Rice Leaf Research Articles

Detection of Rice Leaf Folder in Paddy Fields Based on Unmanned Aerial Vehicle-Based Hyperspectral Images

Pest infestations significantly impact rice production and threaten food security. Remote sensing offers a vital tool for the non-destructive, rapid detection of rice pests. Existing studies often focus on laboratory conditions at the leaf level, limiting their applicability for precise pesticide application. Therefore, this study aimed to develop a method for detecting rice pests (rice leaf folders) in paddy fields based on unmanned aerial vehicle (UAV) hyperspectral data. Firstly, a UAV imaging system collected hyperspectral images of rice plants in both the jointing and heading stages. A total of 222 field plots for investigating rice leaf folders was established during these two periods. Secondly, 23 vegetation indices were calculated as candidates for identifying rice pests. Then, hyperspectral data and field investigation data from the jointing stage were used to construct a machine learning (extreme gradient boosting, XGBoost) algorithm for detecting rice pests. The results showed that the XGBoost model exhibited the best performance when eight vegetation indices were considered as the selected input features for model construction: the Red-edge Normalized Difference Vegetation Index (red-edge NDVI), Structure Insensitive Pigment Index (SIPI), Enhanced Vegetation Index (EVI), Atmospherically Resistant Vegetation Index (ARVI), Soil-Adjusted Vegetation Index (SAVI), Red-edge Chlorophyll Index (CIred-edge), Pigment-Specific Simple Ratio680 (PSSR680), and Carotenoid Reflectance Index700 (CPI700). The training and testing accuracies reached 87.46% and 86%, respectively. Furthermore, the heading stage application confirmed the model’s feasibility. Thus, the XGBoost model with input features of eight vegetation indices provides an effective and reliable method for detecting rice leaf folders, supporting real-time, precise pesticide use in rice cultivation.

Using Immunoblotting for Detection of a Circadian Clock Component, Os-GI, in Rice Leaves.

The adaptability of plants to given environmental conditions is achieved through the regulation of various genes. The functional regulation of genes depends on precise transcriptional and translational controls that, at the end, determine the expression of the translated products (proteins). Here, I describe the immunoblotting method for the detection of proteins expressed in rice leaves. This method includes protein extraction, protein separation, electroblotting, and immune detection.

DeLTa-Seq: High-Throughput Targeted RNA-Seq of Rice Leaves Without RNA Purification.

DeLTa-seq is a high-throughput RNA-seq library preparation method that enables quantification of the expression of hundreds of arbitrarily selected genes without RNA purification. This method involves direct reverse transcription using rice leaf lysate and targeted RNA-seq library preparation. DeLTa-seq enables the precise quantification of gene expression with a small number of sequencing reads. This chapter provides detailed information on the design of gene-specific primers, sampling of rice leaves, preparation of lysates, direct-lysate reverse transcription, targeted RNA-seq library preparation, and bioinformatic analysis of DeLTa-seq data.

Deep Learning-Based Classification Methods for Detection of Diseases in Rice Leaves – A Review

Deep Learning-Based Classification Methods for Detection of Diseases in Rice Leaves – A Review

Design, Synthesis, and Biological Activity Studies of Myricetin Derivatives Containing a Diisopropanolamine Structure.

A series of myricetin derivatives containing diisopropanolamine were designed and synthesized. The in vitro inhibitory effects of the target compounds on 9 fungal pathogens and 3 bacterial pathogens were also evaluated. A12 had the best inhibitory effect against Xanthomonas oryzae pv. oryzae (Xoo), with an EC50 value of 4.9 μg/mL, which was better than zinc-thiazole (ZT: EC50 = 7.3 μg/mL) and thiodiazole-copper (TC: EC50 = 65.5 μg/mL); A25 had the best inhibitory effect against Phomopsis sp. (Ps), with an EC50 value of 17.2 μg/mL, which was better than azoxystrobin (Az: EC50 = 22.3 μg/mL). In vivo inhibition tests were performed on kiwifruit for A25 and rice leaves for A12. At 200 μg/mL, the curative activity of A12 against rice leaf blight was 40.7%, which was better than that of ZT (37.2%) and TC (32.9%), and the protective activity of A12 was 44.8%, which was better than that of ZT (39.5%) and TC (34.6%). The curative activity of A25 against kiwi soft rot disease was 70.1%, which was better than that of Az (62.8%). Preliminary elucidation of the possible mechanisms of action was carried out by experiments on fluorescence microscopy, scanning electron microscopy, formation of biofilms, density functional theory calculations, and so on.

