried out in the Indo-Gangetic alluvial plains in the districts of Hisar and Jind, Haryana, India. The Sentinel-1 backscatters and parameters VV, alpha and anisotropy and, among Sentinel-2 indices, normalized difference vegetation index and weighted difference vegetation index were found to be the most important features for predicting sugarcane phenology. The accuracy of models ranged from 40 to 60%, 56 to 84% and 76 to 88% for Sentinel-1 data, Sentinel-2 data and combined data, respectively. Area under the ROC curve and kappa values also supported the supremacy of the combined use of Sentinel-1 and Sentinel-2 data. This study infers that combined Sentinel-1 and Sentinel-2 data are more efficient in predicting sugarcane phenology than Sentinel-1 and Sentinel-2 alone.

Modelling incidence of sterility mosaic disease (SMD) on pigeonpea [Cajanus cajan (L.) Millsp.] for four locations [S K Nagar (Gujarat), Gulbarga (Karnataka), Rahuri (Maharashtra) and Vamban (Tamil Nadu)] was carried out based on field data sets generated during six kharif seasons [2011-16]. Mean seasonal incidence amongst all locations was on the decline during recent periods (0.5-5.3%) over past decades (9.8-12.8%). Correlation analyses of SMD incidence with weather parameters lagged one and two weeks indicated spatial differences for the variables besides their significance. While Max T (ºC) lagged by one week alone was significantly positive with SMD at Gulbarga (KA), Vamban (TN) had negative significance of rainfall (mm/week) and rainy days. S K Nagar (GJ) and Rahuri (MH) had shown opposite effects of both morning and evening RH (%) of both one and two lagged weeks. Support vector regression (SVR), artificial neural network (ANN) models and their combination with autoregressive integrated moving average (ARIMA) models applied for prediction of SMD incidence across locations revealed performance of hybrid models in general to be better based on the evaluation criteria of root mean square error (RMSE). ARIMASVR> ARIMA-ANN>SVR>ANN was the order of prediction accuracies at S K Nagar (GJ), Gulbarga (KA), and Vamban (TN). At Rahuri (MH), individual models performed better over their hybrids with ARIMA. While application of hybrid model of SVR-ARIMA is applicable under situations of SMD seasonal mean severity exceeding 1%, SVR model proves better for mean seasonal disease incidence in decimal values less than one.

Influence of weather variables on occurrence of spiders in pigeon pea across locations of seven agro-climatic zones of India was studied in addition to development of forecast models with their comparisons on performance. Considering the non-normal and nonlinear nature of time series data of spiders, non-parametric techniques were applied with developed algorithm based on combinations of wavelet–regression and wavelet–artificial neural network (ANN) models. Haar wavelet filter decomposed each of the series to extract the actual signal from the noisy data. Prediction accuracy of developed models, viz., multiple regression, wavelet–regression, and wavelet–ANN, tested using root mean square error (RMSE) and mean absolute percentage error (MAPE), indicated better performance of wavelet–ANN model. Diebold Mariano (DM) test also confirmed that the prediction accuracy of wavelet–ANN model, and hence its use to forecast spiders in conjunction with the values of pest–defender ratios, would not only reduce insecticidal sprays, but also add ecological and economic value to the integrated pest management of insects of pigeon pea.

In the present paper, horizontal and vertical integration was carried out on the wholesale and retail prices of wheat in the major markets of India. On confirming cointegration between the wholesale and retail prices of wheat in all needs, the vector error correction model (VECM) was applied to find the speed of adjustment in the corresponding price channel. The results revealed that price signals are transmitted across regions, indicating that price changes in one market are consistently related to price changes in markets and can influence the prices in other markets. In addition to studying cointegration, threshold autoregressive (TAR) and Momentum TAR (MTAR) models were applied to test for asymmetric cointegration. Hasen and Seo’s test was used to test for the presence of threshold cointegration. It revealed a significant presence of asymmetric and nonlinear cointegration in many markets. Accordingly, a threshold VECM (TVECM) model with two regimes was applied. The results indicate that the retail price significantly responds to the deviations from the long-run equilibrium compared to the wholesale price.

