IoT based agriculture (Ag-IoT) is an emerging communication technology that is widely adopted by agricultural entrepreneurs and farmers to perform agricultural agro-chores in the farm to improve productivity, for better monitoring, and to reduce labor costs. However, the use of the Internet in Ag-IoT facilitates real-time functionality in an agriculture system, it can increase the risk of security breaches and cyber attacks that would cause the Ag-IoT system to malfunction and can affect its productivity. Ag-IoT is overlooked in cyber security parameters, which can have severe impacts on its trustworthiness and adoption by agricultural communities. To address this gap, this article presents a systematic study of the literature published between 2001 and 2023 that discusses advances in Ag-IoT technology. The subjects included in the study on Ag-IoT are emerging applications, different IoT architectures, suspected cyber attacks and cyber crimes, and challenges in incident response and digital forensics. The findings of this study encourage the reader to explore future potential research avenues related to the security risks and challenges of Ag-IoT, as well as the readiness for incident response and forensic investigation in the smart agricultural sector. The main conclusion of this study is that security must be ensured in Ag-IoT environments to offer uninterrupted services and also there is a need for forensic readiness for effective investigation in the event of unanticipated security incidents.

The purpose of the current study is to investigate the qualitative characterization of nine different pure vegetable oil samples using dielectric spectroscopy which is a vastly resourceful and reasoned technique in the temperature range 0 ℃ to 25 ℃. Time-domain reflectometry technique is applied up to the microwave frequencies of 50 GHz for the first time for qualitative characterization of the selected vegetable oil samples with a special focus on the variances of dielectric properties like dielectric permittivity (ε′), dielectric loss (ε″), relaxation time concerning temperature and other physiochemical properties of the vegetable oil specimens. The experimental methodology involves the use of time-domain reflectometry (TDR) measurements up to the scale of 50 GHz done to analyse the aspects like lower and higher scales of values towards the static dielectric permittivity (εs) and relaxation time (τ) (ps) to further meaningfully compare and correlate this values with the fatty acid profiles of each of the nine vegetable oil samples to reason and draw comparative inferences about the quality aspects of vegetable oils. Microwave TDR studies provide an effective, alternate, simple, rapid, and viable way to exercise quality control and actuate data regarding the quality status of vegetable oils. Variances of dielectric permittivity (ε′) concerning dielectric loss (ε″) are graphically interpreted using the Cole Davidson model. The static dielectric permittivity (εs) was further recertified and measured accurately by using a precision LCR meter. Thermodynamic properties of all the nine vegetable oil samples like enthalpy (ΔH) (kJ/mol) and entropy of activation (ΔS) (J/mol ∙ K) are also calculated to further insight the dependence of dielectric properties of these oil samples concerning temperature. This dielectric spectroscopic study affirms the association of the quality aspects of these nine vegetable oil samples with their dielectric properties by providing meaningful correlations, comparatives and concurrencies of dielectric properties concerning the physiochemical properties which are a part of fatty acid profiles of these samples, which is a novel aspect of this study. The Cole-Cole plot underlines the tendency of realignment of dipoles as per the applied field. The complex permittivity spectra indicate the dwindling nature of molecular alignment including a slow decline to average coinciding values depending on the molecular bonding pattern of vegetable oil samples. The activation energy (ΔH) in (kJ/mol) is calculated for all the samples which are indicative of endothermic nature which experimentally proves that high energy is required for rotation of unsaturated oil sample molecules with low relaxation times. The highlight of the current dielectric spectroscopic study is that it conclusively divides the nine vegetable oil samples into two groups based on the dielectric property of relaxation time. The vegetable oil samples with higher relaxation times were measured in ps [soyabean oil (398.5), groundnut oil (412.5), flaxseed oil (318.4), and castor oil (305.3)] and the oil samples with lower relaxation times [safflower oil (37.91), sunflower oil (30.6), walnut oil (22.4) and sesame oil (38.4)] and correlate this dielectric aspect with the aspect extent of the presence of oleic acid: C18H34O2, linoleic acid: C18H32O2, linolenic acid: C18H30O2 and ricinoleic acid C18H34O3 alongside the percentage of unsaturation present in the fatty acid profile of each sample. Saturated fatty profile of coconut oil (percentage of saturation 82.5) with low relaxation time (41.8) ps and its concurrency concerning the extent of percentage presence of lauric acid C12H24O2 (52 ps) myristic acid: C14H28O2 (21 ps) is also correlated. The current dielectric spectroscopic study further highlights and compares the variances of dielectric permittivity of the nine vegetable oils samples with the percentage of unsaturation /saturation to infer upon the correlation with the fatty acid profile of these oil samples.

