Leaf Blast Research Articles

Registration of a blast‐resistant premium medium‐grain rice germplasm Eclipse

AbstractEclipse (Reg. no. GP‐149, PI 701081) is a blast‐resistant and ‘Calrose’ type medium‐grain‐quality rice (Oryza sativa L.) germplasm that was developed by the USDA‐ARS Dale Bumpers National Rice Research Center, Stuttgart, AR. It was selected from a backcross between a blast‐resistant tropical japonica rice cultivar ‘Katy’ and a temperate japonica medium‐grain rice cultivar ‘M‐202’. Eclipse was evaluated in uniform regional rice nurseries in the southern United States during 2019–2020 and further characterized in Arkansas fields during 2020–2021. Blast resistance was determined under greenhouse and field conditions. Under greenhouse conditions, Eclipse was resistant to races IA45, IB1, IB49, IB54, IC17, IE1, IG1, and IH1, similar to that of Katy. Under naturally infected field conditions in Louisiana and Puerto Rico, Eclipse was resistant to leaf and panicle blast infections, similar to that of Katy. Eclipse has Pi‐ta and Ptr genes and lacks Pi‐b, Pi‐k, and Pi‐z. Eclipse is a semidwarf glabrous type of medium‐grain rice and has a low amylose content, similar to M‐202, and quality of Calrose rice. In the southern United States, Eclipse has an average height of 98.5 cm and yields 6,710 kg grain ha−1. It reaches 50% heading at 84 d after emergence with a lodging incidence of 28.5 and 59% head rice yield. Eclipse is useful for breeding for improving disease resistance and grain quality and can be used directly by rice growers for premium medium‐grain rice production.

Detection of Paddy Blast: An Image Processing Approach with Threshold based OTSU

If rice infections spread, the agricultural industry as well as the people who eat rice as their primary food grain suffer greatly from production and financial losses as well as food shortages. One of the deadliest diseases that can affect paddy plants at any stage of development and hinder the growth of rice plants is paddy leaf blast. Because the brown spot and the leaf blast have the same appearance but distinct shapes, it is quite difficult to distinguish between them. In this case, paddy leaf blast is detected using computer vision methods. But because of their resemblance to other spots and poor color channel selection, previous procedures are difficult, time-consuming, and poorly able to detect blasts. In this article, an effective and automated image analysis method has been proposed to identify paddy leaf blasts that can identify leaf blasts by utilizing various shapes. Additionally, the process minimized pointless data exploration and provided superior accuracy of 95.34 percent.

Integrated genetic analysis of leaf blast resistance in upland rice: QTL mapping, bulked segregant analysis and transcriptome sequencing.

Elite upland rice cultivars have the advantages of less water requirement along with high yield but are usually susceptible to various diseases. Rice blast caused by Magnaporthe oryzae is the most devastating disease in rice. Identification of new sources of resistance and the introgression of major resistance genes into elite cultivars are required for sustainable rice production. In this study, an upland rice genotype UR0803 was considered an emerging source of blast resistance. An F2 mapping population was developed from a cross between UR0803 and a local susceptible cultivar Lijiang Xintuan Heigu. The individuals from the F2 population were evaluated for leaf blast resistance in three trials 7 days after inoculation. Bulked segregant analysis (BSA) by high-throughput sequencing and SNP-index algorithm was performed to map the candidate region related to disease resistance trait. A major quantitative trait locus (QTL) for leaf blast resistance was identified on chromosome 11 in an interval of 1.61-Mb genomic region. The candidate region was further shortened to a 108.9-kb genomic region by genotyping the 955 individuals with 14 SNP markers. Transcriptome analysis was further performed between the resistant and susceptible parents, yielding a total of 5044 differentially expressed genes (DEGs). There were four DEGs in the candidate QTL region, of which, two (Os11g0700900 and Os11g0704000) were upregulated and the remaining (Os11g0702400 and Os11g0703600) were downregulated in the susceptible parent after inoculation. These novel candidate genes were functionally annotated to catalytic response against disease stimulus in cellular membranes. The results were further validated by a quantitative real-time PCR analysis. The fine-mapping of a novel QTL for blast resistance by integrative BSA mapping and transcriptome sequencing enhanced the genetic understanding of the mechanism of blast resistance in upland rice. The most suitable genotypes with resistance alleles would be useful genetic resources in rice blast resistance breeding.