Study of scenario and weather based prediction of severity of early blight (Alternaria solani Ell. & Mart) on tomato (Solanum lycopersicum L.) for five Indian states, viz. Rajendranagar (Telangana), Bengaluru (Karnataka), Rahuri (Maharashtra), Raipur (Chhattisgarh) and Ludhiana (Punjab) was made using advanced statistical method of support vector regression (SVR) with its accuracy compared with conventional multiple linear regression (MLR) model. Comparisons of early blight severity for mean and maximum severity levels across seasons for each location was carried out using Duncan’s Multiple Range Test (DMRT). Early blight mean and maximum severity levels were in order: Bengaluru (KA) > Rajendranagar (TS) > Rahuri (MH) > Raipur (CG) > Ludhiana (PB). Ludhiana (PB) had nil incidence during 2015 and not greater than 5% of either mean or maximum severity in any season. Both minimum temperature and morning relative humidity of one and two lagged weeks had negative and positive influence respectively, on mean and maximum severity of early blight at Rajendranagar (TS), Bengaluru (KA) and Rahuri (MH), which had higher blight severity over Raipur (CG) and Ludhiana (PB). MLR indicated 22–56% and 21–61% of variability with respect to mean and maximum severity of early blight due to weather factors that varied with locations. SVR predicted early blight severity nearer to actual values over MLR in terms of goodness of fit as well as Root Mean Square Error (RMSE).

Concept of the paper is firstly to remove the trend of crop yield and then to develop the forecasting models using detrended yield. Not much work is available or development of forecast models or modelling due to their non-linear behaviour. For that, in this paper, methodology developed for forecasting using nonlinear growth models, which will help in forecasting yield, pest and disease incidences etc with high accuracy. Crop yield forecast models for wheat crop have been developed (using non-linear growth models, linear models and weather indices approach with weekly weather data) for different districts of Uttar Pradesh (UP). Weather Indices (WI) were obtained using above two approaches. Weather indices based regression models were developed using weather indices as independent variables while character under study such as crop yield was used as dependent variable for wheat crop, i.e. two step non-linear forecast model. Technique of forecasting using non-linear approach and using weather indices will enrich the knowledge in developing customized models on forecasting for different types of crops and for different locations. The approach provided reliable yield forecast about two months before harvest.

Abundance, infestation and disease transmission by thrips studied on groundnut at Kadiri of Anantapur (Andhra Pradesh) over six kharif seasons of 2011-16 indicated significantly higher abundance of thrips in 2016 over 2011 to 2015 with infestations on par among 2013, 2014 and 2016 and higher over other seasons. Peanut bud necrosis disease (PBND) transmission by thrips was significantly lower in 2015 and 2016 and higher in 2014. Associations of abundance of thrips with infestation and PBND were significant. Significant influence of PBND by the thrips infestation of only the current week implied significance of concurrent population in disease transmission.Significant positive effect of minimum temperature on incidence of PBND and negative effect of rainfall on thrips infestation were noted.Predictions of thrips abundance, infestation and PBND through multiple linear regression (MLR) models revealed positive influence of minimum temperature lagged by a week. Distribution of rainfall over its amount associated with thrips infestation besides negative role of wind with PBND was noted. Prediction models of PBND incidence combining weather and thrips abundance (R2:0.39) and weather and infestation (R2:0.53) showed that the PBND incidence was dependent on relative humidity and prevalent wind over previous two weeks in addition to thrips abundance or infestation.

Hierarchical time-series comprises of several dataset maintaining certain hierarchical relationship among them. There are certain specialized strategies, viz. top-down, bottom-up, middle-out and optimal approaches which take care of predicting future values for such multi-level data. For forecasting of individual series at different levels of hierarchy, a method of aggregation or disaggregation is followed. In the present study, these methodologies are investigated thoroughly. Further, state-wise seasonal sorghum [Sorghum bicolor (L.) moench] production data of India is analyzed by employing the hierarchical forecasting approaches. A comparative study on performance of different methods is carried out from the viewpoint of multi-step-ahead forecasts on the basis of Mean absolute error (MAE) and Root mean square error (RMSE). The findings show that the middle-out technique outperforms other approaches and traditional method of forecasting as well. This fact has been confirmed statistically by using pair-wise t-test. Finally, using the middle-out approach, forecasts of sorghum production for 2015 till 2017 have been carried out at all hierarchical levels. For statistical analysis, R software package has been employed.