Rice is an essential food crop that is cultivated in many countries. Rice leaf diseases can cause significant damage to crop cultivation, leading to reduced yields and economic losses. Traditional disease detection approaches are often time-consuming, labor-intensive, and require expertise. Automatic leaf disease detection approaches help farmers detect diseases without or with less human interference. Most of the earlier studies on rice leaf disease detection depended on image processing and machine learning techniques. Image processing techniques are used to extract features from diseased leaf images, such as the color, texture, vein patterns, and shape of lesions. Machine learning techniques are used to detect diseases based on the extracted features. In contrast, deep learning techniques learn complex patterns from large datasets without explicit feature extraction techniques and are well-suited for disease detection tasks. This systematic review explores various deep learning approaches used in the literature for rice leaf disease detection, such as Transfer Learning, Ensemble Learning, and Hybrid approaches. This review also discusses the effectiveness of these approaches in addressing various challenges. This review discusses the details of various models and hyperparameter settings used, model fine-tuning techniques followed, and performance evaluation metrics utilized in various studies. This review also discusses the limitations of existing studies and presents future directions for further developing more robust and efficient rice leaf disease detection techniques.

Evapotranspiration is an essential component of the hydrological cycle that is of particular interest for water resource planning. Its quantification is helpful in irrigation scheduling, water balance studies, water allocation, etc. Modelling of reference evapotranspiration (ET 0 ) using both gene expression programming (GEP) and artificial neural network (ANN) techniques was done using the daily meteorological data of the Pantnagar region, India, from 2010 to 2019. A total of 15 combinations of inputs were used in developing the ET 0 models. The model with the least number of inputs consisted of maximum and minimum air temperatures, whereas the model with the highest number of inputs consisted of maximum air temperature, minimum air temperature, mean relative humidity, number of sunshine hours, wind speed at 2 m height and extra-terrestrial radiation as inputs and with ET 0 as the output for all the models. All the GEP models were developed for a single functional set and pre-defined genetic operator values, while the best structure in each ANN model was found based on the performance during the testing phase. It was found that ANN models were superior to GEP models for the estimation purpose. It was evident from the reduction in RMSE values ranging from 2 % to 56 % during training and testing phases in all the ANN models compared with GEP models. The ANN models showed an increase of about 0.96 % to 9.72 % of R 2 value compared to the respective GEP models. The comparative study of these models with multiple linear regression (MLR) depicted that the ANN and GEP models were superior to MLR models.

In this study, an artificial neural network (ANN) is developed to predict the performance of a spark-ignition engine using waste pomegranate ethanol blends. A series of experiments on a single-cylinder, four-stroke spark-ignition engine yielded the data needed for neural network training and validation. 70 percent of the experimental data was used to train the network using the feed-forward back propagation (FFBP) algorithm. The developed network model's performance was evaluated by contrasting its output with experimental results. Input parameters included engine speed, ethanol blends, and output parameters included indicated and brake power, thermal, volumetric, and mechanical efficiencies. Training and testing data had regression coefficients that were almost identical to one. The research revealed that the ANN model can be a better option for predicting engine performance with a higher level of accuracy.

