Rice Leaf Research Articles

Hyperspectral and Fluorescence Imaging Approaches for Nondestructive Detection of Rice Chlorophyll.

Estimating and monitoring chlorophyll content is a critical step in crop spectral image analysis. The quick, non-destructive assessment of chlorophyll content in rice leaves can optimize nitrogen fertilization, benefit the environment and economy, and improve rice production management and quality. In this research, spectral analysis of rice leaves is performed using hyperspectral and fluorescence spectroscopy for the detection of chlorophyll content in rice leaves. This study generated ninety experimental spectral datasets by collecting rice leaf samples from a farm in Sichuan Province, China. By implementing a feature extraction algorithm, this study compresses redundant spectral bands and subsequently constructs machine learning models to reveal latent correlations among the extracted features. The prediction capabilities of six feature extraction methods and four machine learning algorithms in two types of spectral data are examined, and an accurate method of predicting chlorophyll concentration in rice leaves was devised. The IVSO-IVISSA (Iteratively Variable Subset Optimization-Interval Variable Iterative Space Shrinkage Approach) quadratic feature combination approach, based on fluorescence spectrum data, has the best prediction performance among the CNN+LSTM (Convolutional Neural Network Long Short-Term Memory) algorithms, with corresponding RMSE-Train (Root Mean Squared Error), RMSE-Test, and RPD (Ratio of standard deviation of the validation set to standard error of prediction) indexes of 0.26, 0.29, and 2.64, respectively. We demonstrated in this study that hyperspectral and fluorescence spectroscopy, when analyzed with feature extraction and machine learning methods, provide a new avenue for rapid and non-destructive crop health monitoring, which is critical to the advancement of smart and precision agriculture.

Cytoplasmic Ca2+ influx mediates iron- and reactive oxygen species-dependent ferroptotic cell death in rice immunity.

Iron- and reactive oxygen species (ROS)-dependent ferroptosis occurs in plant cells. Ca2+ acts as a conserved key mediator to control plant immune responses. Here, we report a novel role of cytoplasmic Ca2+ influx regulating ferroptotic cell death in rice immunity using pharmacological approaches. High Ca2+ influx triggered iron-dependent ROS accumulation, lipid peroxidation, and subsequent hypersensitive response (HR) cell death in rice (Oryza sativa). During Magnaporthe oryzae infection, 14 different Ca2+ influx regulators altered Ca2+, ROS and Fe2+ accumulation, glutathione reductase (GR) expression, glutathione (GSH) depletion and lipid peroxidation, leading to ferroptotic cell death in rice. High Ca2+ levels inhibited the reduction of glutathione isulphide (GSSG) to GSH in vitro. Ca2+ chelation by ethylene glycol-bis (2-aminoethylether)-N, N, N', N'-tetra-acetic acid (EGTA) suppressed apoplastic Ca2+ influx in rice leaf sheaths during infection. Blocking apoplastic Ca2+ influx into the cytoplasm by Ca2+ chelation effectively suppressed Ca2+-mediated iron-dependent ROS accumulation and ferroptotic cell death. By contrast, acibenzolar-S-methyl (ASM), a plant defense activator, significantly enhanced Ca2+ influx, as well as ROS and iron accumulation to trigger ferroptotic cell death in rice. The cytoplasmic Ca2+ influx through calcium-permeable cation channels, including the putative resistosomes, could mediate iron- and ROS-dependent ferroptotic cell death under reduced GR expression levels in rice immune responses.

Detection of Rice Tungro Bacilliform Virus (RTBV) causes of tungro disease in rice plant (Oryza sativa l.) in Langkat, North Sumatera using PCR (Polymerase Chain Reaction) technique

Tungro is one of the important disease in rice which is an obstacle in increasing rice production in Langkat. The detection of diseases caused by this virus has many barrier since there are many virus also have similar symptoms in rice plants, therefore it requires a more accurate technique like PCR. The PCR detects directly the virus itself or its type. Rice leaf samples were taken by Random purposive sampling as many as 16 samples with symptoms of viral diseases from 16 villages in Langkat Regency. The genomic DNA was isolated from the samples and analyzed the virus using specific primers. The indications of infected rice leaf showed dwarf plants, yellowing leaves, few plant saplings, dark spots, rust spots, and midrib and short leaf blades in all samples at 16 villages at Langkat Regency. The similarity analysis of the 16 samples based on symptoms analyzed by the Unwight Pair Group Method with Arithmetic Average (UPGMA) is displayed in the form of a dendogram. All collections of symptomatic rice leaves from 16 villages were clustered at 79% similarity based on symptoms of viral disease. The results of the PCR were successfully amplified and positively infected with Rice Tungro Bacilliform Virus (RTBV) indicated by the presence of a 430 bp band fragment after being analyzed by PCR (Polymerase Chain Reaction) technique.

