Detection of nutrient deficiencies in banana plants using deep learning

The research focuses on the classification of nutrient deficiencies in rice plant leaves using a combination of Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) methods for feature selection. Image features are extracted using Histogram of Oriented Gradients (HOG), which is then optimized with PSO to select the most relevant features in the classification process. Indonesia is one of the largest rice producers in the world, with food security as a major issue that requires sustainable solutions, especially in the agricultural sector. The growth and yield of rice plants are highly dependent on the availability of nutrients such as Nitrogen (N), Phosphorus (P), and Potassium (K). However, traditional observation methods to detect nutrient deficiencies in plants become inefficient as the scale of production increases. The dataset used includes images of rice leaves showing nitrogen (N), phosphorus (P), and potassium (K) deficiencies. Experiments show that the SVM model optimized with PSO provides a classification accuracy of 83.19% and a runtime of 129.63 seconds with 1150 best feature combinations out of 2303 extracted features, which is higher accuracy and faster runtime than the model that does not use PSO. These results show that the integration of PSO in the feature selection process not only improves the accuracy of the model, but also reduces the required computation time. This research makes an important contribution to the development of an automated system for the classification of nutrient deficiencies in crops, which can be implemented in large farms or other agricultural fields.

Biochemical Differences in Maize as Related to Mineral Deficiencies. I. Changes in the Activity of some Enzymes. — The enzymatic systems in the different organs of corn seedlings are variously affected in the first growing stages by deficiency in nitrogen, phosphorus or potassium, according to the specific physiological functions of the organs. Deficiency in nitrogen causes an increase in peroxidase and catalase activity and inhibition of pyruvic and glutamic decarboxylase. Deficiency in phosphorus causes an activation of peroxidase and catalase in leaves and an inhibition of acid phosphatasc, invertase, pyruvic and glutatnic decarboxylase in roots. Deficiency in potassium, as compared to deficiency in nitrogen and phosphorus, leads to the severest disturbances of the different enzymatic systems. This deficiency causes a strong increase in leaf invertase, catalase and peroxidase activity, a stimulus in respiration intensity in the roots, and an inhibition in pyruvic and glutaniic decarboxylase in leaves and roots. The activation and inhibition changes in the enzymatic processes, appearing as a consequence of nitrogen, phosphorus and potassium deficiency have different significance and intensity.

India is an agricultural country, and farming is the most common occupation among Indians. Rice is a vital crop in the agricultural industry. Productivity has been declining for almost a decade. There are several causes for this, including fragmented land holdings, Indian farmer illiteracy, a lack of decision-making capacity in selecting excellent seeds, manure, and irrigational infrastructure. One of the major reasons for rice crop failure is due to malnutrition. Rice, maybe in particular, lacking in nutrients such as potassium, nitrogen, and phosphorus. Nutrient deficiency detection in crops is necessary to plan further actions to enhance yield. Most studies have relied on the use of transfer learning models for agricultural uses. Ensembling of different transfer learning techniques has the ability to greatly increase the predictive model’s performance. Five transfer learning architectures InceptionV3, Xception, VGG16, Resnet50, and MobileNet are all taken into account, and their different ensemble models are used to perform deficiency detection in rice plants. The mobile application was created as a user-friendly interface to assist farmers. The accurate diagnosis of these nutritional deficiencies and recommendation of fertilizer could aid farmers in providing correct plant intervention.

Background Digital image analysis combined with deep learning offers powerful tools for detecting plant nutrient deficiency (ND), a critical challenge in precision agriculture. Aims This study aims to develop an ensemble transfer learning approach for ND detection in black pepper (BP) and evaluate its effectiveness for classification and yield‐loss (YL) prediction. Methods An ensemble of MobileNetV2 and a custom‐made shallow convolutional neural network was implemented, with U2Net‐based background removal to improve feature extraction. The model was validated on the BP Dataset (DS)—BPNutriDef03 (4469 images)—and tested on a rice DS (4399 images). The framework included (1) ND classification using leaf imagery analysis and (2) YL forecasting based on nutrient deficiency severity (NDS). Results The ensemble achieved classification accuracies of 99.22% for BP and 95.14% for rice. The yield prediction based on the NDS model estimated the YL of 27.83% for BP and 33.42% for rice. Conclusions The proposed approach demonstrates robust performance and generalizability, offering a scalable, automated decision‐support system for ND monitoring and yield prediction in precision crop management.