Screening of Finger Millet (<em>Eleusine coracana</em>) Germplasm for the Blast Disease-Resistance in Sri Lanka

Finger millet is the third important cereal crop in Sri Lanka, mostly cultivated in rainfed uplands in dry and intermediate zones. Blast disease (leaf, finger, and neck blast) caused by Magnaporthe grisea is economically devastating to rice and finger millet worldwide. Host resistance is the most viable option for managing the disease as it is mainly grown in low-input systems. One hundred thirty-nine finger millet accessions collected from the Plant Genetic Resources Center in Sri Lanka were field screened for leaf blast disease in three seasons under artificial inoculation at the Field Crops Research and Development Institute at Mahailluppallama, Sri Lanka. The results revealed that almost all the tested accessions were susceptible to leaf blast at the early seedling stage. However, 5–6 weeks after sowing, the severity of leaf blast disease decreased drastically, and all the germplasm were resistant or moderately resistant. The finger blast and neck blast severity, scored under natural infection, was low under both high and low-density planting. Seven and 87 finger millet accessions consistently showed immune reactions for finger blast and neck blast, respectively. A negative correlation was observed between the days to flowering and blast disease. The early flowering accessions, namely, Ac12968 and Ac2384 from Jaffna, TVFM, 13-1, TVFM-04, and TVFM-02 from Killinochchi, showed a higher severity score for leaf, finger, and neck blast compared to other accessions. A significant positive correlation (P<0.05) was found between finger blast and neck blast, however, these two diseases did not show a significant correlation (P>0.05) with leaf blast.

Rice CO 53: A high yielding drought tolerant rice variety for drought prone districts of Tamil Nadu

Early duration drought tolerant rice culture CB 06803, a derivative of the cross PMK (R ) 3 x Norungan was released as Rice CO 53 during the year 2020 as an alternate variety for Anna(R)4, with 115 -120 days duration. It possesses desirable features like high yield, drought tolerance and better physiological efficiency. This culture with semi dwarf stature has efficient tillering capacity, long droopy panicles with a highly acceptable plant characters and is a replacement for the rice variety Anna (R) 4 due to its grain yield and pest and disease resistance. In the overall yield analysis, the culture CB06803 recorded an overall mean grain yield of 3718 kg/ha which was 12.19 per cent increase over TKM (R) 12 and 14.08 per cent over Anna (R) 4 under dry condition. Under semi dry condition, it recorded 3866 kg/ha with 18.40 per cent increase over TKM (R) 12 and 8.67 per cent over Anna (R) 4. It is moderately resistant to WBPH, leaf blast, neck blast, sheath rot, brown spot and RTD under artificial condition. It has white short bold rice with high milling percentage (69.6), head rice recovery (59.6%) and suitable for idly making. The culture, CB 06803 had better  agronomic efficiency than TKM (R)12 and Anna (R) 4 by recording more number of productive tillers per plant and grain yield under control and drought. The culture CB 06803 had better physiological efficiency under drought than TKM (R) 12 and Anna (R) 4  having higher RWC, total chlorophyll content, chlorophyll stability index, photosynthetic rate, stomatal conductance and photo chemical efficiency. The culture had higher proline content than TKM (R) 12 and was on par with Anna (R) 4. It had higher catalase activity than Anna (R) 4. CB 06803 had better physiological efficiency under drought by showing partial closure of stomata as that of Sahbagidhan. CO 53 with higher grain yield under drought, disease resistance and short bold grains and suitable for cultivation in drought prone districts of Tamil Nadu as direct seeded rainfed or semi dry rice ecosystem. Keywords: Rice CO 53, bold grain rice, short duration, drought tolerance

Ubiquitin-Specific Protease 2 (OsUBP2) Negatively Regulates Cell Death and Disease Resistance in Rice.

