Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
13 results
Search Results
Item Age-based classification of arecanut crops: a case study of Channagiri, Karnataka, India(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2016) Bhojaraja, B.E.; Shetty, A.; Nagaraj, M.K.; Manju, P.Arecanut is one of the predominant plantation crop grown in India. Yield of this crop depends upon age of the crop and there is no information on the spectral behaviour of arecanut crops across its ages. In this study popular supervised classification algorithms were utilized for age discrimination of arecanut crops using Hyperion imagery. Arecanut plantations selected for the study are located in Channagiri Taluk, Davanagere district of Karnataka state, India. Ground truth information collected involves: (i) GPS coordinates of selected plots, (ii) spectral reflectance of arecanut crops with age ranging from 1 to 50 years, using handheld spectroradiometer with 1 nm spectral resolution. These spectral measurements were made close in time to the acquisition of Hyperion imagery to build age-based spectral library. It is observed from the analysis that crops of ages below 3, 3–7, 8–15 and above 15 years were showing distinct spectral behaviour. Accordingly, crops age ranging from 1 to 50 were grouped into four classes. Classification of arecanut crops based on age groups was performed using methods like spectral angle mapper, support vector machine and minimum distance classifier, and were compared to find the most suitable method. Among the classification methods adopted, support vector machine with linear kernel function resulted in most accurate classification method with overall accuracy of 72% for within class seperability. Individual age group classification producer’s accuracy varied minimum of 12.5% for 3–7 years age group and maximum of 86.25% for above 15 years age group. It may be concluded that, not only age- based arecanut crop classification is possible, but also it is possible to develop age-based spectral library for plantation crop like arecanut. © 2015 Taylor & Francis.Item Development of cost-effective media for the in vitro liquid culture of entomopathogenic nematodes(Brill Academic Publishers, 2022) Dunn, M.D.; Belur, P.D.; Malan, A.P.Summary Entomopathogenic nematodes (EPN) are successful biological control agents of a variety of soilborne insect pests. They have the potential to be mass-produced, using in vitro liquid culture technology, and can be formulated and sold as a biopesticide. To commercialise an EPN-based biopesticide successfully, the method of liquid mass production requires in-depth optimisation to reduce the cost of production and to increase yields, to make it affordable to the farming community. This study attempted to optimise the liquid culture protocol for the South African isolates, Steinernema jeffreyense and S. yirgalemense, by investigating the impact of cheaper medium ingredients on the recovery and yield of the liquid culture process. Studies were conducted by investigating alternative protein, lipid and nitrogen/yeast sources, compared to the more expensive laboratory-grade ingredients currently used. The results showed that egg yolk has no impact on the yield in the case of S. jeffreyense. However, for S. yirgalemense, egg yolk was shown to be a superior protein source to soy and insect-based protein in terms of nematode yield. Moreover, neither canola oil nor olive oil showed a significant difference in the yield of S. yirgalemense, with yeast extract being found to be the optimal nitrogen/yeast source. When comparing the yields with those in other liquid culture research on S. yirgalemense, yields have been successfully increased by 300%, with the cost of the nematode nutrient medium having decreased by 77%. Thus, it is imperative that, prior to a scale up to large bioreactors, the nutrient medium should be optimised to reduce the cost of production. © 2022 Copyright 2022 by Koninklijke Brill NV, Leiden, The Netherlands.Item Multivariate analysis of concurrent droughts and their effects on Kharif crops—A copula-based approach(John Wiley and Sons Ltd, 2022) Muthuvel, D.; Mahesha, M.Apart from creating an ecological imbalance, drought events could affect an agrarian country's economy and food security by reducing crop yields. The antecedent meteorological droughts could prolong into hydrological and (or) agricultural droughts and may co-exist as concurrent droughts. The current study aims to comprehensively study Indian concurrent droughts, their effects on crop yield, and possible teleconnection with ENSO (El Niño–Southern Oscillation), adopting a copula-based multivariate approach. The copula functions can replicate the correlation among the variables and keep the dependence structure intact. The concurrent drought characteristics are computed using a multivariate standardized drought index that incorporates the three primary drought indices using the Gaussian copula. Some of the severe concurrent drought years such as 2002, 1987, 1972, and 1965 caused considerable yield losses in Kharif season crops of groundnut, millet, and rice. This prompts to construct quad-variate models involving the crop yield and the three drought indices using the vine copulas that perform better than the elliptical and symmetric Archimedean copula. Though the isolated forms of droughts could cause mild yield losses, the probability of concurrent droughts causing high to exceptional losses is more. Further, the ENSO teleconnection with the concurrent monsoon droughts is analysed and mapped. The above-normal warming of the Nino 3.4 region over the tropical Pacific during the months leading up to the monsoon could signal concurrent monsoon droughts in the areas under the Ganga-Brahmaputra basin at a probability of around 45%. These results could be helpful in drought mitigation measures and policymaking. © 2021 Royal Meteorological Society.Item Identifying Rice Crop Flooding Patterns Using Sentinel-1 SAR Data(Springer, 2022) Keerthana, N.; Salma, S.; Dodamani, B.M.In