Rice Leaf Disease Classification—A Comparative Approach Using Convolutional Neural Network (CNN), Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), and MobileNet-V2 Architectures

Classifying rice leaf diseases in agricultural technology helps to maintain crop health and to ensure a good yield. In this work, deep learning algorithms were, therefore, employed for the identification and classification of rice leaf diseases from images of crops in the field. The initial algorithmic phase involved image pre-processing of the crop images, using a bilateral filter to improve image quality. The effectiveness of this step was measured by using metrics like the Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). Following this, this work employed advanced neural network architectures for classification, including Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), MobileNetV2, and Convolutional Neural Network (CNN). The proposed CNN model stood out, since it demonstrated exceptional performance in identifying rice leaf diseases, with test Accuracy of 98% and high Precision, Recall, and F1 scores. This result highlights that the proposed model is particularly well suited for rice leaf disease classification. The robustness of the proposed model was validated through k-fold cross-validation, confirming its generalizability and minimizing the risk of overfitting. This study not only focused on classifying rice leaf diseases but also has the potential to benefit farmers and the agricultural community greatly. This work highlights the advantages of custom CNN models for efficient and accurate rice leaf disease classification, paving the way for technology-driven advancements in farming practices.

Identification and functional study of Fib-L, a major silk fibroin gene component in rice leaf folders.

The rice leaf folder, Cnaphalocrocis medinalis (Lepidoptera: Pyralidae), is a major migratory pest in rice agriculture. This pest is characterised by its larvae's ability to fold rice leaves using silk, a behaviour that culminates in the formation of a silken cocoon during the pupal stage. The fibroin light chain (CmFib-L) gene is crucial for silk production, yet its specific function in C. medinalis has reminded elusive. This study presents a comprehensive analysis of the CmFib-L gene, revealing its complete open reading frame (ORF) and expression patterns. Notably, the gene is highly expressed in the fifth-instar larvae and the silk gland, which are critical stages for silk production. Our experiments demonstrate that silencing the CmFib-L gene leads to a reduction in pupal weight, an extension of the pupal stage and a disorganised silk cocoon. Furthermore, the larval behaviour of leaf folding and spinning is significantly impaired when the expression of CmFib-L is downregulated. These findings not only show the importance of fibroin light chain in silk production but also reveal a new target gene to regulate and control the behaviour and development of C. medinalis.

Heredity and fine mapping of a yellow leaf and less tillering mutant yllt10 in rice

Rice (Oryza sativa L.) is a major food crop and increasing rice yield is the primary objective of rice research. Photosynthesis and nitrogen utilization efficiency directly affect the tiller number of rice, which affects the yield of rice. In this study, a stable yellow leaf and less tillering rice mutant yllt10 (yellow leaf and less tillering 10) was obtained by heavy-ion beam mutagenesis of rice variety 'Ke-fu-geng 7'. Compared with the wild type, yllt10 showed reduced chlorophyll content, decreased photosynthesis rate, and abnormal chloroplast structure. The genetic analysis indicated that the phenotype of yllt10 was controlled by a single recessive nuclear gene. Map-based cloning localized YLLT10 between two molecular markers J4 and J5 on chromosome 10. The sequencing of candidate genes within this interval revealed that YLLT10 was an allelic mutation of CAO1/PGL with a single base deletion in the first exon resulting in the frame shift mutation of CAO1/PGL, and YLLT10 was a new allelic variation of CAO1/PGL. The mutant yllt10 was insensitive to changes in nitrogen concentration when being incubated with different nitrogen concentrations. YLLT10 controls leaf color and tiller number and affects photosynthesis and yield of rice. The study of this gene provides a theoretical basis for molecular breeding of rice.

Application of deep learning for rice leaf disease detection in the Mekong Delta

The Mekong River Delta, the largest rice-producing region in Vietnam with an annual output of over 25 million tons, plays a vital role in ensuring food security both within the country and globally. In recent years, it has undergone significant transformation in rice cultivation, which aims to support farmers here to plant rice more effectively. However, severe weather conditions and soil degradation have negatively impacted rice growth. Additionally, rice is highly susceptible to various diseases that must be identified and prevented promptly. As a result, leveraging technology such as AI and deep learning to diagnose rice diseases based on leaf symptoms is essential. This paper utilizes an image dataset of three common rice leaf diseases—leaf smut, brown spot, and bacterial leaf blight—and applies deep learning networks (MobileNet and ResNet) to evaluate and select the best model. A diagnostic program is then developed to detect these diseases. Experimental results show that the MobileNetV3-Small model (a variant of the MobileNet network) is the most optimal, offering fast training time, high accuracy, and acceptable levels of loss and error.

Revealing pest patterns: A comparative spatial distribution analysis of insect threats in Kharif rice across the key agricultural regions in the Eastern India.