Lesion mimic mutants (LMMs) are great materials for studying programmed cell death and immune mechanisms in plants. Various mechanisms are involved in the phenotypes of different LMMs, but few studies have explored the mechanisms linking deubiquitination and LMMs in rice (Oryza sativa). Here, we identified a rice LMM, rust spots rice (rsr1), resulting from the mutation of a single recessive gene. This LMM has spontaneous reddish-brown spots on its leaves, and displays enhanced resistance to both fungal leaf blast (caused by Magnaporthe oryzae) and bacterial blight (caused by Xanthomonas oryzae pv. oryzae). Map-based cloning showed that the mutated gene in rsr1 encodes a Ubiquitin-Specific Protease 2 (OsUBP2). The mutation of OsUBP2 was shown to result in reactive oxygen species (ROS) accumulation, chloroplast structural defects, and programmed cell death, while the overexpression of OsUBP2 weakened rice resistance to leaf blast. OsUBP2 is therefore a negative regulator of immune processes and ROS production. OsUBP2 has deubiquitinating enzyme activity in vitro, and the enzyme active site includes a cysteine at the 234th residue. The ubiquitinated proteomics data of rsr1 and WT provide some possible target protein candidates for OsUBP2.

Genotypic and Phenotypic Selection of Newly Improved Putra Rice and the Correlations among Quantitative Traits

This experiment was conducted to genotypically and phenotypically select new rice lines pyramided with blast and bacterial leaf blight disease resistance genes after a marker-assisted backcross breeding programme. The inter-relationship among agro-morphological characteristics and their effect on yield was also studied. The polymorphic functional and microsatellite markers Xa21FR and pTA248 (Xa21), Xa13prom (xa13), RM21 (xa5), MP (Xa4), RM6836 (Pi2, Pi9 & Piz) and RM8225 (Piz) were first confirmed for the target genes. The selected markers were used for foreground selection of BC2F2 homozygous progenies with the target genes. Plants that had homozygous IRBB60 alleles for these markers were evaluated for their recovery of the recurrent parent genome. IRBB60 was used as the donor parent for bacterial blight resistance genes while Putra-1 served as a recipient/recurrent parent with background blast-resistance genes and high yield. After the foreground selection, 79 polymorphic simple sequence repeat markers identified from the marker polymorphism survey were used for marker-assisted background selection to determine the percentage recovery of the recurrent parent genome. In order to make a selection on a phenotypic basis, 14 agro-morphological traits were measured and recorded. The result obtained from the study showed that 16 lines received the seven resistance genes in sufficiently varied numbers and were selected. The distribution of yield per hectare showed that about 50% of the selected lines had yields as high as 5 t/ha and above. Some of the lines produced as high as 8.4 t/ha. These lines demonstrated the potential of recording uniform 8t/ha upon recombination at BC2F2. The study also indicated that the number of panicles per hill correlated strongly, significantly and positively with the number of tillers (r = 0.962 **), total grain weight per hill (r = 0.928 **) and yield per hectare (r = 0.927 **). It was concluded that the newly improved resistant lines which were selected have the capability to compete with Putra-1 in terms of its productivity and yield. The newly developed lines would be useful in future breeding programmes as donors for bacterial leaf blight and blast resistance genes. These lines are recommended for release to farmers in Malaysia and other rice-growing agro-ecologies for commercial cultivation.