The world receives more than 200 thousand people in a day and it is expected that the total world population will reach 9.6 billion by the year 2050. This will result in extra food demand, which can only be met from enhanced crop yield. Therefore, modernization of the agricultural sector becomes the need of the hour. There are many constraints that are responsible for the low production of crops, which can be overcome by using drone technology in the agriculture sector. This paper presents an analysis of drone technologies and their modifications with time in the agriculture sector in the last decade. The application of drones in the area of crop monitoring, and pesticide spraying for Precision Agriculture (PA) has been covered. The work done related to drone structure, multiple sensor development, innovation in spot area spraying has been presented. Moreover, the use of Artificial Intelligent (AI) and deep learning for the remote monitoring of crops has been discussed.

• Imaging techniques used for plant phenotyping. • Machine vision methodologies used for plant trait estimation and classification. • Plant image segmentation techniques for plant growth tracking. • Publicly available dataset for plant phenotyping. • Future research directions in plant phenotyping. Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques. Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field. Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red, green and blue (RGB) imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, 3-dimensional (3-D) imaging or high resolution volumetric imaging. This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping. This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification. In this paper, information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods. This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural (2-D and 3-D), physiological and temporal trait estimation, and classification studies in plants.

• A perforated pooled circular stepped cascade (PPCSC) aerator was developed with maximum aeration efficiency using hybrid ANN-PSO technique. • A 3–6-1 ANN model coupled with particle swarm optimization (PSO) technique was used for optimizing the geometric and dynamic parameters of PPCSC aerator. • The optimized values of the consecutive step width ratio, the ratio of perforation diameter to the bottom-most radius, and the water flow rate were found to be 1.15, 0.0027 and 0.0167 m 3 /s, respectively. • The developed PPCSC aerator showed a 25.79% and 68.89% increase in the SAE as compared to the PCSC and CSC aerators, respectively. Artificial aeration system for aquaculture ponds becomes essential to meet the oxygen requirement posed by the aquatic species. The performance of an aerator is generally measured in terms of standard aeration efficiency (SAE), which is significantly affected by the different geometric and dynamic parameters of the aerator. Therefore, to enhance the aeration performance of an aerator, these parameters need to be optimized. In the present study, a perforated pooled circular stepped cascade (PPCSC) aerator was developed, and the geometric and dynamic parameters of the developed aerator were optimized using the hybrid ANN-PSO technique for maximizing its aeration efficiency. The geometric parameters include consecutive step width ratio ( W i-1 /W i ) and the perforation diameter to the bottom-most radius ratio ( d/R b ), whereas the dynamic parameter includes the water flow rate ( Q ). A 3–6-1 ANN model coupled with particle swarm optimization (PSO) approach was used to obtain the optimum values of geometric and dynamic parameters corresponding to the maximum SAE. The optimal values of the consecutive step width ratio ( W i-1 /W i ), the perforation diameter to the bottom-most radius ratio ( d/R b ), and the water flow rate ( Q ) for maximizing the SAE were found to be 1.15, 0.002 7 and 0.016 7 m 3 /s, respectively. The cross-validation results showed a deviation of 3.07 % between the predicted and experimental SAE values, thus confirming the adequacy of the proposed hybrid ANN-PSO technique.

• Color transformation based seed points initialization provides precise start for the leaf region extraction. • Energyand level-set based leaf region refinement offers an improvement in accuracy. • It offers high accuracy for the complex leaf region segmentation on multiple crops image datasets. • Combination of conventional algorithms with MLP performs outstandingly for crop disease image classification. Agricultural crop production is a major contributing element to any country’s economy. To maintain the economic growth of any country plants disease detection is a leading factor in agriculture. The contribution of the proposed algorithm is to optimize the extracted information from the available resources for the betterment of the result without any additional complexity. The proposed technique basically localizes the leaf region prior to the image classification into healthy and diseased. The novelty of this work is to fuse the information extracted from the available resources and optimize it to enhance the expected outcome. The leaf colors are analyzed using color transformation for the seed region identification. The mapping of a low-dimensional RGB color image into L*a*b color space provides an expansion of the spectral range. The neighboring pixels-based leaf region growing is applied on the initial seeds. In order to refine the leaf boundary and the disease-affected areas, we employed a random sample consensus (RANSAC) for suitable curve fitting. The feature sets using bag of visual words, Fisher vectors, and handcrafted features are extracted followed by classification using logistic regression, multilayer perceptron model, and support vector machine. The performance of the proposal is analyzed through PlantVillage datasets of apple, bell pepper, cherry, corn, grape, potato, and tomato. The simulation-based analysis of the proposed contextualization-based image categorization process outperforms as compared with the state of arts. The proposed approach provides average accuracy and area under the curve of 0.932 and 0.903, respectively.