This study investigates the spatial distribution and aggregation patterns of major insect pests in Kharif rice fields during the 2023 growing season in Eastern India. The analysis focuses on key pests such as yellow stem borer (YSB), gall midge, green leaf hopper (GLH), and brown planthopper (BPH), as well as rice thrips, caseworm, whorl maggot, Gundhi bug, grasshopper, and leaf folder. Using statistical indices, this study aims to understand pest behavior across Standard Meteorological Weeks (SMWs) to better inform pest control strategies. The study reveals significant clustering and aggregation patterns among the pests. YSB exhibited variance-mean ratio (VMR) values between 1.14 (40th SMW) and 1.96 (31st SMW), with dispersion parameter (K) values ranging from 0.57 to 21.65, and a peak index of dispersion of 132.66 (43rd SMW). Similarly, gall midge showed VMR values from 6.19 to 10.48, whereas GLH and BPH recorded VMR ranges of 1.19 to 132.10 and 1.01 to 1.50, respectively. These spatial distribution trends were confirmed through values for Iwao's patchiness index and Taylor's power law, indicating strong pest aggregation in specific areas. The results underscore the need for region-specific integrated pest management strategies that take into account pest clustering and environmental factors influencing pest distribution. Although an S-curve pattern of infestation-showing gradual population increases, rapid peaks, and eventual decline-was observed, the primary focus remains spatial patterns, which are critical for optimizing pest management and improving rice crop sustainability in the region. © 2024 Society of Chemical Industry.

Characterization of Endophytic Streptomyces rhizosphaericola Ahn75 and Its Potential for Biocontrol against Rice Blast.

Plant endophyte Streptomyces are excellent candidates as biocontrol agents against the rice blast fungus, Magnaporthe oryzae. In this study, a novel strain Ahn75 with antifungal activity was isolated from healthy rice stem and identified as Streptomyces rhizosphaericola by phenotypic characterization and phylogenetic analysis based on 16S rRNA, multilocus and genome sequences. Inhibition test using culture filtrate showed that Ahn75 could effectively suppress M. oryzae, with mycelia growth inhibition rate of 80.88% and spore germination inhibition rate of 78.26%. Genome sequence analysis of strain Ahn75 showed 40 gene clusters of secondary metabolites and several genes related to plant growth promotion were predicted in the genome of Ahn75. Several antimicrobial compounds including valinomycin, tetrabutylammonium, and benzalkonium chloride, were also detected in the antifungal fraction from Ahn75 culture filtrate by liquid chromatography and high resolution mass spectrometry. Meanwhile, strain Ahn75 demonstrates UV tolerance under UV irradiation for 60 min, pH tolerance between pH6 and pH9, and a high halotolerance in 7% (w/v) of NaCl. Greenhouse experiments indicated that Ahn75 is able to colonize rice stems, roots, and leaves, which help rice to reduce the rice leaf blast incidence by 59.76%. All these findings suggest that strain Ahn75 could be a potential biocontrol agent for rice blast.

Rice Leaf Diseases Classification Using Deep Learning Algorithms for Smartphone Application Development: An Empirical Study

Rice is the most widely consumed grain across the world. The rice plants often suffer from diseases. Early detection of such diseases and adopting remedial measures can help the farmers to avoid major losses and can produce best-quality crops in large quantities. However, the conventional rice leaf disease detection techniques are often not accurate, time-consuming and sometimes require laboratory testing. In this context, automatic rice leaf disease detection techniques are presented based on the various deep learning classifiers (namely MobileNetV2, ResNet50, VGG16 and Le-Net5) and an Android application is also developed in order to instantly determine the possible rice diseases from the uploaded rice leaf images captured by the smartphone. The developed models are tested using the publicly available benchmark rice leaf dataset containing three types of rice leaf diseases, namely bacterial leaf blight, leaf smut and brown spot. Experimental results show that MobileNetV2 model performed better compared to other models in terms of classification accuracy, recall and [Formula: see text]-score. The results of statistical significance test also confirmed the superiority of the MobileNetV2 model over other compared deep learning models.

Image recognition based on THGS algorithm to optimize ResNet-18 model

In order to quickly and accurately identify brown spot images, an improved THGS-ResNet-18 recognition model is proposed in this paper. Firstly, the Hunger Game search algorithm is improved by using Tent chaos mapping to solve the problem of excessive randomness in the population initialization of the Hunger Game search algorithm. Secondly, the hyperparameters of the improved Hunger Game search algorithm are optimized for the ResNet-18 model. Finally, the improved model THGS-ResNet-18 is applied to identify 5064 rice leaf images, and compared with four other ResNet-18 models improved by swarm intelligence algorithm on seven evaluation indicators. Experiments show that the model proposed in this paper has improved accuracy 5.22%−6.09%, sensitivity 3.53%−5.31%, specificity 7.38%, precision 6.95%−7.13%, recall 3.53%−5.31%, f-measure 5.22%−6.20%and g-mean 5.24%−6.13%.