Rice Leaf Diseases Classification Using Discriminative Fine Tuning and CLR on EfficientNet

Rice cultivation in Nepal is effect by many factors, one of the main factor is rice leaf diseases which limits the crops production. Image classification of rice leaf classify different rice leaf diseases. Image dataset of rice leaf diseases is taken from open source platform. Pre-processing of image is done which is followed by feature extraction and classification of images. This thesis presents image classification of rice leaf diseases into four classes, namely: Brown Spot, Healthy, Hispa, Leaf Blast using Convolutional Neural Network (CNN) architecture EfficicentNet-B0 and EfficicentNet-B3 based on fine-tuning with cyclical learning rate and based on discriminative fine-tuning. It is found that the test accuracy of EfficientNet-B0 is 81.96% and EfficientNet-B3 is 85.12% based on fine-tuning with cyclical learning rate and the test accuracy of EfficienNet-B0 is 83.99% and EfficientNet-B3 is 89.18% based on discriminative fine-tuning for 15 epochs. The results also conclude that the CNN architectures work better with discriminative fine-tuning than on fine-tuning with cyclical learning rate. The classification models of EfficicentNet-B0 and EfficicentNet-B3 are evaluated by recall, precision and F1-score metrics.

Summary of the worldwide available crop disease risk simulation studies that were driven by climate change scenarios and published during the past 20 years

AbstractHere, published crop disease risk simulations are summarized, which were driven by climate change scenarios on a timescale terminating between 2001 and 2100. Thirty different agricultural and horticultural crops were specifically considered. Wheat diseases (mainly leaf rust) were most often simulated, followed by rice diseases (mainly leaf blast), grapevine diseases (mainly downy mildew) and potato diseases (mainly late blight). Most simulations suggest that within the projection period simulated, crop disease risk will more often increase (86 simulations) than decrease (45 simulations) or remain similar (12 simulations). The majority of crop disease risk simulations focus on Europe and Brazil. For example, there is agreement across crop disease risk simulations that in Europe the risk of leaf rust of wheat will increase. In other cases, there is disagreement across crop disease risk simulations, for example, due to contemporary climatic differences of locations. Therefore, it is risky to extrapolate results across locations. Mitigation and adaptation methods should be more often integrated in the crop disease risk simulations in order to inform about potential methods to reduce disease risk in future.

Comparative performance of four CNN-based deep learning variants in detecting Hispa pest, two fungal diseases, and NPK deficiency symptoms of rice (Oryza sativa)

Crop production can be significantly increased if stresses are detected at the earliest possible time to facilitate the implementation of necessary mitigation measures. This present study aims to evaluate the comparative performance of the Convolutional Neural Network (CNN) and four pre-trained deep CNN models, for automatic and rapid detections of Hispa, brown spot, leaf blast, and NPK deficiency symptoms from public and real field images. Deep learning models were trained using different public and field datasets combinations. Best accuracy was achieved for mixed public and field datasets rather than solely field or solely public datasets, with VGG19 models achieving 91.8% accuracy. Relatively simple structured CNN was found to predict phosphate deficient leaves with better performance (96% accuracy) than the other four advanced models, while VGG16 performed better for leaf blast and N deficiency identification. Likewise, ResNet50 could be recommended among the five models for the Potassium deficient leaf identification, while for the Hispa pest, VGG19 outperforms the InceptionV3, ResNet50, and VGG16 models, and was slightly better than the basic CNN. The implication of the study is enormous considering practical application as it deals with the complex dataset of pest, disease and nutrient deficiency. This non-invasive way of detecting different stresses of rice could help farmers in practicing precision agriculture. The findings from this study could be used to develop a user-friendly interface for the rapid and inexpensive detection of diseases and nutrition status by farmers, in a non-destructive way. Similar to rice, various biotic and abiotic stress symptoms in other economic crops could also be captured and identified by deep learning algorithms.

