ARIMA timeseries forecast modeling for whitefly, Bemisia tabaci (Gennadius)
Keywords:
Auto-correlation, Auto-regressive, Augmented Dickey-Fuller test, Forecasting, Integrated, Moving averageAbstract
Farmers face numerous challenges in their efforts to enhance crop productivity, with adverse weather conditions and the prevalence of insectpests being primary factors. Among these pests, Bemisia tabaci (Gennadius) commonly referred to as the tobacco whitefly is of significant global concern due to its polyphagous nature. In pulse crops, this pest is particularly detrimental, serving as the sole vector of Yellow Mosaic Disease (YMD) caused by Begomo viruses in Vigna crops. The presence of B. tabaci can lead to substantial reductions in potential productivity, with severe infestations resulting in complete crop failure. To reduce yield losses from pest attacks, accurate forecasting of pest populations using historical data is crucial. In this study, an Auto regressive Integrated Moving Average (ARIMA) time-series model was employed to model and forecast whitefly populations. Stationarity of the data was confirmed via the Augmented Dickey-Fuller test, which was significant at 5%. Based on the Auto correlation Function (ACF) and Partial Auto Correlation Function (PACF), several ARIMA models were fitted, with the model parameters p=1, d=0, and q=6. Among the fitted models, ARIMA (1,0,2) was identified as the most suitable, based on the lowest σ² and Akaike Information Criterion (AIC) values.
References
Arya P, Paul RK, Kumar A, Singh KN, and Sivaramne N and Chaudhary P. 2015. Predicting pest population using weather variables: An ARIMAX time series framework. International Journal of Agricultural and Statistical Sciences 11(2): 381-386.
Bhagawati R, Bhagawati K, Jini D, Alone RA, Singh R, Chandra A, Makdoh B, Sen A, and Shukla KK. 2017. Review on climate change and its impact on agriculture of Arunachal Pradesh in the North eastern Himalayan region of India. Nature Environment and Pollution Technology 16(2): 535-539.
Boopathi T, Singh SB, Manju T, Ramakrishna Y, Akoijam RS, Chowdhury S, Singh NH and Ngachan SV. 2015. Development of Temporal Modeling for Forecasting and Prediction of the Incidence of Lychee, Tessaratoma papillosa (Hemiptera: Tessaratomidae), Using Time- Series (ARIMA) Analysis. Journal of Insect Science 15(1): 55.
Box GE, Jenkins GM, Reinsel GC, and Ljung GM. 2015. Time series analysis: fore casting and control, 5th Edition, John Wiley & Sons. Breiman L. 2001. Statistical Modeling: The two cultures (with comments and a rejoinder by the author). Statistical Science 16(3): 199-231.
Chandra A, Bhagawati K, Kalita H and Angami T. 2022. Weather-based fruit fly population dynamics prediction model for the mid-hills of Eastern Himalayan region of India. Current World Environment 17(3): 690-697.
Chandra A, Sujayanand GK and Kumar R. 2021. Influence of Sowing Dates and Host Crops on Population Incidence of Whitefly, Bemisia tabaci (Gennadius) in Greengram and Blackgram. National Academy Science Letters 44(5): 389–391.
Khudri NAFRS, MohdMasri MM, Maidin MST, Kamarudin N, Hussain MH, AbdGhani I and Jalinas J. 2021. Preliminary evaluation of acoustic sensors for early detection of red palm weevil, Rhynchophorus ferrugineus incidence on oil palm and coconut in Malaysia. International Journal of Tropical Insect Science 41(4): 3287-3292.
Kumar H, Chandra A, Deo MM and Bhagawati K. 2024. Weather variable selection for whitefly population prediction modeling by using backward elimination regression. Journal of Food Legumes 37(2): 205-210.
Kumar J, Choudhary AK, Gupta DS and Kumar S. 2019. Towards exploitation of adaptive traits for climateresilient smart pulses. International journal of molecular sciences 20(12): 2971.
Kumar N, Hashim M, Nath CP, Hazra KK and Singh AK. 2023. Pulses in conservation agriculture: An approach for sustainable crop production and soil health. Journal of Food Legumes 36(1): 1-9.
Liebhold AM, Rossi RE and Kemp WP. 1993. Geostatistics and geographic information systems in applied insect ecology. Annual Review of Entomology 38: 303–327.
Lin-Ya C, Dan JAR, Chen-Yi L and Ta-Te L.2019. Modelling and Forecasting of Greenhouse Whitefly Incidence using Time-Series and ARIMAX Analysis. IFAC Papers 52(30): 196–201.
Meyler A, Kenny G and Quinn T. 1998. Forecasting Irish inflation using ARIMA models. Central Bank and Financial Services Authority of Ireland Technical Paper Series (3): 1-48.
Montero-Manso P, Athanasopoulos G, Hyndman RJ and Talagala TS. 2020. FFORMA: Feature-based forecast model averaging. International Journal of Forecasting 36(1): 86-92.
Murguía-González J, Landero-Torres I, Leyva-Ovalle OR, Galindo Tovar ME, L larena-Hernández RC, Presa-Parra E and García Martínez MA. 2018. Efficacy and cost of trap-bait combinations for capturing Rhynchophorus palmarum L. (Coleoptera: Curculionidae) in ornamental palm polycultures. Neo tropical Entomology 47(2): 302-310.
Nene YL.1973. Control of Bemisia tabaci Genn., a vector of several plant viruses. Indian Journal of Agricultural Sciences 43: 433–436.
Nurhamidah N, Nusyirwan N and Faisol A. 2020. Forecasting seasonal time series data using the holtwinters exponential smoothing method of additive models. Journal MatematikaIntegratif 16(2): 151-157.
Pasaribu YP, Fitrianti H and Suryani DR. 2018. Rainfall forecast of merauke using autoregressive integrated moving average model. In: E3S Web of Conferences 73: p. 12010). EDP Sciences
Senf C, Seid R and Hostert P. 2017. Remote sensing of forest insect disturbances: Current state and future directions. International Journal of Applied Earth Observation and Geoinformation 60: 49- 60.
Singh DP. 1980. Inheritance of resistance to yellow mosaic virus in blackgram (Vigna mungo L.). Theoretical and Applied Genetics 52: 233-235.
Varma PM. 1952. Studies on the relationship of the Bhendi yellow vein mosaic virus and its vector, the whitefly (Bemisia tabaci Genn.). Indian Journal of Agricultural Sciences 22: 75–91.
Yadav RK, Chandra A, Parihar AK, Sujayanand GK, Kumar V, Bandi SM and Arya M. 2022. Escape resistance in fieldpea against Phytomyzahorticola Goureau, as influenced by sowing time and its correlation with plant metabolites. Pest Management in Horticultural Ecosystems 28(2): 119-128.