Enhancement of porosity and aerenchyma formation in nitrogen-deficient rice roots

Due to the integration of artificial intelligence with sensors and devices utilized by Internet of Things technology, the interest in automation systems has increased. One of the common features of both agriculture and artificial intelligence is recommendation systems that increase yield by identifying nutrient deficiencies in plants, consuming resources correctly, reducing damage to the environment and preventing economic losses. The biggest shortcomings in these studies are the scarcity of data and the lack of diversity. This experiment aimed to identify nutrient deficiencies in basil plants cultivated in a hydroponic system. Basil plants were grown by applying a complete nutrient solution as control and non-added nitrogen (N), phosphorous (P) and potassium (K). Then, photos were taken to determine N, P and K deficiencies in basil and control plants. After a new dataset was created for the basil plant, pretrained convolutional neural network (CNN) models were used for the classification problem. DenseNet201, ResNet101V2, MobileNet and VGG16 pretrained models were used to classify N, P and K deficiencies; then, accuracy values were examined. Additionally, heat maps of images that were obtained using the Grad-CAM were analyzed in the study. The highest accuracy was achieved with the VGG16 model, and it was observed in the heat map that VGG16 focuses on the symptoms.

The earliest detection of plant disease is the primary concern of the farming community. The availability of advanced digital cameras and smartphones with improved image acquisition modes and deep learning methods like convolutional neural networks (CNN) can detect plant disease with high accuracy. This study used 2259 smartphone images of various rice (Oryza sativa) plant parts under various classes and 250 real-time validation images for classifying 12 rice diseases and nutrient deficiency symptoms. Different image segmentation techniques like foreground extraction were used to segment affected portions. Additionally, optimization of models and procedures to use them in smartphones with offline working capabilities have been described. Furthermore, a dynamic framework has been developed and demonstrated where the server trains on unseen image data to improve the classification performance and updates the model on falling below a certain threshold level. A comparison was made across different models used for image classification with many supporting metrics to select the best model for transfer learning. The top four performing models were DenseNet201, Xception, MobileNetV2, and ResNet50, with validation accuracies of 0.9803, 0.9778, 0.9756, and 0.9718, respectively. The ResNet50 model was found to best among all for cloud architectures, while MobileNetV2 appeared as the best model for the smartphone application. Finally, the android application, “Rice Disease Detector” compiled with the MobileNetV2 model was tested for multiple disease occurrences in a single capture. More research is warranted to test the application for smartphones with variable configurations.

Abstract—Nutrient deficiencies in rice plants, especially nitrogen (N), phosphorus (P), and potassium (K), can cause significant effects on rice yield and quality. Conventional methods for diagnosing nutrient deficiencies in rice leaves, including visual observation and soil analysis, are time-consuming and often unreliable. This research aims to develop an online rice leaf nutrient deficiency diagnosis system using machine learning and image processing techniques. The proposed system uses a DenseNet121 convolutional neural network (CNN) model that is fine-tuned on rice leaf images to achieve high accuracy in diagnosing nutrient deficiencies. The system is built using Flask as the backend framework, SQLite as the database management system, and role-based access control for users (farmers, agronomists, and administrators). The proposed system has been shown to achieve an average accuracy of 94-98% across datasets, providing a scalable and user-friendly solution for precision agriculture

The visual symptoms of several mineral deficiencies on the Dwalganup strain of subterranean clover are outlined. Phosphorus, nitrogen, and molybdenum deficiencies particularly reduce the rate of leaf production and leaf size. They may be distinguished by leaf colour-dark green in phosphorus deficiency and greenish yellow to pale yellow in nitrogen and molybdenum deficiency. Sulphur deficiency reduces the rate of leaf production after the onset of symptoms. Leaf size was not greatly affected by the degree of sulphur deficiency studied. The older leaves were uniformly lemon yellow in colour. Both potassium and zinc deficiency result in very pronounced reduction in leaf size. Potassium deficiency, in addition, shows marginal necrosis of older leaves, while with zinc deficiency leaf shape is profoundly affected. Copper deficiency particularly reduces seed production. The leaves are lighter green in colour than normal. With calcium (and manganese) deficiency, no prominent symptoms were recorded on the soils used. The advantages and limitations of diagnosis by visual symptoms are discussed.