Multi-Scale Features Fusion Convolutional Neural Networks for Rice Leaf Disease Identification

It is time-consuming and labor-intensive to detect rice diseases manually. The purpose of this research is to develop a convolutional neural networks (CNNs)-based system to automatically detect the diseased rice leaf infected with rice leaf blast, helminthosporium leaf blight, and bacterial leaf blight. The sizes of rice leaf spots vary with the severity of disease infection. A single model based CNN cannot effectively classify images, especially for images with objects of small size as well as multiple object scales, and complicated image background. In this research, a multiscale serial convolution neural network (MSSCNN) and a multiscale parallel convolution neural network (MSPCNN) are proposed to identify diseased rice leaf spots based on multi-modal fusion to extract different perception features and combine them to improve the performances obtained by using only one modality. Experimental results delineate that MSSCNN and MSPCNN can get better performance in identifying the diseased rice leaves. In MSPCNN, the features of tiny spots on diseased rice leaves can be completely preserved. MSPCNN can hence offer better performances than MSSCNN. Additionally, MSPCNN architecture is suitable for parallel computing environment.

Characterization of Six Partial Resistance Genes and One Quantitative Trait Locus to Blast Disease Using Near Isogenic Lines with a Susceptible Genetic Background of Indica Group Rice (Oryza sativa)

Seven near isogenic lines (NILs) for six partial blast-resistance genes— Pi35, pi21, Pi37(t)( Pi37-KRIL17), Pb1, and Pi34 (two: Pi34-Chubu32 and Pi34-Chugoku40, originating from different Japonica Group rice lines, ‘Chubu 32’ and ‘Chugoku 40’, respectively)—and one quantitative trait locus (QTL), PiPHL9, derived from Japonica Group line ‘Hokkai PL9’, were developed in rice ( Oryza sativa L.). These NILs have the genetic background of an Indica Group susceptible line ‘US-2’, which does not harbor complete resistance genes and can clarify the effects of partial resistance genes and the QTL. These NILs and US-2 were used to determine the effects of the partial resistance genes and the QTL based on the results of an inoculation test for leaf blast using international standard differential blast isolates in the young seedling stage and a natural infection test in the mature stage after heading at a blast field. The NILs produced mainly moderate reactions in the inoculation test and rarely exhibited “resistant” and “susceptible” reactions. Each of the partial resistance genes and the QTL had different effects in panicle blast. Two genes, Pi35 and Pb1, were the most effective with respect to resistance, followed by Pi37-KRIL17. Pi34-Chugoku40 was the weakest. The effects of pi21, Pi34-Chubu32, and PiPHL9 varied among cultivation seasons and could be easily affected by environmental conditions. This is the first report clarifying the effects of partial resistance genes without the major complete genes, which will be helpful for advanced genetic and pathological studies and as a source of genes for rice breeding. [Formula: see text] Copyright © 2022 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license .

Deep Learning Utilization in Agriculture: Detection of Rice Plant Diseases Using an Improved CNN Model.

Rice is considered one the most important plants globally because it is a source of food for over half the world’s population. Like other plants, rice is susceptible to diseases that may affect the quantity and quality of produce. It sometimes results in anywhere between 20–40% crop loss production. Early detection of these diseases can positively affect the harvest, and thus farmers would have to be knowledgeable about the various disease and how to identify them visually. Even then, it is an impossible task for farmers to survey the vast farmlands on a daily basis. Even if this is possible, it becomes a costly task that will, in turn, increases the price of rice for consumers. Machine learning algorithms fitted to drone technology combined with the Internet of Things (IoT) can offer a solution to this problem. In this paper, we propose a Deep Convolutional Neural Network (DCNN) transfer learning-based approach for the accurate detection and classification of rice leaf disease. The modified proposed approach includes a modified VGG19-based transfer learning method. The proposed modified system can accurately detect and diagnose six distinct classes: healthy, narrow brown spot, leaf scald, leaf blast, brown spot, and bacterial leaf blight. The highest average accuracy is 96.08% using the non-normalized augmented dataset. The corresponding precision, recall, specificity, and F1-score were 0.9620, 0.9617, 0.9921, and 0.9616, respectively. The proposed modified approach achieved significantly better results compared with similar approaches using the same dataset or similar-size datasets reported in the extant literature.