Rice leaf chlorophyll content estimation with different crop coverages based on Sentinel-2

Chlorophyll content is an important index for evaluating the health and productivity of crops, and environmental stress on them. The real-time, rapid, and accurate acquisition of chlorophyll content plays a key role in crop growth monitoring. Remote sensing can quickly obtain chlorophyll content in regional and global scale, but how to eliminate the interference of soil background in estimation is a major challenge. The statistical analysis method based on empirical/semi-empirical model is simpler, faster and easier to implement than that based on radiative transfer mechanism model. The statistical analysis method can eliminate the influence of environmental background by looking for a Vegetation index (VI) that is sensitive to the chlorophyll content but not to soil background to a certain extent. However, the accuracy of this method is low in fields with different degrees of crop coverage. Additionally, the special soil background characteristics of rice fields make the method a doubtful tool to estimate the Chlorophyll content in rice coverage. To improve the accuracy of the rice leaf chlorophyll content (LCC) estimation model, we here propose a new model based on crop coverage. We analyzed remote sensing images of the Sentinel-2 over rice-planting areas of Qian Gorlos County in Jilin Province of China. We divided the study area into three regions based on high-, medium-, and low-rice canopy coverage. Rice LCC in each region was estimated by identifying remote sensing vegetation indices that are sensitive to chlorophyll in different rice canopy coverages. Compared to the estimated results without considering the crop coverage, our model achieves a higher accuracy. In addition, we applied the model in the region of Northeast China in 2023 to verify its strong generalisability and robustness. Our study provides a reference for rapidly and non-destructively obtaining rice LCC based on Sentinel-2 images. However, the applicability of our model to other crops will be verified in the future.

Rice Leaf Disease Detection using Deep Learning

Abstract: A wide range of bacterial, viral, or fungal diseases can damage rice leaves, significantly reducing rice yield. Finding the causes of rice ailments in the leaves is essential to feeding the world's massive population. However, the recognition of rice leaf rot depends on the settings and background of the image capture. Convolutional neural network (CNN) driven model is one of the most popular study topics in rice leaf disease detection. However, the existing CNN-based models only learn large network parameters and perform much worse in terms of recognition rates on different datasets. In order to detect rice leaf illnesses, we lower the network parameters and introduce a unique CNN-based method in this research. Using a special dataset of 4199 images ofrice leaf diseases, multiple CNN-based models are trained to identify five common rice leaf diseases. The recommended model achieves the best levels of 99.78% training accuracy and 97.35% validation accuracy. An independent set of pictures of rice leaf disease is used to evaluate the effectiveness of the proposed model, yielding the highest accuracy of 97.82% and an area under the curve (AUC) of 0.99. Additionally, based on binary classification trials, our proposed model achieves identification rates of 97%, 96%, 96%, 93%, and 95% for Blast, Brown spot, Bacterial Leaf Blight, Sheath Blight, and Turgor, respectively. These results demonstrate the effectiveness and superiority of our approach over the most sophisticated CNN-based algorithms for recognizing rice leaf

Morpho-biochemical Basis of Resistance Against Cnaphalocrocis Medinalis Guenee in South Gujarat

The study aimed to investigate the morpho-biochemical basis of resistance to the rice leaf folder Cnaphalocrocis medinalis in ten rice varieties, at the Main Rice Research Centre Farm, Navsari Agricultural University, Navsari, Gujarat during kharif 2021. The width of the leaves varied among the varieties, with GNR-2, GNR-6, GNR-7, and GR-15 having the smallest leaves and TN-1 and GNR-4 having the largest. There was a significant positive correlation between leaf width and infestation. Analysis of chlorophyll, sugar, and protein content in the leaves showed that TN-1 had the highest levels at both 30 days and 50 days after transplanting (DAT), while GR-15 had the lowest. These factors were positively correlated with infestation. On the other hand, phenol content was the highest in GR-15 and lowest in TN-1, with a significant negative correlation with infestation. Chlorophyll, sugar, and protein content increased with higher infestation levels while phenol content decreased.