Utilizing Convolutional Neural Networks for the Effective Classification of Rice Leaf Diseases Through a Deep Learning Approach

Utilizing Convolutional Neural Networks for the Effective Classification of Rice Leaf Diseases Through a Deep Learning Approach

Effects of nutritional stress on soil fertility and antioxidant enzymes of rice in different growth periods.

Stress in plants denotes the detrimental impact of alterations in external environmental conditions on regular plant growth and development. Plants employ diverse mechanisms to mitigate or evade nutritional stress-induced damage. In order to investigate the physiological response mechanism of plants to nutritional stress and assess its impact on soil nutrient content and antioxidant enzyme activity in rice, a field experiment was conducted applying five treatments: control, nitrogen (N) deficiency, phosphorus (P) deficiency, potassium (K) deficiency, and full fertilization. Rice leaf and soil samples were concurrently gathered during both the vegetative and reproductive growth stages of rice. Analysis was conducted on soil N, P, and K levels, as well as leaf antioxidant enzyme activities, to investigate the impact of nutrient stress on rice antioxidant enzymes and soil fertility. The research findings indicate that full fertilization treatment enhanced the agronomic properties of the soil compared to the control treatment. In the N-deficiency treatment, reactive oxygen species (ROS) levels increased by 16.53-33.89% during the reproductive growth period compared to the vegetative growth period. The peroxidase (POD) activity decreased by 41.39% and superoxide dismutase (SOD) activity increased by 36.22% under K-deficiency treatment during the reproductive growth period compared to the vegetative growth period. Consequently, applying N and P fertilizer during the vegetative growth period can decrease membrane lipid peroxidation levels by 7.34-72.53%. The full fertilization treatment markedly enhanced rice yield compared to other treatments and increased the Nitrogen activation coefficient (NAC) and Phosphorus activation coefficient (PAC) in the soil, while decreasing the PAC. Elevating NAC levels can stimulate the activity or content of PRO, MDA, and RPS during the vegetative growth stage, whereas in the reproductive growth stage, it will decrease the content of ROS, PRO, and MDA. This data offers valuable insights and theoretical support for nutritional stress research.

Allelochemicals Released from Rice Straw Inhibit Wheat Seed Germination and Seedling Growth

Recently, returning rice straw to soil has become a common problem in wheat production because it causes decreased wheat seedling emergence. Allelopathy is an important factor affecting seed germination. However, the effects of rice straw extracts on wheat seed germination and seedling growth remain unclear. Wheat seeds and seedlings were treated with 30 g L−1 of rice leaf extracts (L1), 60 g L−1 of rice leaf extracts (L2), 30 g L−1 of rice stem extracts (S1), 60 g L−1 of rice stem extracts (S2) and sterile water (CK) to study the allelopathic effects of rice straw extracts on wheat seed germination and seedling growth. The α-amylase and antioxidant enzyme activities in wheat seeds; the agronomic traits, photosynthetic indicators, and nutrient contents of wheat seedlings; and the phenolic acids in rice stem extracts were determined. Common allelochemicals, including 4-hydroxybenzoic acid, hydrocinnamic acid, trans-cinnamic acid, vanillic acid, benzoic acid, protocatechualdehyde, caffeic acid, syringic acid, sinapic acid, and salicylic acid, were detected in rice stem extracts. Low-concentration rice leaf and stem extracts (30 g L−1) had no effect on the germination rate of wheat seeds. High-concentration (60 g L−1) rice stem and leaf extracts decreased the seed germination rate by 11.00% and 12.02%. Rice stem extract (60 g L−1) decreased the α-amylase activity, and gibberellin content of wheat seeds but increased superoxide dismutase, peroxidase, and catalase activities and malondialdehyde content in wheat seeds. Allelochemicals entered the internal tissues of wheat seeds, where they decreased the gibberellin content and α-amylase activity and increased the antioxidant enzyme activity, ultimately leading to an inhibitory effect on seed germination. Rice stem and leaf extracts decreased the SPAD value and photosynthetic indicators of wheat seedlings. Rice stem extract (60 g L−1) decreased the fresh weight and root length of wheat seedlings by 31.37% and 45.46%. Low-concentration rice leaf and stem extract (30 g L−1) had no effect on the nutrient contents of wheat seedlings. Rice leaf and stem extracts (60 g L−1) decreased the nitrogen and potassium contents of wheat seedlings. These results indicated that low-concentration rice leaf and stem extract (30 g L−1) had no effect on wheat seed germination and the high-concentration rice stem extract (60 g L−1) released allelochemicals and inhibited wheat seed germination and seedling growth. These findings provide a basis for the improvement of straw return techniques.