Recently many methods have been induced for plant disease detection by the influence of Deep Neural Networks in Computer Vision. However, the dearth of transparency in these types of research makes their acquisition in the real-world scenario less approving. We propose an architecture named ResTS (Residual Teacher/Student) that can be used as visualization and a classification technique for diagnosis of the plant disease. ResTS is a tertiary adaptation of formerly suggested Teacher/Student architecture. ResTS is grounded on a Convolutional Neural Network (CNN) structure that comprises two classifiers (ResTeacher and ResStudent) and a decoder. This architecture trains both the classifiers in a reciprocal mode and the conveyed representation between ResTeacher and ResStudent is used as a proxy to envision the dominant areas in the image for categorization. The experiments have shown that the proposed structure ResTS (F1 score: 0.991) has surpassed the Teacher/Student architecture (F1 score: 0.972) and can yield finer visualizations of symptoms of the disease. Novel ResTS architecture incorporates the residual connections in all the constituents and it executes batch normalization after each convolution operation which is dissimilar to the formerly proposed Teacher/Student architecture for plant disease diagnosis. Residual connections in ResTS help in preserving the gradients and circumvent the problem of vanishing or exploding gradients. In addition, batch normalization after each convolution operation aids in swift convergence and increased reliability. All test results are attained on the PlantVillage dataset comprising 54 306 images of 14 crop species.

Tuna is superior among the marine fishes that are exported in the forms of raw fish and processed food. Separation of Tuna into their species is done in industries manually, and the process is tiresome. This work proposes an automated system for classifying Tuna species based on their images. An ensemble of region-based deep neural networks is used. A sub region contrast stretching operation is applied to enhance the images. Each fish image is then divided into three regions and is augmented before giving as input to pre-trained convolutional neural networks (CNN). After fine-tuning the models, the output from the last convolutional layer is given to a grouped 2D-local binary pattern descriptor (G2DLBP). Statistical features from the descriptor are applied to different classifiers, and the best classifier for each image region model is identified. Different ensemble methods are subsequently used to combine the three CNN-G2DLBP models. Among the ensemble techniques, super learner ensemble method with random forest (RF) classifier using 5-fold cross-validation shows the highest classification accuracy of 97.32%. The performance of different ensemble methods is analyzed in terms of accuracy, precision, recall, and f-score. The proposed system shows an accuracy of 93.91% when evaluated with an independent test dataset. An ensemble of region-based CNN with textural features from G2DLBP is applied for the first time for fish classification.

The fungal diseases in banana cause major yield losses for millions of farmers around the globe. Early detection of these diseases helps the farmers to devise successful management strategies. The characteristic leaf blade discoloration pattern at the earlier stages of infection could be used to understand the onset of each disease. This paper demonstrates a methodology for classification of three important foliar diseases in banana, using local texture features. The disease affected regions are identified using image enhancement and color segmentation. Segmented images are converted to transform domain using three image transforms (DWT, DTCWT and Ranklet transform). Feature vector is extracted from transform domain images using LBP and its variants (ELBP, MeanELBP and MedianELBP). These texture based features are applied to five popular image classifiers and comparative performance analysis is done using ten-fold cross validation procedure. Experimental results showed best classification performance for ELBP features extracted from DTCWT domain (accuracy 95.4%, precision 93.2%, sensitivity 93.0%, Fscore 93.0% and specificity 96.4%). Compared with traditional methods of feature extraction, this novel method of fusing DTCWT with ELBP features has attained high degree of accuracy in precisely detecting and classifying fungal diseases in banana at an early stage.