Combining canopy spectral reflectance and RGB images to estimate leaf chlorophyll content and grain yield in rice

Predicting rice grain yield using multi-source remotely sensed data is crucial for improving prediction accuracy, optimizing nitrogen management, and advancing precision agricultural development. However, the feasibility and reliability of using multi-source remotely sensed data to predict the grain yield remain unclear. Therefore, this study aimed to explore the possibility of providing rice leaf chlorophyll content (LCC) estimations and predictions of the grain yield using multi-source remotely sensed data. Two rice field experiments were conducted with various rice cultivars and nitrogen rates, and a field spectrometer and an unmanned aerial vehicle (UAV) equipped with a digital camera were employed to acquire the spectral reflectance and red–green–blue (RGB) images at the tillering, jointing, and full-heading stages. Destructive sampling was then conducted to measure the LCC and grain yield. The LCC was used as a bridge to develop remotely sensed prediction models for the grain yield. First, the linear relationship between grain yield and the LCC was determined at the tillering, jointing, and full-heading stages. A multiple linear regression (MLR) model was then developed to predict grain yield using multi-temporal LCCs at three growth stages. Second, multiple stepwise regression, support vector regression, and back propagation neural network were used to evaluate the estimation performance of spectral reflectance, RGB image data, and their combination for LCC. Third, the most accurate LCC estimation model was selected and coupled with the linear and MLR models of grain yield. The results showed that grain yield was significantly and positively related to the LCC at the tillering, jointing, and full-heading stages, and that the MLR model of grain yield achieved the best estimation accuracy using multi-temporal LCCs. The fusion models established by combining spectral reflectance and RGB image data improved LCC estimation accuracies. Using multi-growth stages, the most accurate predictions of grain yield were obtained from LCC estimation models (R2 = 0.698, RMSE = 0.742 t ha−1, rRMSE = 9.004 %) compared to those using single growth stages. Our study concluded that multi-source remotely sensed data fused from ground-based spectral reference and UAV-based RGB images can better predict and explain the grain yield for both single and multi-growth stages. This study provides a novel method of estimating the crop chlorophyll content and grain yield.

Design an optimization based ensemble machine learning framework for detecting rice leaf diseases

Design an optimization based ensemble machine learning framework for detecting rice leaf diseases

Beyond the β-amino alcohols framework: identification of novel β-hydroxy pyridinium salt-decorated pterostilbene derivatives as bacterial virulence factor inhibitors.

Bacterial virulence factors are involved in various biological processes and mediate persistent bacterial infections. Focusing on virulence factors of phytopathogenic bacteria is an attractive strategy and crucial direction in pesticide discovery to prevent invasive and persistent bacterial infection. Hence, discovery and development of novel agrochemicals with high activity, low-risk, and potent anti-virulence is urgently needed to control plant bacterial diseases. A series of novel β-hydroxy pyridinium cation decorated pterostilbene derivatives were prepared and their antibacterial activities against Xanthomonas oryzae pv. oryzae (Xoo) were systematacially assessed. Among these pterostilbene derivatives, compound 4S exhibited the best antibacterial activity against Xoo in vitro, with an half maximal effective concentration (EC50) value of 0.28 μg mL-1. A series of biochemical assays including scanning electron microscopy, crystal violet staining, and analysis of biofilm formation, swimming motility, and related virulence factor gene expression levels demonstrated that compound 4S could function as a new anti-virulence factor inhibitor by interfering with the bacterial infection process. Furthermore, the pot experiments provided convinced evidence that compound 4S had the high control efficacy (curative activity: 71.4%, protective activity: 72.6%), and could be used to effectively manage rice bacterial leaf blight in vivo. Compounds 4S is an attractive virulence factor inhibitor with potential for application in treating plant bacterial diseases by suppressing production of several virulence factors. © 2024 Society of Chemical Industry.