The ionome is defined as the mineral element composition of an organism or tissue and is genetically and environmentally influenced. Although nutrient deficiency changes the plant ionome, the differences among different species have not been elucidated fully. In the present study, we examined the ionomic responses to nutrient deficiency in wheat (Triticum aestivum L.), maize (Zea mays L.), sunflower (Helianthus annuus L.), and soybean (Glycine max (L.) Merr.) to understand the differences in response to nutrient deficiency among different plant species. The plants were cultivated in fields with four fertilizer treatments: complete fertilization, without nitrogen, without phosphorus, and without potassium. Each plant species was sampled just before the flowering stage, and mineral concentrations of each organ were analyzed. The species-specific and nonspecific changes in accumulation by the treatment were observed in different elements. Under phosphorus deficiency, sunflower showed a different variation in the ionome profile than the other species, particularly in the increased accumulation of many metal elements. Increased accumulation of many elements was observed in all plant species under potassium deficiency. Under nitrogen deficiency, leaf molybdenum accumulation was increased in non-leguminous plants. An unknown role of molybdenum in the metabolic responses to the nitrogen deficiency was predicted. To carry out further research based on the results of such ionomics studies may reveal the unknown function of essential elements in metabolic responses in plants.

The changes in the amounts of ribulose-1,5-bisphosphate carboxylase/ oxygenase (Rubisco) and chlorophyll were compared under nitrogen, phosphorus, or potassium deficiency and standard treatments in field crops (spring wheat, maize, soybean, and potato). The experiments were conducted in the field where the following treatments had been applied since 1914; 1) application of nitrogen, phosphorus, and potassium, 2) absence of application of nitrogen (—N), phosphorus (—P), and potassium (—K). Under the —N treatment, although the decrease in the amount of Rubisco was remarkable, the activity of Rubisco (crop growth rate/Rubisco) did not decrease significantly in all the crops. Under the —P treatment, though the amount of Rubisco decreased in soybean and potato, the activity of Rubisco decreased in spring wheat and maize. Under the —K treatment, the amount of Rubisco decreased in all the crops, and the activity of Rubisco decreased in spring wheat and potato. As the proportion of Rubisco-N to the total nitrogen level in the leaves at the vegetative growth stage was affected by the treatment in some cases, but was stable at the maximum shoot growth (MSG) stage regardless of nitrogen, phosphorus, or potassium deficiency, it is therefore assumed that some mechanisms of stabilization of the proportion of Rubisco-N to total nitrogen may operate in the leaves against mineral deficiency. The ratio of Rubisco-N to the chlorophyll content decreased after the MSG stage. This ratio was higher in the —N, —P, and —K treatments than in the control at the MSG stage.

Deficiency of necessary macronutrients, i.e., Potassium (K), Magnesium (Mg), Nitrogen (N), Phosphorus (P), and Sulfate (S) in the soil leads to a reduction in plant growth and yield, which is a result of changes in expression level of various genes. This study was performed to identify the differentially expressed genes and its associated metabolic pathways occurred in soil grown wheat root samples excavated from the control and treated fields. To identify the difference in gene expression levels due to deficiency of the said nutrients, a transcriptomic, meta-analysis was performed on array expression profile data. A set of 435 statistically significant probes encoding 398 Nutrient Deficiency Response Genes (NRGs) responding at-least one nutrients deficiency (ND) were identified. Out of them 55 NRGs were found to response to minimum two ND. Singular Enrichment Analysis (SEA) predicts ontological based classifications and functional analysis of NRGs in different cellular/molecular pathways involved in root development and growth. Functional annotation and reaction mechanism of differentially expressed genes, proteins/enzymes in the different metabolic pathway through MapMan analysis were explored. Further the meta-analysis was performed to revels the active involvement each NRGs in distinct tissues and their comparative potential expression analysis in different stress conditions. The study results in exploring the role of major acting candidate genes such as Non-specific serine/threonine protein kinase, Xyloglucan endotransglucosylase/hydrolase, Peroxides, Glycerophosphoryl diester phosphodiesterase, S-adenosylmethionine decarboxylase proenzyme, Dehydrin family proteins, Transcription factors, Membrane Proteins, Metal binding proteins, Photosystem proteins, Transporter and Transferase associated in different metabolic pathways. Finally, the differences of transcriptional responses in the soil-grown root of T. aestivum cv. and in-vitro grown model plants under nutrients deficiency were summarized.

