Dynamic Prediction of Chilo suppressalis Occurrence in Rice Based on Deep Learning

(1) Background: The striped rice stem borer (SRSB), Chilo suppressalis, has severely diminished the yield and quality of rice in China. A timely and accurate prediction of the rice pest population can facilitate the designation of a pest control strategy. (2) Methods: In this study, we applied multiple linear regression (MLR), gradient boosting decision tree (GBDT), and deep auto-regressive (DeepAR) models in the dynamic prediction of the SRSB population occurrence during the crop season from 2000 to 2020 in Hunan province, China, by using weather factors and time series of related pests. (3) Results: This research demonstrated the potential of the deep learning method used in integrated pest management through the qualitative and quantitative evaluation of a reasonable validating dataset (the average coefficient of determination Rmean2 for the DeepAR, GBDT, and MLR models were 0.952, 0.500, and 0.166, respectively). (4) Conclusions: The DeepAR model with integrated ground-based meteorological variables, time series of related pests, and time features achieved the most accurate dynamic forecasting of the population occurrence quantity of SRSB as compared with MLR and GBDT.

The Use of Jayanti (Sesbania Sesban) Molluscicide in Overcoming Golden Snail, Pest Of Rice Plant in The Village of Bunut Baok, Central Lombok

As a result of the attack golden snails, rice production declined to 30 % in some places in the province of West Nusa Tenggara. Application of science and technology activities for the community ( IbM ) to address the problem of golden snail pest have been conducted in The Village of Bunut Baok, Central Lombok. IbM program conducted by subject matter covers characteristics of jayanti plant (Sesbania sesban ) and its cultivation method, characteristics of golden snail species that is pests of the rice plant, how to prepare and manufacture of jayanti molluscicide, and its application to control rice pest snails. The methods used include lecture, discussion, demonstration and practice. IbM activity followed by 12 members of Farmers Group Mohon Petunjuk Bunut Baok Village. The results of the practice is that the use of 1 ppm solution jayanti leaf can be lethal 48% to 84% of golden snail population. Other results achieved are covering the growing appreciation of farmers to plant jayanti, increasing farmers' knowledge and skills in identifying plants jayanti, skilled to make jayanti molluscicide, and its use to control rice pest golden snails.

Dynamic analysis and control of a rice-pest system under transcritical bifurcations

World-wide rice consummation constantly grows constantly with non-proportional yield as large amounts of rice are lost due to pest infestations. Cultural methods were widely applied at an early stage of agricultural pest management but then replaced over time through insecticides. To describe a rice-pest system and to control the corresponding pests applying cultural methods and/or insecticides, statistical analyses have been used, and also other mathematical models using an Integrated Pest Management (IPM) strategy considering long time period and more parametric values. Considering the limitations of IPM, we have developed a mathematical model for a rice-pest system found in agricultural management. The mathematical model consists of two non-linear differential equations (NDEs) to illustrate the interrelation of rice and its corresponding agricultural pests. This model is extended to become an optimal control problem (minimization problem), considering both, cultural methods and pesticides, to minimize the density of agricultural pests and to increase the production of rice, reducing gross annual losses. Pesticides have been applied only in emergencies to reduce environmental pollution and damage to nearby ecosystems such as aquatic ecosystems, and a decision model has also been developed to mitigate potential risks. To compare the effectiveness of the considered controls, the ratio of annual production of rice is studied for both controls and without control. This study contributes to building a relationship between NDEs and agricultural management as well as connecting mathematically rice-pest relationships to global food security.