Transcriptome analysis reveals the inhibitory mechanism of 3,4-Dimethoxyphenol from Streptomyces albidoflavus strain ML27 against Xanthomonas oryzae pv. oryzae

Bacterial leaf blight, caused by Xanthomonas oryzae pv. oryzae (Xoo), poses a significant threat to rice cultivation across diverse regions. Growing concerns about pesticide resistance and environmental impact underscore the urgent necessity for eco-friendly biopesticides. Here, the complete genome sequence of Streptomyces albidoflavus strain ML27 revealed substantial antimicrobial activity and secondary metabolite production potential through genome mining. 3,4-dimethoxyphenol (purity 97%) was successfully isolated from the fermentation broth of S. albidoflavus strain ML27, exhibiting broad and pronounced inhibitory effects on the growth of seven different fungi and five tested bacteria. The efficacy of 3,4-dimethoxyphenol in controlling rice bacterial leaf blight was evaluated through pot tests, demonstrating substantial therapeutic (69.39%) and protective (84.53%) effects. Application of 3,4-dimethoxyphenol to Xoo resulted in cells displayed notable surface depressions, wrinkles, distortions, or even ruptures compared to their typical morphology. Transcriptome analysis revealed significant inhibition of membrane structures, protein synthesis and secretion, bacterial secretion system, two-component system, flagellar assembly, as well as various metabolic and biosynthetic pathways by 3,4-dimethoxyphenol. Notably, the down-regulation of the type III secretion system (T3SS) expression was a pivotal finding. Furthermore, validation via quantitative real-time polymerase chain reaction (qRT-PCR) analysis confirmed significant downregulation of 10 genes related to T3SS upon 3,4-dimethoxyphenol treatment. Based on these results, it is promising to develop 3,4-dimethoxyphenol as a novel biopesticide targeting the T3SS of Xoo for controlling bacterial leaf blight in rice.

A novel technique predicting the rice leaf diseases using Convolutional Neural Network

Various ailments affect rice, a staple crop in India, across different stages of its growth. Identification of these diseases manually poses a significant challenge, especially for farmers lacking in-depth knowledge. Recently, there's been promising advancement in deep learning research through automated picture identification systems employing Convolutional Neural Network (CNN) models. To tackle the scarcity of rice leaf disease image datasets, we developed a deep learning model using Transfer Learning on a limited dataset. Our approach leverages VGG-16 to train and evaluate the proposed CNN architecture, drawing from rice field and internet datasets. Impressively, the model achieves a 95 percent accuracy rate. Key terms in this study include Deep Learning, Convolutional Neural Network (CNN), fine-tuning, and rice leaf diseases.

Rice Leaf Diseases Detection Using YOLOv8

The development of rice plants holds immense importance today as it impacts crucial aspects of life such as food security, agricultural advancement, and the economy of nations. Consequently, research on disease detection in rice plants, particularly using machine learning, is gaining popularity. Several diseases pose a threat to rice leaves, with Leaf Blast, Leaf Folder, and Brown Spot being the most common ones, directly affecting crop cultivation and causing yield loss. In this study, we propose the utilization of deep learning, the state-of-the-art image processing solution, to address this issue. Our proposed method consists of two steps: first, collecting reliable dataset by approaching and capturing direct images of rice leaf diseases in the fields, and second, designing and training an Artificial Intelligence (AI) model using the YOLOv8 algorithm to detect and classify the three aforementioned diseases. The data set used in this study includes 3175 images, divided into three parts, of which the training part is 2608 images, the validation part is 326 images and the test part is 241 images. Our experimental results demonstrate an accuracy up to 88.9% for the proposed model.

A Communication-Efficient Federated Learning Framework for Sustainable Development Using Lemurs Optimizer

The pressing need for sustainable development solutions necessitates innovative data-driven tools. Machine learning (ML) offers significant potential, but faces challenges in centralized approaches, particularly concerning data privacy and resource constraints in geographically dispersed settings. Federated learning (FL) emerges as a transformative paradigm for sustainable development by decentralizing ML training to edge devices. However, communication bottlenecks hinder its scalability and sustainability. This paper introduces an innovative FL framework that enhances communication efficiency. The proposed framework addresses the communication bottleneck by harnessing the power of the Lemurs optimizer (LO), a nature-inspired metaheuristic algorithm. Inspired by the cooperative foraging behavior of lemurs, the LO strategically selects the most relevant model updates for communication, significantly reducing communication overhead. The framework was rigorously evaluated on CIFAR-10, MNIST, rice leaf disease, and waste recycling plant datasets representing various areas of sustainable development. Experimental results demonstrate that the proposed framework reduces communication overhead by over 15% on average compared to baseline FL approaches, while maintaining high model accuracy. This breakthrough extends the applicability of FL to resource-constrained environments, paving the way for more scalable and sustainable solutions for real-world initiatives.