India, the majority of the population relies heavily on rice as it is their primary source of nutrition. Rice crop yield productivity depends on seasonal variations and mainly depends on hydrological conditions. Long-term water clogging in rice fields for an extended period causes crop flooding and reduces production in terms of quality and quantity. This study deals with the identification of rice crop fields and their flooding due to surface irrigation using Sentinel-1 SAR data. The identification of rice fields was attempted by classifying the image data using a random forest algorithm. For crop flooding analysis, the temporal backscatter of the corresponding fields has been extracted from SAR data and local thresholding is used. The temporal analysis of the SAR backscattering showed a similar tendency in terms of crop growth. The overall accuracy of rice crop classification for VH and VV is 97.30% and 92.24% with RMSE errors of 0.0143 and 0.0145, respectively, obtained at the peak stage of the crop. From the crop flooding analysis, it is observed that crop fields have been flooded at the growth stage due to surface irrigation and rainfall. We identified crop flooding even at the crop mature stage. In the analysis, it has been observed that the flooding is not due to irrigation water but is due to the precipitation water. © 2022, Indian Society of Remote Sensing.Item Future global concurrent droughts and their effects on maize yield(Elsevier B.V., 2023) Muthuvel, D.; Sivakumar, B.; Mahesha, A.Droughts are one of the most devastating natural disasters. Droughts can co-exist in different forms (e.g. meteorological, hydrological, and agricultural) as concurrent droughts. Such concurrent droughts can have far reaching implications for crop yield and global food security. The present study aims to assess global concurrent drought traits and their effects on maize yield under climate change. The standardized indices of precipitation, runoff, and soil moisture incorporated as multivariate standardized drought index (MSDI) using copula functions are used to quantify the concurrent droughts. The ensemble data of several General Circulation Models (GCMs) considering the high emission scenario of Coupled Model Intercomparison Project phase 6 (CMIP6) are utilized. Applying run theory on a time series (1950–2100) of MSDI values, the duration, severity, areal coverage, and average areal intensity of concurrent droughts are computed. The temporal evolution of drought duration and severity are compared among historical (1950–2014), near future (2021–2060), and far future (2061–2100) timeframes. The results indicate that the most vulnerable regions in the late 21st century are Central America, the Mediterranean, Southern Africa, and the Amazon basin. The indices and spatial extent of the individual droughts are used as predictor variables to predict the country-level crop index of the top seven producers of maize. The historical dynamics between maize yield and different drought forms are projected using XGBoost (Extreme Gradient Boosting) algorithms. The future temporal changes in drought-crop yield dynamics are tracked using probabilities of various drought forms under yield-loss conditions. The conditional concurrent drought probabilities are as high as 84 %, 64 %, and 37 % in France, Mexico, and Brazil, revealing that concurrent drought affects the maize yield tremendously in the far future. This approach of applying statistical and soft-computing techniques could aid in drought mitigation under changing climatic conditions. © 2022 Elsevier B.V.Item Prediction of crop yield using climate variables in the south-western province of India: a functional artificial neural network modeling (FLANN) approach(Springer Science and Business Media B.V., 2023) Jena, P.R.; Majhi, B.; Kalli, R.; Majhi, R.To meet the demand of the growing population, there exists pressure on food production. In this context, appropriate prediction of crop yield helps in agricultural production planning. Given the inability of the traditional linear models to provide satisfactory prediction performance, there is a need to develop a crop yield prediction model that is simple in complexity, accurate in prediction, and less time-consuming during training and validation phases. Keeping these objectives in view, the present paper focuses on building an adaptive, low complexity, and accurate nonlinear model for the prediction of crop yield. A time series dataset for the period 1991–2012 of Karnataka, a southwestern state of India, is used for yield prediction. An empirical nonlinear relation between crop yield and the four independent attributes has been obtained from the proposed ANN model. The independent attributes employed are total rainfall, the cumulative distribution of temperature, the proportion of irrigated land, and the average amount of fertilizer used. It is demonstrated that the developed model exhibits better prediction accuracy, less root mean square error in the range of 0.07–0.14, less mean square error in the range of 0.01–0.04, and mean absolute error in the range of 0.07–0.15 compared to its corresponding linear regression model. It is recommended that the proposed ANN model can also be applied to predict other agricultural products of the same or other geographical regions of the globe. © 2022, The Author(s), under exclusive licence to Springer Nature B.V.Item Temporal Assessment of Meteorological Drought Events Using Stationary and Nonstationary Drought Indices for Two Climate Regions in India(American Society of Civil Engineers (ASCE), 2023) Sajeev, A.; Kundapura, S.This study attempts to build nonstationary indices for assessing meteorological drought in two different climate zones in India: the arid Saurashtra and Kutch and humid-tropical Coastal Karnataka. Time and climate indices are considered as covariates to develop nonstationary models using the generalized additive model in location, scale, and shape (GAMLSS) for the period, 1951-2004. A comparative study has been conducted to assess