Participatory Evaluation of Rice Varieties for Specific Adaptation to Organic Conditions in Italy

Rice is the fourth most important crop in Italy with a growing area under organic management. We conducted a participatory evaluation of 21 rice cultivars (10 old, 10 modern and a mixture) in four organic/biodynamic farms, for two cropping seasons, to assess the extent of varieties × farms and varieties × years within farm interactions and farmers’ preferences. There were significant differences between farms and varieties, as well as large interactions between varieties and farms, particularly in the case of plant height and reactions to Fusarium fujikuroi Nirenberg (bakanae) and Magnaporthe oryzae B Cooke (leaf and neck blast), but also for grain yield. There were also large interactions between varieties and years, which resulted in considerable differences in stability among varieties with one of the old, one modern and the mixture combining high grain yield and stability. Farmers, regardless of gender, were able to visually identify the highest yielding varieties in a consistent way across years, and although accustomed to seeing uniform varieties, they scored the mixture higher than the mean. The results are discussed in the context of a decentralized-participatory breeding program, to serve the target population of heterogenous environments represented by organic and biodynamic farms.

Leaf blast, a new disease on Pennisetum sinese caused by Pyricularia pennisetigena in China.

Pennisetum sinese Roxb, named king grass or 'sugarcane grass', belonging to the Poaceae family, is widely cultivated in China because of its use for livestock feed, bioenergy, water-soil conservation and phytoremediation. In September 2018, leaf blast on P. sinese was observed in a pasture in Zhanjiang, Guangdong province (21.15°N, 110.30°E ). The lesions initially were round, water-soaked, oval or spindle-shaped, then later turned to typical eye-shaped, whitish in the center with brown-black necrotic borders surrounded by a yellow halo (Fig. S1). Almost all of plants were infected and most of the spots appeared on the blades in the lower part of the plants. The leaves gradually turned yellow and withered, which affected the growth and quality of the herbage. Diseased leaves were surface-sterilized with 75% ethanol for 30s, followed by 3% hydrogen peroxide solution for 3 mins, and rinsed three times with sterile water, then placed in a hermetic container with moistened filter paper, and kept at 21-24℃ to stimulate conidiogenesis. After conidiation, conidial suspensions were prepared with sterile water and evenly spread onto PDA, and incubated at 25 ℃ in the dark to collect single-spore isolates. Colonies on PDA were fuscous black with grey centers, broad white and flat. Conidiophores were solitary, erect, straight or curved, unbranched, medium brown, smooth, 2 septate, and sometimes up to 5 septate. Conidia with a protruding and truncating hilum on basal-cells were pyriform to obclavate, 2 septate, 22.2-28.8 × 7.1-9.6 μm ( 24.9±1.7 × 8.5±0.6 μm) (Fig S2). The internal transcribed spacer region (ITS), nrRNA gene large subunit (LSU), actin gene (ACT) and RNA polymerase II largest subunit gene (RPB2) were PCR amplified, and the amplicons were sequenced by Sangon Biotech (Shanghai) Co., Ltd. (ITS: OM294657, LSU: OM294656, ACT: OM304642, RPB2: OM304643). BLASTn result showed above 99% nucleotide identity with the ITS (KM484935 465/465 bp), LSU (MH412641 862/863 bp), ACT (XM_029891619 418/421 bp) and RPB2 (XM_029892603 894/898 bp) of Pyricularia pennisetigena strains. Maximum likelihood (ML) analysis based on ITS using MEGA revealed that the fungal isolate clustered in P. pennisetigena clade with 99% bootstrap support (Fig S3). Based on morpho-molecular criteria, the fungus was identified as P. pennisetigena (Klaubauf et al., 2014; Gómez Luciano et al, 2019; Wang et al., 2019). Four healthy leaves of a 2-month-old plant were surface disinfected, and 2 leaves were wounded with a sterile needle (3 wound sites each leaf), then one leaf was inoculated with 10 μl 105 conidia/ml suspension on each site, and on the other leaf, sterile water was used as the control inoculation. The similar inoculations were conducted on the other 2 unwounded leaves. Pathogenicity tests were repeated three times. Seven days later, all inoculated leaves (wounded and unwounded) showed typical symptoms, while no symptoms were observed with the controls on both the wounded and unwounded leaves. The same fungus was recovered and confirmed by morphology and the ITS and LSU sequences. P. pennisetigena is pathogenic on a wide range of Poaceae plants in Brazil, Japan, Mali, Philippines, United States, China (Klaubauf et al., 2014; Reges et al., 2016, Wang et al., 2019). Han et al (2020) reported bacterial leaf blast on king grass while this is first report of P. pennisetigena causing leaf blast. This finding is a warning to prevent and control of this disease and its infectivity to Poaceae plants.