Interpretation of Agricultural Pest Problem Handling System in Usada Wisada Pari Scripture

The knowledge of cultivation and the methods of treating and solving pest problems naturally without neglecting the local culture has been an inseparable aspect of Balinese agricultural life, which is known for its irrigation system called subak. This study aims to examine agricultural scripture named Usada Wisada Pari from two perspectives. First, this study examines the types of pests and its countermeasure. Secondly, it is important to study the lexicon form of these pests. This study shows that the types of rice pests in the Usada Wisada Pari text are categorized into two types, namely animals and plants. The countermeasure consists of natural ritual elements from plants and incantations. Furthermore, this research also shows that all kinds of plague and agricultural pests, along with ways to overcome them, reflect the very strong Shivaistic teachings. All kinds of diseases, countermeasures and prevention are described as the authority of Lord Shiva as the god of destruction in the Hindu concept. It can be concluded that the scripture of Usada Wisada Pari is a text that provides knowledge about rice pest antidotes in an environmentally friendly and holistic manner because it involves natural and religious elements. This study is expected to contribute both to academics or future researchers as well as to the public. It is hoped that academics and researchers can use this present study as a source and expand as well as deepen the object of study based on ethnoagriculture. Meanwhile, the general public can increase their knowledge regarding alternative management of agricultural epidemics in synergy with nature and local wisdom.

Analysis on outsourcing service behavior of rice pest and disease control based on Heckman selection model—A case study of ten counties in Fujian Province

Under the background of relatively slow agricultural labor transfer and land circulation, agricultural production outsourcing has become the main means of agricultural modernization. In order to provide a beneficial perspective for appropriately expanding the scale of rice control outsourcing services, we investigated the situation of rice control outsourcing in ten counties of Fujian Province, and analyzed the factors influencing rice farmers’ decision-making and control degree by using Heckman model. First of all, the main factors affecting farmers’ participation in outsourcing are agricultural labor force, whether family members are cooperative members, planting area, proportion of grain income, degree of organization of outsourcing team, region and so on. Secondly, agricultural labor force, cooperative members, planting area, part-time behavior, mechanical efficiency of prevention and control organization, and region are the main factors affecting the scale of control outsourcing. Thirdly, from a regional perspective, the rice farmers in northern and Western Fujian are more dependent on outsourcing services consumption compared with the rice farmers in Southern Fujian. These results have a clear impact on policymakers, indicating that policy and measures should encourage the prevention and control of the nature of cooperation, and improve the advanced nature of outsourcing facilities of plant protection equipment, thereby effectively improving the professional level of rice pest and disease control.

Convolutional Rebalancing Network for the Classification of Large Imbalanced Rice Pest and Disease Datasets in the Field

The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classification model. This paper proposes a novel convolutional rebalancing network to classify rice pests and diseases from image datasets collected in the field. To improve the classification performance, the proposed network includes a convolutional rebalancing module, an image augmentation module, and a feature fusion module. In the convolutional rebalancing module, instance-balanced sampling is used to extract features of the images in the rice pest and disease dataset, while reversed sampling is used to improve feature extraction of the categories with fewer images in the dataset. Building on the convolutional rebalancing module, we design an image augmentation module to augment the training data effectively. To further enhance the classification performance, a feature fusion module fuses the image features learned by the convolutional rebalancing module and ensures that the feature extraction of the imbalanced dataset is more comprehensive. Extensive experiments in the large-scale imbalanced dataset of rice pests and diseases (18,391 images), publicly available plant image datasets (Flavia, Swedish Leaf, and UCI Leaf) and pest image datasets (SMALL and IP102) verify the robustness of the proposed network, and the results demonstrate its superior performance over state-of-the-art methods, with an accuracy of 97.58% on rice pest and disease image dataset. We conclude that the proposed network can provide an important tool for the intelligent control of rice pests and diseases in the field.