The agriculture sector has an immense potential to improve the requirement of food and supplies healthy and nutritious food. Crop insect detection is a challenging task for farmers as a significant portion of the crops are damaged, and the quality is degraded due to the pest attack. Traditional insect identification has the drawback of requiring well-trained taxonomists to identify insects based on morphological features accurately. Experiments were conducted for classification on nine and 24 insect classes of Wang and Xie dataset using the shape features and applying machine learning techniques such as artificial neural networks (ANN), support vector machine (SVM), k-nearest neighbors (KNN), naive bayes (NB) and convolutional neural network (CNN) model. This paper presents the insect pest detection algorithm that consists of foreground extraction and contour identification to detect the insects for Wang, Xie, Deng, and IP102 datasets in a highly complex background. The 9-fold cross-validation was applied to improve the performance of the classification models. The highest classification rate of 91.5% and 90% was achieved for nine and 24 class insects using the CNN model. The detection performance was accomplished with less computation time for Wang, Xie, Deng, and IP102 datasets using insect pest detection algorithm. The comparison results with the state-of-the-art classification algorithms exhibited considerable improvement in classification accuracy, computation time performance while apply more efficiently in field crops to recognize the insects. The results of classification accuracy are used to recognize the crop insects in the early stages and reduce the time to enhance the crop yield and crop quality in agriculture.

In agriculture, insect pests must be identified at the initial stage of infestation to avoid their spread in the field. Leaf folders (cnaphalocrocis medinalis) and yellow stemborers (scirpophaga incertulas) are destructive pests of paddy crops, which are causing severe yield loss. Manual identification of insect pests in the crop is time-consuming, tedious, and ineffective. This paper focuses on a light trap based four-layer deep neural network with search and rescue optimization (DNN-SAR) method to identify leaf folders and yellow stemborers. Light traps are designed to lure the insects in the paddy field and the images of trapped insects are analyzed using the proposed detection method. In the DNN-SAR, images are contrast-enhanced using deer hunting algorithm, impulse noise is removed with fast average group filter, and segmented using social ski-driver optimization. The search and rescue optimization algorithm is used for the selection of optimal weights in the deep neural network, which has improved the convergence rate, lowered the complexity of learning, and improved the accuracy of detection. The proposed method outperformed the existing methods and achieved 98.29% pest detection accuracy.

Optical remote sensing (RS) with robust algorithms is needed for accurate assessment of crop canopy features. Despite intensive studies on algorithms, their performance using RS needs to be improved. We evaluated five different algorithms (partial-least-squares regression (PLSR), support vector regression (SVR), random forest regression (RFR), locally-weighted-PLSR (PLSRLW) and PLSR with feature selection (PLSRFS)) for rapid assessment of leaf area index (LAI) and canopy water content (CWC) for rice canopies using canopy reflectance spectra over visible to short-wave infrared region. Two pooled datasets of LAI (600) and CWC (480) were collected from two replicated field experiments during 2014–15 and 2015–16 rice growing season. The performance of each algorithm was evaluated using coefficient of determination (R2). Results showed that PLSRLW performed more accurately than other algorithms with R2 values 0.77 and 0.66 for LAI and CWC, respectively. We also used a bootstrapping approach to generate a kernel density estimator of root mean squared error values for each model. The results suggested that the improvement in prediction accuracy of LAI and CWC can be achieved if a suitable algorithm is selected by assigning higher weights to calibration samples, which has similar canopy structure as the test sample. Subsetting of the canopy spectral data results large error values in test dataset, therefore the use of entire season canopy spectral data should be used for model calibration.