The Oryza sativa transcriptome responds spatiotemporally to polystyrene nanoplastic stress

Nanoplastic represents an emerging abiotic stress facing modern agriculture, impacting global crop production. However, the molecular response of crop plants to this stress remains poorly understood at a spatiotemporal resolution. We therefore used RNA sequencing to profile the transcriptome expressed in rice (Oryza sativa) root and leaf organs at 1, 2, 4, and 8 d post exposure with nanoplastic. We revealed a striking similarity between the rice biomass dynamics in aboveground parts to that in belowground parts during nanoplastic stress, but transcriptome did not. At the global transcriptomic level, a total of 2332 differentially expressed genes were identified, with the majority being spatiotemporal specific, reflecting that nanoplastics predominantly regulate three processes in rice seedlings: (1) down-regulation of chlorophyll biosynthesis, photosynthesis, and starch, sucrose and nitrogen metabolism, (2) activation of defense responses such as brassinosteroid biosynthesis and phenylpropanoid biosynthesis, and (3) modulation of jasmonic acid and cytokinin signaling pathways by transcription factors. Notably, the genes involved in plant-pathogen interaction were shown to be successively modulated by both root and leaf organs, particularly plant disease defense genes (OsWRKY24, OsWRKY53, Os4CL3, OsPAL4, and MPK5), possibly indicating that nanoplastics affect rice growth indirectly through other biota. Finally, we associated biomass phenotypes with the temporal reprogramming of rice transcriptome by weighted gene co-expression network analysis, noting a significantly correlation with photosynthesis, carbon metabolism, and phenylpropanoid biosynthesis that may reflect the mechanisms of biomass reduction. Functional analysis further identified PsbY, MYB, cytochrome P450, and AP2/ERF as hub genes governing these pathways. Overall, our work provides the understanding of molecular mechanisms of rice in response to nanoplastics, which in turn suggests how rice might behave in a nanoplastic pollution scenario.

Preparation and performance of 10 wt% of chlorantraniliprole Nano-suspension concentrate (SC) using polyether amine-bridged sulfonated alkali lignin (PSAL) as a dispersant

Polyether amine-bridged sulfonated alkali lignin (PSAL) with different sulfonic group contents and molecular weights was firstly synthesized and characterized. Then, 10 wt% of chlorantraniliprole Nano-suspension concentrate (SC) was prepared by the water-based grinding method, and the optimum grinding parameters were explored and obtained. Based on this optimum grinding formula, chlorantraniliprole Nano-SC was prepared and three optimum dispersants were finally obtained as follows: the compounds of polycarboxylate D-2 separately with P1SAL0.68, P1SAL0.84 and TERSPERSE 2500 at the mass ratio of 1:1. All Nano-SC prepared by these three dispersants had a D90 particle size below 200 nm, suspension percentage above 99%, water separation proportion below 1%, excellent thermal storage stability, and also better wettability on banana leaf surface. Additionally, adding glycerin could effectively inhibit the agglomeration and austenogenization of pesticide nanoparticles, and thus improve the stability of Nano-SC. Finally, the farmland experiments indicated chlorantraniliprole Nano-SC prepared in this work had a significantly improved pesticide effect on first-instar rice leaf rollers than traditional micron-sized SC. This work provided a new dispersant with excellent performance for chlorantraniliprole Nano-SC as well as broadened the high value-added utilization of industrial lignin into pesticide Nano-SC field, which had great economic and environmental benefits.

An oligo peptide transporter family member, OsOPT7, mediates xylem unloading of Fe for its preferential distribution in rice.

Iron (Fe) needs to be delivered to different organs and tissues of above-ground parts for playing its multiple physiological functions once it is taken up by the roots. However, the mechanisms underlying Fe distribution are poorly understood. We functionally characterized OsOPT7, a member of oligo peptide transporter family in terms of expression patterns, localization, transport activity and phenotypic analysis of knockdown lines. OsOPT7 was highly expressed in the nodes, especially in the uppermost node I, and its expression was upregulated by Fe-deficiency. OsOPT7 transports ferrous iron into the cells coupled with proton. Immunostaining revealed that OsOPT7 is mainly localized in the xylem parenchyma cells of the enlarged vascular bundles in the nodes and vascular tissues in the leaves. Knockdown of OsOPT7 did not affect the Fe uptake, but altered Fe distribution; less Fe was distributed to the new leaf, upper nodes and developing panicle, but more Fe was distributed to the old leaves. Furthermore, knockdown of OsOPT7 also resulted in less Fe distribution to the leaf sheath, but more Fe to the leaf blade. Taken together, OsOPT7 is involved in the xylem unloading of Fe for both long-distance distribution to the developing organs and local distribution within the leaf in rice.