Background: Legumes play an important role in improving soil quality and nutrition in humans. Soybean is one of the legumes which are rich in protein and oil content. Nutrients deficiency in soybean plant could affect the growth of the plants and might lead to loss in its yield. The developments in modern technologies such as computer vision and deep learning are being leveraged in identifying nutrient deficiencies in soybean plants. Methods: Convolutional neural network with six feature extraction blocks and one classification block is developed to identify macro nutrient deficiency in soybean plants. Images are first collected, pre-processed and labeled. They are then split into training images and testing images in the ratio of 80:20. The proposed convolutional neural network model is trained over training images and the final trained model is tested with testing images. Result: In detecting the deficiency of macro nutrients such as nitrogen, phosphorus and potassium in soybean plants, the testing results of the proposed convolutional neural network architecture achieved an accuracy of 97.43%. Accuracy comparison against existing models such as VGG16, ResNet50 and MobileNetV3 demonstrate that the proposed model effectively identifies nutrient deficiencies in soybean plants. Thus, the proposed system is designed to support farmers in making timely decisions and to contribute to food security by leveraging deep learning techniques.

Root exudates serve as crucial mediators for information exchange between plants and soil, and are an important evolutionary mechanism for plants’ adaptation to environmental changes. In this study, 15 different abiotic stress models were established using various stress factors, including drought (D), high temperature (T), nitrogen defi- ciency (N), phosphorus deficiency (P), and their combinations. We investigated their effects on the seedling growth of Salvia miltiorrhiza Bunge and the activities of Solid-Urease (S-UE), Solid-Nitrite Reductase (S-NiR), Solid-Nitrate Reductase (S-NR), Solid-Phosphotransferase (S-PT), and Solid-Catalase (S-CAT), as well as the contents of polysaccharides in the culture medium. The results showed that the growth of S. miltiorrhiza was inhibited under 15 stress conditions. Among them, 13 stress conditions increased the root-shoot ratio. These 15 stress conditions significantly reduced the activity of S-NR, two combinations significantly improved the activity of S-NIR, they were synergistic stresses of high temperature and nitrogen deficiency (TN), and synergistic stresses of drought and nitrogen deficiency (DN) (p < 0.05). The activity of S-UE was significantly improved under N, D, T, synergistic stresses of drought and high temperature (DT), DN, synergistic stresses of drought and phosphorus deficiency (DP), and synergistic stresses of high temperature, nitrogen, and phosphorus deficiency (TNP) stress conditions (p < 0.05). Most stress combinations reduced the activity of S-PT, but D and T significantly improved it. (p < 0.05). The N, DN, and TN stress conditions significantly reduced S-CAT activity. The P, DT, and synergistic stresses of drought, high temperature, and phosphorus deficiency (DTP) significantly decreased the total polysaccharide content of the soil (p < 0.05). The research suggested that abiotic stress hindered the growth of S. miltiorrhiza and altered the behavior of root secretion. Roots regulated the secretion of several substances in response to various abiotic stresses, including soil nitrogen cycle enzymes, phosphorus transport-related enzymes, and antioxidant enzymes. In conclusion, plants regulate the utilization of rhizosphere substances in response to abiotic stresses by modulating the exudation of soil enzymes and polysaccharides by the root system. At the same time, soil carbon sequestration was affected by the adverse environment, which restricted the input of organic matter into the soil.

Nutrient deficiency limits population development, yield formation, and nutrient uptake of direct sown winter oilseed rape