Medicinal plants are generally suggested for degraded land or areas having low rain-fall. Andrographis paniculata is an important medicinal plant known for its diterpene lactone i.e. andrographolide. We exposed 26 genotypes of A. paniculata to rain-fed condition during early-season rain-fed (ESRF) and mid-season rain-fed (MSRF) conditions and compared with the control to assess their suitability in semi-arid climate region of Gujarat, India. The study was performed during two consecutive years 2016–2017 in split plot design with rain-fed conditions as main-plot treatment and genotypes as sub-plot treatment in three replications. The gaseous exchange parameters taken at 85∼100 days after transplanting exhibited mean photosynthesis rate was 20.5 μmol CO2 m−2 s−1 ranging between 15.9 μmol CO2 m−2 s−1 and 24.0 μmol CO2 m−2 s−1. Exceeding 7% decrease in stomatal conductance was recorded compared to the control plants under imposed rain-fed condition. The mean value of transpiration rate was 4.8 mmol H2O m−2 s−1. The mean value of water use efficiency was 4.6. MSRF condition decreased leaf water potential from −0.517 to −1.189 Mpa. The dry herbage decreased by 29.2% due to MSRF condition as compared the control. The andrographolide yield per plant suffered significantly and under ESRF condition it reduced mainly due to reduction in andrographolide content. Reduced andrographolide yield per plant in MSRF condition was mainly due to reduction in herbage yield. Results revealed that ESRF and MSRF condition characterized by erratic rainfall pattern and dry spell is not beneficial for quality production in A. paniculata. Based on the least decrease in andrographolide, yield two genotypes viz., AP 6 and AP 12 identified to be suitable for ESRF condition and two genotypes viz., AP 19 and AP 6 suitable for MSRF condition. Overall, four genotypes, AP 35, AP 39, AP 61 and AP 24 were suitable as the promising genotypes having high andrographolide yield.

Papaya (Carica papaya) is a tropical fruit having commercial importance because of its high nutritive and medicinal value. The packaging of papaya fruit as per its maturity status is an essential task in the fruit industry. The manual grading of papaya fruit based on human visual perception is time-consuming and destructive. The objective of this paper is to suggest a novel non-destructive maturity status classification of papaya fruits. The paper suggested two approaches based on machine learning and transfer learning for classification of papaya maturity status. Also, a comparative analysis is carried out with different methods of machine learning and transfer learning. The experimentation is carried out with 300 papaya fruit sample images which includes 100 of each three maturity stages. The machine learning approach includes three sets of features and three classifiers with their different kernel functions. The features and classifiers used in machine learning approaches are local binary pattern (LBP), histogram of oriented gradients (HOG), Gray Level Co-occurrence Matrix (GLCM) and k-nearest neighbour (KNN), support vector machine (SVM), Naive Bayes respectively. The transfer learning approach includes seven pre-trained models such as ResNet101, ResNet50, ResNet18, VGG19, VGG16, GoogleNet and AlexNet. The weighted KNN with HOG feature outperforms other machine learning-based classification model with 100% of accuracy and 0.099 5 s training time. Again, among the transfer learning approach based classification model VGG19 performs better with 100% accuracy and 1 min 52 s training time with consideration of early stop training. The proposed classification method for maturity classification of papaya fruits, i.e. VGG19 based on transfer learning approach achieved 100% accuracy which is 6% more than the existing method.

The present study was aimed to model the hydration characteristics of green chickpea (GC) using mathematical modelling and examine predictive ability of artificial neural network (ANN) modelling. Hydration of GC was performed at different temperatures 25, 35, 45, 55 and 65 °C. Different mathematical models were tested for the hydration at different temperatures. In ANN modelling, the hydration time and hydration temperature were used as input variables and moisture ratio, moisture content and hydration ratio were taken as output variables. Peleg model best described the hydration behavior at 25 °C; while hydration at high-temperature was better described by Page model and Ibarz et al. model. The optimum temperature obtained for hydration was 35 °C. Effective mass diffusion coefficient (De) increased from 1.55 × 10-11-1.79 × 10-9 m2/s with the increase in the hydration temperature. The low activation energy (39.66 kJ/moL) shows the low-temperature sensitiveness of GC. Low temperature hydration (25 °C) required higher time (>200 min) to achieve the equilibrium moisture content (EMC), however high temperature hydration (35–65 °C) reduced the EMC time (150 min). ANN was used to predict the hydration behavior and K fold cross validation was performed to check the over fitting of ANN model. Results show that the LOGSIGMOID transfer function showed better performance when used at the hidden layer input node in conjunction to both PURELIN and TANSIGMOID. TANSIGMOID was found suitable for moisture ratio (MR) and hydration ratio (HR) prediction, as opposed to PURELIN for moisture content (MC) data. Satisfactory model prediction was obtained when the number of neurons in the hidden layer for MC, MR and HR was 12, 8 and 15, respectively. Mathematical and ANN modelling results are useful to improve/predict the MC, MR and HR during hydration process of GC at different temperature and other similar process.