Influence of weather variables on the incidence and development of rice leaf blast (Magnaporthe oryzae)​

Rice is the second largest grown cereal crop in the world and the most consumed main staple meal. The devastating nature of rice blast disease has resulted in large annual losses. Therefore, a pot experiment was conducted at Paddy Breeding Station, Tamil Nadu Agricultural University, Coimbatore, during Rabi seasons of 2018-19, 2019-20, 2020-21, and 2021-22, with the objective to investigate the possible role of weather variables on rice leaf blast. Research analysis performed through correlation and decision tree analysis was carried under R studio to study the relation between weather parameters and per cent disease index (PDI) of leaf blast. The results revealed that, morning dew point temperature (X4, r = 0.69** and 0.67**) and minimum temperature (X2, r = 0.68** and 0.65**) had higher negative correlation both in real time and in one week lead time (LT1W) respectively. Further, the decision tree analysis showed the combination of rainfall of 5.9 mm and minimum temperature less than 22.6 ºC helped achieve disease incidence of greater than 80 per cent. Thus, the occurrence and development of leaf blast are significantly influenced by the minimum temperature and dew point temperature with drizzling rainfall, and these weather variables can be employed for weather-based disease forewarning against rice leaf blast.

Integrated Approaches to Manage Leaf Blast Disease of Rice in Farmer's Field at Godawari, Lalitpur

Blast, caused by Pyricularia oryzae is the most important disease of rice (Oryza sativa) in Nepal. With the aim of finding effective control measures against leaf blast disease, an experiment was done in randomized complete block design with three replications in farmer's field at Godawari, during the main seasons of 2018 and 2019. Three plant extracts; commercially available Nimbecidine, leaf extract of Asuro and Titepati, two bio-control agent Trichoderma viride and Kisan Pseudomonas along with one fungicide Kasugamycin were used as treatments. First spray was given as a prophylactic spray at jointing stage and treatments were applied 3 times at 14 days interval. Disease scoring was done according to a 0–9 scale. The result concluded that application of 0.2% Kasugamycin, 2% stock solution of Titepati and 1% Trichoderma viride were produced highest percentage disease control among the treatments by 54.76%, 47.62% and 30.96% respectively. Similarly, 0.2% Kasugamycin, 1% Trichoderma and 2% solution of Titepati treated plot produces the highest yield 5.87 t/ha, 5.49 t/ha and 4.68 t/ha respectively. To reduce leaf blast and higher grain yield of rice, Kasugamycin is the first priority and Titepati is second and for bio control Trichoderma is suggested as alternate approaches.