Retraction: Optimized Scorpion Polypeptide LMX: A Pest Control Protein Effective against Rice Leaf Folder.

Retraction: Optimized Scorpion Polypeptide LMX: A Pest Control Protein Effective against Rice Leaf Folder.

Efficacy of Insecticides Against Yellow Stem Borer (Scirpophaga incertulas Walker) and Rice Leaf Folder (Cnaphaocrocis medinalis Guenee) and Their Impact on Natural Enemies in Rice Ecosystem

The experiment was conducted at AAU-Assam Rice Research Institute, Titabor to test the efficacy of some insecticides against yellow stem borer and rice leaf folder. Out of 8 tested insecticides, Chlorantraniliprole 18.5 SC showed the best result in minimizing yellow stem borer and rice leaf folder infestation. The lowest infestation percentage of yellow stem borer (2.10%) was observed on Chlorantraniliprole 18.5 SC treated plots followed by treatment with Chlorantraniliprole 10% + Lambda Cyhalothrin 5% ZC (2.33 %) at 7 DAT. Similarly, white ear head (0.33%) was also recorded as the lowest on Chlorantraniliprole 18.5 SC treated plots. Chlorantraniliprole 18.5 SC recorded the lowest infestation percentage of rice leaf folder at 7 DAT (3.40 %) and 14 DAT (3.53 %) followed by Chlorantraniliprole 10% + Lambda Cyhalothrin 5% ZC. While, the highest number of spiders and coccinellids were recorded in Chlorantraniliprole 0.4GR (2.43 spider/plant and 1.33 coccinellids/plant) followed by Thiamethoxam 25WG (2.13 spiders/plant and 1.10 coccinellids/plant). In terms of yield, Chlorantraniliprole 18.5 SC was found to be the best insecticide which provided the highest yield of 5.83t/ha among all the tested insecticides.

"A novel hybrid deep learning framework for enhanced segmentation of rice leaf diseases using attention-driven efficientnet models"

Rice diseases such as bacterial leaf blight, brown spot, and blast pose significant threats to global food security by reducing crop yields, making early and accurate detection crucial. This study aims to improve automated segmentation of rice leaf diseases using advanced deep learning techniques, specifically U-Net with MobileNetV2, DeepLabV3+ with EfficientNetB4, and U-Net with EfficientNetB7 integrated with attention gates. The models were evaluated on a dataset of diseased rice leaves for segmentation accuracy, computational efficiency, and robustness in real-world conditions. Results show that the U-Net with EfficientNetB7 and attention gates outperforms the other models, particularly for complex leaf images, achieving superior accuracy and generalization. This research provides a practical, real-time solution for early disease detection in rice, contributing to precision agriculture by helping reduce crop losses and optimize the use of agrochemicals, ultimately promoting sustainable crop management.

Self-correcting deep learning for estimating rice leaf nitrogen concentration with mobile phone images

As a pivotal role in crop development, the application of nitrogen fertilizers enhances yields, while excessive use poses environmental risks. Precision nitrogen management requires rapid crop nitrogen assessment in field conditions and mobile phone images can be a promising approach. However, few studies have investigated how arbitrary white balance and exposure value settings affect crop nitrogen diagnosis using phone photos. Therefore, a new deep learning framework: self-correcting leaf nitrogen concentration estimation network (SCLNC-Net), was proposed to explore the potential of mobile phone images for non-destructive nitrogen status monitoring. Imperfect camera metering and incorrect user operations were addressed through attention U-Net for automatic white balance and exposure correction. Then a lightweight deep learning algorithm MobileNetV3 was utilized to estimate rice leaf nitrogen concentration based on the self-corrected images. Compared with most deep learning models, SCLNC-Net has fewer parameters and higher computational efficiency, which is better suited for deployment on mobile platforms. The results revealed that SCLNC-Net enhanced image quality and acquired high accuracy in the estimation of rice leaf nitrogen concentration (R2 = 0.84, RMSE = 0.39 %, RRMSE = 13 %). Moreover, the robustness and effectiveness of the proposed SCLNC-Net remained excellent across various shooting angles, mobile phone types, and rice varieties. This study provides insights into rapid and cost-efficient nutrient assessment and precision nitrogen management.