Weather Based Pest Forewarning Model for Major Insect Pests of Rice – An Effective Way for Insect Pest Prediction

Manikandan, Narayanasamy; Kennedy, J. S.; Vellingiri, Geethalakshmi

doi:10.9734/arrb/2017/37365

Cited by 6 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predicting pest populations helps specify pest management strategies, reduce the use of pesticides, and is an integral part of the successful implementation of IPM. For pest prediction models, weather variables such as temperature, humidity, rainfall, and sunshine duration are often used as abiotic predictors in model development [8][9][10][11][12][13]26]. We found that TEMP [1,7], RH, and SDD were positively associated with the SRSB light trap catch, while AP and PRCP were negatively associated with the SRSB light trap catch.…”

Section: Discussionmentioning

confidence: 87%

“…The severe difficulty for statistical regression methods lies in choosing the relevant factor x; most researchers currently tend to build predicting models with relevant meteorological factors [9,10]. Some researchers have found that combining weather factors with other factors, such as variety, soil, fertilization, etc., can improve a model's prediction capability [11,12]. The statistical learning-based methods focusing on finding the linear relations between variables have high interpretability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Tan

Zheng

et al. 2021

Processes

View full text Add to dashboard Cite

(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.

show abstract

Section: Discussionmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 99%

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

Tan

Zheng

et al. 2021

Processes

View full text Add to dashboard Cite

show abstract

“…The whiteflies incidence in cotton was positively correlated with temperature (0.67516) where as thrips,rot andS. Litura by relative humidity (0.65793, 0.52732 and 0.24170) and rainfall on thrips and S. litura (0.37354 and 0.31510) (Selvaraj et al [10] and Lakshmi and Reddy, [11] but blight not have any correlation with weather parameters (Table 4). The relationship between castor pests and ambient weather parameters revealed minimum temperature, humidity, wind speed and wind direction were significant negative influence lepidopteran pest population according to Manjunatha, and his co workers [12].…”

Section: Discussionmentioning

confidence: 97%

Effect of Weather Parameters on of Pests and Diseases in Groundnut and Castor in Salem District of Tamil Nadu, India

Kanna,

Premalatha,

Kavitha

et al. 2023

IJECC

View full text Add to dashboard Cite

The roving survey on the incidence of pests and diseases in groundnut and castor was conducted from August, 2020 to March 2021 in Salem district at fortnight intervals revealed that, in groundnut , leaffolder (20.38%), cutworms S. litura (1.63/20 pls), thrips (10.69/20 pls), leaf spot (15.25%) and root rot (6.31%) , similarly in castor pests, whiteflies (23.06/20 pls), A. janata (8.38/20 pls), S. litura (10.19/ 20 pls), thrips (11.63 / 20 pls), C. punctiferalis (7.25/20 pls), alternaria blight (17.56%) and botrytis rot (4.19%) were found feeding /infecting on different parts of the crops. The correlation with weather parameters indicated, positive correlation of rainfall, relative humidity and wind speed on incidence of leaffolder (0.47998, 0.311421 and 0.339961) but rainfall and relative humidity increased root rot (0.433059 and 0.393255) whereas, maximum temperature influenced high infection of leafspot (0.67911) in groundnut. The whiteflies incidence in castor was positively correlated with (0.490967) and rainfall (0.389125) whereas, lepidopteran pests by relative humidity (0.61212) and rainfall (0.49415). The thrips and botrytis rot were influenced by relative humidity and rainfall rot (0.65914 and 0.77965, 0.57456 and 0.82709). But natural enemies in groundnut and castor had non-significant correlation with weather parameters.

show abstract

“…The correlation coefficient is calculated and the step down regression analysis to predict the development of tikka and rust one week before was formed considering weather as the major factor. Manikandan Narayanasamy et al [2] developed a pest forewarning model considering weather parameters using generalized linear model. To identify the effect of weather in the growth of pest and disease the correlation between the weekly average minimum and maximum temperature, relative humidity, sunshine hours and the weekly light traps of leaf folder, yellow stem borer, Brown plant hopper.…”

Section: Related Workmentioning

confidence: 99%

“…The number of diseased plant which is the percent of disease intensity and is calculated using the following formula. (2) where X represents the number of diseased plant in the experimental plot with respect to the disease severity scale which rates from 0 to 9. The influence of weather parameters on tikka and rust disease of groundnut in different sowing dates were observed and recorded with which the correlation and regression were calculated using the following formula.…”

Section: Source : Google Imagesmentioning

confidence: 99%

Predicting the Outbreak of Tikka and Rust in Grountnut (Arachis Hypogaea)

Mangala*,

Padmapriya

2020

IJRTE

View full text Add to dashboard Cite

Groundnut (Arachis hypogaea) is one among the most important oil seed crop cultivated in India. Tikka leaf spot and Rust are the major disease of groundnut that effects on production and productivity. The prediction was made based on factors such as minimum and maximum temperature, morning and evening humidity, wind speed, sunshine hours that quantifies the disease infestation in groundnut. The relationship between the weather, pest and disease infestation are identified which supports the model to predict the occurrence of the disease. The observations were recorded at an interval of one week from the occurrence of tikka and rust. The percent disease intensity is calculated based on the scale explained by Mayee and Data. The favourable climatic conditions for tikka and rust disease development ranges between 26OC – 31OC and 25OC – 30OC respectively, relative humidity greater than 85%, prolonged heavy rainfall, wind speed and rain. The rules are generated based on the recorded observation and the weather parameters. The main objective is to diagnose the existence of tikka and rust disease coupled with weather parameters.

show abstract

Weather Based Pest Forewarning Model for Major Insect Pests of Rice – An Effective Way for Insect Pest Prediction

Cited by 6 publications

References 0 publications

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

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

Effect of Weather Parameters on of Pests and Diseases in Groundnut and Castor in Salem District of Tamil Nadu, India

Predicting the Outbreak of Tikka and Rust in Grountnut (Arachis Hypogaea)

Contact Info

Product

Resources

About