An Advanced CNN based System for Rice Plant Diseases Detection and classification in Precision Agriculture

For the vast majority of people on the planet, agriculture is one of the most crucial industries. Rice is a vital food source, but it also faces serious risks from illnesses that can affect yield quality and quantity, potentially resulting in 20% to 40% crop losses. Reducing production losses requires early diagnosis of these disorders. For farmers, however, it is not possible to manually monitor such large areas of field. The proposed model based on a Convolutional Neural Network of Resnet50 and transfer learning model, specifically a modified TLResnet152V2. Transfer learning-based weights are used for precise identification and categorization and detection for rice leaf diseases. The proposed system demonstrates high accuracy in identifying four classes of rice diseases viz: Brown spot, Healthy, LeafBlast, NeckBlast. It achieves a remarkable accuracy of Resnet50 & TLResnet152V2 is 93.20% and 95.03 % for normalized augmented dataset respectively. Comparative analysis reveals that modified approach outperforms similar methodologies applied to the Bangladesh rice dataset or datasets of comparable size given in the existing research work. Overall findings underscore the efficacy of proposed approach in advancing the precision of rice plant disease detection, offering a promising solution to enhance agricultural practices and mitigate production losses.

Detection of diseases in rice leaf using convolutional neural network with transfer learning based on ResNeXt

Rice is the most cultivated crop in the agricultural field and is a major food source for more than 60% of the population in India. Occurrence of disease in rice leaves, majorly affects the rice quality, production and also the farmers’ income. Nowadays, new variety of diseases in rice leaves are identified and detected periodically throughout the world. Manual monitoring and detection of plant diseases proves to be time consuming for the farmer and also a costly affair for using chemicals in the disease treatment. In this paper, a deep learning method of convolutional neural networks (CNN) with a transfer learning technique is proposed for the detection of a variety of diseases in rice leaves. This method uses the ResNeXt network model for classifying the images of disease-affected plants. The proposed model’s performance is evaluated using accuracy, precision, recall, F1-score and specificity. The experimental results of ResNeXt model measured for accuracy, precision, recall, F1-score, and specificity, are respectively 99.22%, 92.87%, 91.97%, 90.95%, and 99.05%, which proves greater accuracy improvement than the existing methods of SG2-ADA, YOLOV5, InceptionResNetV2 and Raspberry Pi.

ANALYZING THE COMPARATIVE METHODS OF PREWITT, ROBINSON, KRISCH AND ROBERTS IN DETECTING THE EDGES OF RICE LEAVES

This research explores the vital role of rice in Indonesia as a staple food and primary source of income for farmers. Efforts are being made to increase rice production to meet the growing demand. The study focuses on object edge detection in image analysis, evaluating methods like Prewitt, Robinson, Krisch, and Roberts. Digital imaging plays a crucial part in visually presenting information, and image processing improves image quality for human and machine recognition. Detecting object edges, particularly in rice leaf images, is essential for computer inspection. The experiment on fifteen rice leaf images shows that the Krisch method performs better in edge detection, with a 52% average accuracy and smoothness. Other methods, such as Prewitt (6%), Robinson (11%), and Roberts (14%), have lower accuracy rates. These findings provide a foundation for enhancing edge detection in rice leaf image analysis. The study also emphasizes the need for refining classification models. Overall, this research provides insights into the effectiveness of edge detection methods in rice leaf image analysis.

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

In this study, we address that foliar diseases of rice (Oryza sativa L.) pose a serious threat to agricultural productivity and propose an effective method for disease detection using Convolutional Neural Network (CNN). We use transfer learning on the MobilenetV3Large model to improve the model's performance. Our study involves a curated dataset containing images of infected rice leaves, followed by a careful preprocessing step. This dataset is then used to train a CNN model. The results show a commendable accuracy rate of over 90% and almost reaching 95% when the model is trained over 200 epochs. The model performance graph shows a consistent upward trend in accuracy coupled with decreasing loss during the training process. Furthermore, the classification results highlight the ability of the model to discriminate between different types of diseases affecting rice leaves. This study demonstrates the effectiveness of our proposed method and positions it as a valuable tool for leaf disease detection in rice. By providing faster and more accurate control measures, our approach has the potential to significantly improve agricultural productivity. The successful application of the CNN model using MobilenetV3Large highlights its adaptability and robust performance in addressing the pressing problem of rice leaf diseases and provides a promising path for future advances in precision agriculture.