Onion prices exhibit very high instability/volatility in all the selected markets of Delhi. The present study aimed to forecast the prices of onion for three markets of Delhi, viz. Azadpur, Keshopur and Shahdara using different foresting techniques. The study was based on times series secondary data on monthly wholesale price of onion from April 2005 to February 2015. After ensuring the stationarity of series after seasonal adjustment and differencing, the best ARIMA model was chosen for individual series. The residuals were checked for the presence of autocorrelation, it was found that the residuals are correlated implying improper specification of the models. Also, the plots of prices in the selected markets also exhibited nonlinearity in the series, which necessitated the application of non-linear models to the data. Considering this, squared residuals were checked for the presence of conditional heteroscedasticity. The presence of conditional heteroscedasticity was found in all the three price series. A significant ARCH-LM test and high value of skewness and kurtosis coefficients justify the selection of EGARCH models as the best fit models in these markets. The out-of-sample forecast of onion price has been carried out by using the best fitted EGARCH/GARCH model and it is projected that the prices of onion will be between rupees 1800-1950 per quintal in Azadpur and Shahdara market; while the prices will remain between rupees 2178 to 2413 per quintal in Keshopur market during March to July, 2015.

In the present investigation, five different non-parametric stability measures are proposed based on the ranks of the genotypes to assess genotype-environment interaction, when the data does not satisfy the normality assumption. The behaviours of developed stability indices are studied by simulation technique under the assumption of normal as well as non-normal distributions such as log-normal, gamma, beta and t - distributions. These indices are compared empirically by using power of the test and type-I error. Results from the non-parametric analysis with the help of simulation study demonstrated that the proposed index A4 outperformed other indices in normal as well as nonnormal data scenarios.

This study was carried out to examine the instability and volatility in the export of livestock and marine products of India. It was found that marine export was a bit more stable and less volatile compared to livestock products export. Further, cointegration between the two was also tested. It was concluded that the two export data series were cointegrated. One of its benefits is that the long-run equilibrium relationship can be modelled by a straightforward regression involving the levels of the variables. Finally, the forecast were also obtained, which were quite reliable.

Amongst Asian countries India is one of the most vulnerable countries to climate change. During the past century, surface temperature in India has shown a significant increasing trend. In this paper, we have investigated behavior of mean monthly temperature during the period 1901–2001 over four agroclimatic zones of India and also tried to detect structural change in the temperature series. A structural break in the series has been observed at the national as well regional levels between 1970 and 1980. An analysis of trends before and after the structural break shows a significant increase in July temperature in the arid zone since 1972.

A sorption study was conducted on different soils collected from five agroecological zones of West Bengal, India, to understand the soil environmental behavior and fate of cadmium. For this purpose batch adsorption experiments were carried out at the native soil pH and at three different temperatures (25°C, 35°C, and 45°C). The adsorption data fitted by a linear least squares technique to the different sorption isotherms. Most data obtained give the good fit to both Freundlich and modified Langmuir isotherms, but they are not consistent with the linear Langmuir adsorption model. Thermodynamic parameters, namely, thermodynamics equilibrium constant at a particular temperature T (KT0), Gibbs free energy at a particular temperature T (ΔGT0), and change of enthalpy (ΔH0) and change of entropy at temperature T (ΔST0), were also determined by applying sorption value and concentrations of Cd in equilibrium solution within the temperature range. The thermodynamic parameters revealed that Cd sorption increases as the values of KT0, ΔGT0, ΔH0, and ΔST0 were increased on reaction temperatures. The spontaneous sorption reaction can be concluded due to high values of ΔGT0. The positive values of ΔH0 indicated that the Cd sorption is an endothermic one. Under these present conditions, the soil and its components possibly supply a number of sites having different adsorption energies for cadmium sorption.