KNM 1638 - A High Yielding Gall Midge Resistant Early Duration PJTSAU Rice (Oryza sativa L.) Variety Suitable for Telangana State

The promising high yielding rice genotype, KNM 1638 is a medium slender, early duration (120 –125 days) and photo insensitive culture with high yield potential (7356 kg ha-1) having resistance to gall midge and leaf blast, and moderately resistant to neck blast with better adaptability. This rice culture KNM 1638, a derivative of the cross JGL 11727×JGL 17004 was released through State Varietal Release Committee on the name of Kunaram Vari 2 for Telangana state during the year 2021 as an alternate variety to BPT 5204. It has semi-dwarf plant type with moderate tillering, semi-erect flag leaf, all plant parts green, semi-compact well exerted semi-erect attitude of branching panicle, straw-colored awn less grains and its grain classified as a translucent medium slender grain. In the overall performance, KNM 1638 recorded mean productivity of 7356 kg ha-1 in the eight years of trials with 12.8% increase over the check varieties. It has good grain, cooking and eating quality, and good marketing facility as quality-wise it recorded 63% head rice recovery and 21.47% amylose content with soft gel consistency and moderate gelatinization temperature. The rice variety, KNM 1638 is suitable for cultivation during kharif, late kharif and rabi seasons throughout Telangana State with higher yield, better pest and disease resistance and good cooking quality in comparison to the check varieties.

Automatic Rice Disease Detection and Assistance Framework Using Deep Learning and a Chatbot

Agriculture not only supplies food but is also a source of income for a vast population of the world. Paddy plants usually produce a brown-coloured husk on the top and their seed, after de-husking and processing, yields edible rice which is a major cereal food crop and staple food, and therefore, becomes the cornerstone of the food security for half the world’s people. However, with the increase in climate change and global warming, the quality and its production are highly degraded by the common diseases posed in rice plants due to bacteria and fungi (such as sheath rot, leaf blast, leaf smut, brown spot, and bacterial blight). Therefore, to accurately identify these diseases at an early stage, recently, recognition and classification of crop diseases is in burning demand. Hence, the present work proposes an automatic system in the form of a smartphone application (E-crop doctor) to detect diseases from paddy leaves which can also suggest pesticides to farmers. The application also has a chatbot named “docCrop” which provides 24 × 7 support to the farmers. The efficiency of the two most popular object detection algorithms (YOLOv3 tiny and YOLOv4 tiny) for smartphone applications was analysed for the detection of three diseases—brown spot, leaf blast, and hispa. The results reveal that YOLOv4 tiny achieved a mAP of 97.36% which is significantly higher by a margin of 17.59% than YOLOv3 tiny. Hence, YOLOv4 tiny is deployed for the development of the mobile application for use.

Effects of Image Dataset Configuration on the Accuracy of Rice Disease Recognition Based on Convolution Neural Network.

In recent years, the convolution neural network has been the most widely used deep learning algorithm in the field of plant disease diagnosis and has performed well in classification. However, in practice, there are still some specific issues that have not been paid adequate attention to. For instance, the same pathogen may cause similar or different symptoms when infecting plant leaves, while the same pathogen may cause similar or disparate symptoms on different parts of the plant. Therefore, questions come up naturally: should the images showing different symptoms of the same disease be in one class or two separate classes in the image database? Also, how will the different classification methods affect the results of image recognition? In this study, taking rice leaf blast and neck blast caused by Magnaporthe oryzae, and rice sheath blight caused by Rhizoctonia solani as examples, three experiments were designed to explore how database configuration affects recognition accuracy in recognizing different symptoms of the same disease on the same plant part, similar symptoms of the same disease on different parts, and different symptoms on different parts. The results suggested that when the symptoms of the same disease were the same or similar, no matter whether they were on the same plant part or not, training combined classes of these images can get better performance than training them separately. When the difference between symptoms was obvious, the classification was relatively easy, and both separate training and combined training could achieve relatively high recognition accuracy. The results also, to a certain extent, indicated that the greater the number of images in the training data set, the higher the average classification accuracy.