The estimation of evapotranspiration (ETo) is one of the main tools for the control of crop growth and to make a rational use of water resources. To estimate this parameter accurately, it is necessary to have a daily measurement of four meteorological variables, these are: temperature, solar radiation, relative humidity and wind speed. It is not always possible to count on all the variables, that is why there are empirical methods that use a limited number of variables that make an approximate estimate of the ETo value. Each of these models are applicable to different regions with completely different climates. In this paper, a study has been carried out to define the model of ETo estimation that best adapts to the semi-arid region in South India. Two different datasets for the same period from different meteorological stations were used. In addition to the empirical methods for estimating ETo, computer models ANFIS (Adaptive Neuro-Fuzzy Inference System) were implemented. These models consist in the future estimation of a certain parameter by using current variables and a history of variables and past results. The results of this work show that ANFIS 11 model makes the best estimate with RMSD = 0.002 and r = 0.999. The RITCHIE method is the most suitable empirical model for this region, which reaches RMSD = 0.507 and r = 0.851. In addition, ranking of equations is elaborated for both datasets for daily estimates of ETo. Finally, comparison is made with the results for each case and thus confirm or reject the convenience of one model over the rest. To achieve this, a series of statistical indicators were used: Index of agreement (d), MAE (Mean absolute error), SEE (Standard error of estimate) and RMSD (Root mean square difference). Moreover, a sensitivity analysis was performed in order to compare and show the stability of the best models when an error is introduced within the input parameters. In this case, the empirical models demonstrate a better performance than the ANFIS models. This work demonstrates that the Ritchie method is a good estimator of the ETo value for a semi-arid region in southern India. In addition, the results of the ANFIS models are promising and could be used as estimation methods.

Pan evaporation is an important climatic variable for developing efficient water resource management strategies. In the past, many machine learning models are reported in the literature for pan evaporation modeling using the different combinationof available climatic variables. In order to develop a novel model with improved accuracy and reduced computational complexity, the functional link artificial neural network (FLANN) is chosen as an architecture to estimate daily pan evaporation in three agro-climatic zones (ACZs) of Chhattisgarh state in east-central India. Single neuron and single layer in its structure make it less complex as compared to other multilayer neural networks and neuro-fuzzy based hybrid models. Estimation results obtained with the FLANN model are compared with those obtained by multi-layer artificial neural networks (MLANN) and two empirical methods using the same raw data and corresponding features. Statistical indices like root mean square error (RMSE), mean absolute error (MAE) and efficiency factor (EF) is also computed to evaluate the model performance. It is demonstrated that pan evaporation estimates obtained with the proposed FLANN models provide an improved estimation of pan evaporation (RMSE = 0.85 to 1.27 m m d - 1 , MAE = 0.63 to 0.95 m m d - 1 and EF = 0.70 to 0.89) as compared to MLANN (RMSE = 0.94 to 1.58 m m d - 1 , MAE = 0.73 to 1.14 m m d - 1 and EF = 0.62 to 0.88) and empirical (RMSE = 1.19 to 2.19 m m d - 1 , MAE = 0.91 to 1.62 m m d - 1 and EF = 0.49 to 0.88) models in different ACZs.

Food security for the 7 billion people on earth requires minimizing crop damage by timely detection of diseases. Most deep learning models for automated detection of diseases in plants suffer from the fatal flaw that once tested on independent data, their performance drops significantly. This work investigates a potential solution to this problem by using segmented image data to train the convolutional neural network (CNN) models. As compared to the F-CNN model trained using full images, S-CNN model trained using segmented images more than doubles in performance to 98.6% accuracy when tested on independent data previously unseen by the models even with 10 disease classes. Not only this, by using tomato plant and target spot disease type as an example, we show that the confidence of self-classification for S-CNN model improves significantly over F-CNN model. This research work brings applicability of automated methods closer to non-experts for timely detection of diseases.