Diversity Of Insect Pests In Rice Plant (Oryza Sativa L) in The Rice Fields Of South Kualuh District, North Labuhanbatu

Eradicating rice pests in South Kualuh is difficult to do optimally, because most farmers do not understand the types of pests that attack their rice plants. The objective of this study was to obtain information about the type of pest insects in rice plants and to find out the diversity index of insect pests in rice plants. This research was conducted using trap method and collection of insects was done using a insect net. Observation data was analised using Shanon Wiener (H) diversity / diversity index. The result showed 13 types of pest insects which belongs to 10 families. That is Tettigonia sp.(Linnaeus, 1758), Sogatella furcifera (Horváth, 1899), Nephotettix virescens (Distant, 1908), Cofana spectra (Distant, 1908), Atractomorpha crenulata (Fabricius, 1793), Erotides sp.(Laporte, 1836), Leptocorisa acuta (Thunberg, 1783), Aulacophora indica (Gmelin, 1790), Chrysochus cobaltinus (LeConte, 1857), Silba capsicarum (McAlpine, 1956), Hercostomus germanus (Wiedemann, 1817), Cnaphalocrosis medinalis (Guenée, 1854), Scirpophaga incertulas (Walker, 1863). The diversity index of rice pest insects was categorized as moderate with a value of 2,35 and a dominance index of 0,108. This value indicates that the distribution of species is evenly distributed so that no insect species dominates in the area.

Comparison of morphology, development and expression patterns of hsf and hsp11.0 of Cotesia chilonis under normal and high temperature

Cotesia chilonis (Munakata) is the dominant parasitic wasp of the rice pest, Chilo suppressalis (Walker), and is a valuable parasitic wasp for the prevention and control of C. suppressalis. In this study, developmental indicators and expression of Cchsp11.0 (heat shock protein 11.0) and Cchsf (heat shock factor) were compared for C. chilonis at 27 °C and 36 °C. Developmental duration, morphology, emergence rate, and number of C. chilonis offspring were shortened at 36 °C while the ratio of females to males increased. Cchsp11.0 and Cchsf were highly expressed in the 1st instar stage at 36 °C, and Cchsp11.0 expression gradually decreased as C. chilonis matured; Cchsf expression was not correlated with Cchsp11.0 expression. Compared with 27 °C, the expression pattern of Cchsp11.0 and Cchsf was also not consistent, and Cchsp11.0 expression increased significantly at the adult stage. In conclusion, mildly high temperatures impact growth, development and reproduction of C. chilonis and stimulate the expression of Cchsp11.0 and Cchsf, and Cchsp11.0 and Cchsf play different roles in different developmental stages of C. chilonis at normal and high temperature.

Classification of Level of Rice Pest Incidence Based on Weather Information

Aims: To classify the rice pest data based on the weather attributes using a machine learning approach, a decision tree classifier, and to validate the performance results with other existing techniques through comparison. Design: Rice pest classification using C5.0 algorithm Methodology: We collected rice pest data from the crop fields of various regions in the state of Maharashtra of India. The dataset contains the name of the region (Taluk), period (week), pest data, temperature, rainfall, and relative humidity. The data is collected from 39 taluks within four districts in different weeks of the year of 2013-2014. The weather information plays a vital role in this rice pest data analysis, because based on the weather, pest infestation varies in all the regions. The pests considered in this research are Yellow Stem borer, Gall midge, Leaf folder, and Planthopper. The collected dataset is given as input to the classifier, where 75% of data from the dataset is used for training, and 25% of data are used for testing the classifier. Results: The proposed C5.0 algorithm performed better in the classification of rice pest dataset based on weather attributes. The C5.0 algorithm achieved 88.99% accuracy, 78.81% sensitivity, and 89.11% specificity, which are higher in performance when compared with other techniques. Compared with the other different methods, the C5.0 algorithm achieved 1.3 to 8.5% improved accuracy, 2.4 to 9% improved sensitivity, and 0.8 to 7.8% improved specificity. Conclusion: Early detection of pest and pest based diseases is an essential process to avoid major crop losses. The proposed classification model is designed to classify the level of pest infestations based on weather attributes, as level of infestations caused by the rice pest varies based on weather conditions. The C5.0 algorithm classified the rice pest data based on the weather attributes in the dataset.