the statistical performance of stationary and nonstationary models on various time scales (3, 6, 12, and 24 months). The best model is selected to conduct copula-based bivariate drought analysis. For this purpose, drought properties such as drought severity, duration, and peak are calculated. The annual and seasonal rainfall departures are also analyzed, and more rainfall-deficient years are detected in Saurashtra and Kutch regions than in Coastal Karnataka. The nonstationary index performed better in capturing drought properties in statistical analysis over both the study areas at all time scales. The nonstationary drought index shows better consistency with historical drought and flood events than the stationary index. Cooccurrence and joint return periods are calculated and compared with univariate return periods. A significant difference is observed between bivariate and univariate return periods, and more risk is detected in Saurashtra and Kutch than in Coastal Karnataka. The impacts of rainfall and drought on the yield of major crops in study areas are also analyzed. The yield loss rate of bajra significantly correlates with the nonstationary standardized precipitation index (NSPI) in Saurashtra and Kutch, whereas rice yield has no significant correlation with the index in Coastal Karnataka. This new aspect of drought analysis provides feasible results in both arid and humid regions in a changing environment. © 2023 American Society of Civil Engineers.Item Semi physical and machine learning approach for yield estimation of pearl millet crop using SAR and optical data products(Mapping Sciences Institute Australia, 2024) Kshetrimayum, A.; Goyal, A.; Ramesh, H.; Bhadra, B.K.Pearl millet (Pennisetum glaucum L.R.Br.), is the most widely cultivated food crop after rice, wheat, and maize. The aim of the project is to determine the crop acreage of Pearl millet (Bajra) using Sentinel-1A SAR data and Machine Learning Algorithm to determine the yield estimation of the Pearl millet crop at the tehsil level using the Monteith approach. The classification overall accuracy is found to be 86.48% for Agra district and 80.15% for Firozabad district. The Relative Deviation of yield estimation for the Agra and Firozabad districts is found to be 10.14 and 6, respectively. © 2023 Mapping Sciences Institute, Australia and Geospatial Council of Australia.Item DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification(Elsevier B.V., 2024) Dai, G.; Tian, Z.; Fan, J.; Sunil, C.K.; Dewi, C.Accurate identification of crop diseases is an effective way to promote the development of intelligent and modernized agricultural production, as well as to reduce the use of pesticides and improve crop yield and quality. Deep learning methods have achieved better performance in classifying input plant disease images. However, many plant disease datasets are often constructed from controlled scenarios, and these deep learning models may not perform well when tested in real-world agricultural environments, highlighting the challenges of transitioning to natural farm environments under the new demand paradigm of Agri 4.0. Based on the above reasons, this work proposes using a multi-level deep information feature fusion extraction network (DFN-PSAN) to achieve plant disease classification in natural field environments. DFN-PSAN adopts the YOLOv5 Backbone and Neck network as the base structure DFN and uses pyramidal squeezed attention (PSA) combined with multiple convolutional layers to design a novel classification network PSAN, which fuses and processes the multi-level depth information features output from DFN and highlights the critical regions of plant disease images with the help of pixel-level attention provided by PSA, thus realizing effective classification of multiple fine-grained plant diseases. The proposed DFN-PSAN was trained and tested on three plant disease datasets. The average accuracy and F1-score exceeded 95.27%. The PSA attention mechanism saved 26% of model parameters, achieving a competitive performance among existing related methods. In addition, this work effectively enhances the transparency of the features of the model attention to plant diseases through t-SNE with SHAP interpretable methods. © 2023 Elsevier B.V.Item Effect of irrigation on farm efficiency in tribal villages of Eastern India(Elsevier B.V., 2024) Kalli, R.; Jena, P.R.; Timilsina, R.R.; Rahut, D.B.; Sonobe, T.Irrigation is an important adaptation strategy to cope with climate change which reduces vulnerability to water stress and improves crop productivity to feed millions. There is evidence of crop yield stagnation in many developing countries, and irrigation efficiency is claimed to increase crop productivity. Therefore, this paper uses data envelopment analysis to evaluate the farmer's productivity through technical efficiency (TE), i.e., the relationship between resource inputs and outputs of 513 paddy farmers in Eastern India. The results show that the farms are, on average operating at 14% TE, leaving a considerable scope to improve up to 86% to reach the optimal level. A significant difference is observed between irrigated and rain-fed paddy farmers, such that10% of the irrigated farms achieved efficiency scores over 40% and only 2% of rain-fed farms achieved the same. The tobit and beta fit regression models are estimated to find out the factors that influence the TE. Both surface water and groundwater sources of irrigation are used as predictors, along with other socio-demographic factors. Access to surface water irrigation is identified to be a significant determinant of farm efficiency, however, surface water irrigation, such as canal irrigation, is accessible only to farmers living on plain land. Farmers living on highlands need to explore other sources of irrigation practices, such as drip and sprinkler, that can increase TE and farm productivity. Therefore, this paper calls for government intervention to provide extensive training and facilities for these micro-irrigation practices. © 2023 The Authors