Rapid acquisition of information about nitrogen (N) uptake and grain yield is an essential step in making site-specific in-season fertilizer N management decisions. The objective of this study was to quantify and validate the relationships between N uptake and grain yield of wheat using in-season measurements with atLeaf chlorophyll meter and GreenSeeker optical sensor at Feekes 6 growth stage (jointing stage) of wheat. The relationships were developed using data generated from experiments with multi-rate fertilizer N treatments and conducted in two consecutive wheat seasons (2017/2018 and 2018/2019) at two locations in the western Nile Delta of Egypt. A power function based on atLeaf measurement at Feekes 6 stage of wheat could explain 55.3% and 53.3% variations in the N uptake at this stage and grain yield at maturity, respectively. Measurements with GreenSeeker were related with N uptake and yield of wheat through exponential function and could explain 68.5% and 60.6% of the variation in N uptake and grain yield, respectively. The developed models were validated on an independent data set from another field experiment on wheat. The normalized root mean square error for the relation between atLeaf measurements and N uptake and grain yield were fair, whereas the fits were good for measurements with GreenSeeker. This study reveals that atLeaf chlorophyll meter and GreenSeeker optical sensor can be successfully used for establishing site-specific N management strategies in wheat.

• Today Big Data is used in every business, hence data analytics tools and techniques are in demand. Thus Big data has no shortage of uses within farming. • Large Opportunities for Big Data analysis in agriculture towards smart Farming and Precision Farming. • With the help of Big Data, every farmer's goal around Profitability, Efficiency and Cost management are not only realistic but achievable. • Big Data Business Models will be a Key Issue and Challenge to be addressed in Future Research. Agriculture is the backbone of the Indian Economy. However, statistics show that the rural population and arable land per person is declining. This is an ominous development for a country with a population of more than one billion, with over sixty-six percent living in rural areas. This paper aims to review current studies and research in agriculture, employing the recent practice of Big Data analysis, to address various problems in this sector. To execute this review, this article outline a framework for Big Data analytics in agriculture and present ways in which they can be applied to solve problems in the present agricultural domain. Another goal of this review is to gain insight into state-of-the-art Big Data applications in agriculture and to use a structural approach to identify challenges to be addressed in this area. This review of Big Data applications in the agricultural sector has also revealed several collection and analytics tools that may have implications for the power relationships between farmers and large corporations.

On-time recognition and early control of the stresses in the paddy crops at the booting growth stage is the key to prevent qualitative and quantitative loss of agricultural yield. The conventional paddy crop stress identification and classification activities invariably rely on human experts to identify visual symptoms as a means of categorization. This process is admittedly subjective and error-prone, which in turn may lead to incorrect action in stress management decisions. The proposed work presented in this paper aims to develop an automated computer vision system for the recognition and classification of paddy crop stress types from the field images using the state-of-the-art color features. The work examines the impact of eleven stress types, two biotic and nine abiotic stresses, on five different paddy crop varieties during the booting growth stage using field images and analyzes the stress responses in terms of color variations using lower-order color moments and two visual color descriptors defined by the MPEG-7 standard, the Dominant Color Descriptor (DCD) and Color Layout Descriptor (CLD). The Sequential Forward Floating Selection (SFFS) algorithm has been employed to reduce the overlapping between the features. Three different classifiers, the Back Propagation Neural Network (BPNN), the Support Vector Machine (SVM), and the k-Nearest Neighbor (k-NN) have been deployed to distinguish among stress types. The average stress classification accuracies of 89.12%, 84.44% and 76.34% have been achieved using the BPNN, SVM, and k-NN classifiers, respectively. The proposed work finds application in the development of decision support systems and mobile apps for the automation of crop and resource management practices in the field of agricultural science.