Detection and Classification of Rice Infestation with Rice Leaf Folder (Cnaphalocrocis medinalis) Using Hyperspectral Imaging Techniques

The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.

COMPARATIVE TOXICITY OF SOME INSECTICIDES AGAINST RICE LEAF FOLDER (Cnaphalorosis medinalis) UNDER FIELD SITUATIONS

against Cnaphalorosis medinalis. Four synthetic insecticides were applied with three replicates at recommended dose rates. Toxicity trials were performed under RCBD. The results of the toxicity experiments disclosed the lowest mean leaf reduction damage (6.84%) after 14 days of 2nd spray by application of Flubendamide followed by Emmamectin Benzoate (15.03%). The damage was reduced 17.21-17.00% in case of Fibronil and 17.19-16.12% by Lambda cyhalothrin but was superior to untreated plots. The results of 1st spray revealed that the lowest mean leaf damage (12.24%) was noted in case of Flubendamide application among the tested insecticides. In case of yield analysis, the highest percent grain filling (92.34%) was examined in Belt insecticide trailed by Timer (87.12%), whereas the lowest (70.46%) was noted in case of control. Increase in yield (%) disclosed that the highest increase in yield (21.54%) was recorded in application of Belt insecticide, while relatively the lowest (10.23%) was observed in Boxer insecticide. Overall, the results depicted that the longest exposure period proved more effective as relative high reduction in leaf damage, and Flubendamide was the most effective among the all tested insecticides. Hence, this insecticide can be used in Intergrated Pest Management Program (IPM) for the successful management of C. medinalis. Keywords: Oryza sativa, insect pests, IPM, pest scouting, toxicity bioassays, efficacy.

Host plant resistance against yellow stem borer and rice leaf folder through varietal screening of rice

Rice plant is attacked by many insect-pests of which yellow stem borer (dead heart at vegetative stage and white ear head at reproductive stage) and leaf folder are considered as prime devastator, responsible for major economic loss. To combat this problem, resistant varieties of rice are required for better production as well as better productivity. Host plant resistance is very much effective in integrated pest management (IPM) system, where negligible pesticidal hazard is present as well as environmental safety, low cost farming by without or minimum pesticide application and proper identification of resistant varieties for selection as parent in crossing programme to develop resistant varieties in future. The 78 rice varieties were screened out against Scirpophaga incertulas (yellow stem borer) and Cnaphalocrocis medinalis (rice leaf folder) of rice during Kharif, 2010-2012 at Rice Research Station, Chinsurah, Hooghly, under Government of West Bengal. The experiment was carried out to determine the level of resistance in early, mid-early, medium and late duration rice varieties, and shallow and semi-deep rice varieties. The pest infestation level was determined by counting dead heart, white ear head and damaged/folded leaves. The experimental results revealed that the early duration variety viz. Narendra 97 and IR 50, the mid-early duration variety i.e. IR 64 and IET 17904 proved resistant against both yellow stem borer (dead heart) and leaf folder. The medium duration variety, Ranjit was highly resistant against both yellow stem borer (dead heart) and leaf folder, and the variety, Pratiksha showed a fair degree of resistance against both yellow stem borer and leaf folder; while Jarava, the late duration variety exhibited high degree resistance against yellow stem borer (dead heart and white ear head). Besides, the varieties, Sashi and Giri recorded very low level of infestation of both lepidopteran pests while shallow and semi-deep variety such as Sashi was also considered resistant against the noxious pests.

Plant density and water management effect to leaf folder and narrow brown spot severity in irrigated rice

Rice Leaf Folder and Narrow Brown Spot cause yield losses of rice production. Environmental factors are suggested effects the severity of them. This research was aimed to determine the effect of plant density and water management to the severity of these pest and disease in the agro ecosystem of irrigated paddy field. Research was conducted using Inpari 44 variety in Godean Sleman Yogyakarta, April to July 2020. Experimental design was randomized block design with 4 treatments and 4 replications. Treatments were plant density (high = 50 kg ha-1 and low = 25 kg ha-1) and water management (alternate wetting and drying/AWD, and continues flooding). Results showed that highest attack intensity of leaf folder (25%) was occurred in 42nd days after planting in high plant density with AWD. Meanwhile, highest severity of narrow brown spot (58%) was found in 63rd days after planting in plant with low density and continues flooding. High leaf folder attack intensity was caused by high plant density, but not effected by water management. At the other side, high severity of narrow brown spot was affected by water management, but not effected by plant density.