Weather based forecasting of sterility mosaic disease in pigeonpea (Cajanu cajan) using machine learning techniques and hybrid models

RANJIT KUMAR PAUL; S VENNILA; SATISH KUMAR YADAV; M N BHAT; M KUMAR; P CHANDRA; A K PAUL; M PRABHAKAR

doi:10.56093/ijas.v90i10.107971

Authors

RANJIT KUMAR PAUL Senior Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
S VENNILA Principal Scientist, ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
SATISH KUMAR YADAV ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
M N BHAT Senior Research Fellow, ICAR-NCIPM
M KUMAR Senior Research Fellow, ICAR-NCIPM
P CHANDRA Senior Research Fellow, ICAR-NCIPM
A K PAUL Principal Scientist, ICAR-IASRI, New Delhi
M PRABHAKAR Principal Scientist, ICAR-CRIDA

https://doi.org/10.56093/ijas.v90i10.107971

Keywords:

ANN, ARIMA, Pigeonpea, SMD, SVR, Weather variables

Abstract

Modelling incidence of sterility mosaic disease (SMD) on pigeonpea [Cajanus cajan (L.) Millsp.] for four locations [S K Nagar (Gujarat), Gulbarga (Karnataka), Rahuri (Maharashtra) and Vamban (Tamil Nadu)] was carried out based on field data sets generated during six kharif seasons [2011-16]. Mean seasonal incidence amongst all locations was on the decline during recent periods (0.5-5.3%) over past decades (9.8-12.8%). Correlation analyses of SMD incidence with weather parameters lagged one and two weeks indicated spatial differences for the variables besides their significance. While Max T (ÂºC) lagged by one week alone was significantly positive with SMD at Gulbarga (KA), Vamban (TN) had negative significance of rainfall (mm/week) and rainy days. S K Nagar (GJ) and Rahuri (MH) had shown opposite effects of both morning and evening RH (%) of both one and two lagged weeks. Support vector regression (SVR), artificial neural network (ANN) models and their combination with autoregressive integrated moving average (ARIMA) models applied for prediction of SMD incidence across locations revealed performance of hybrid models in general to be better based on the evaluation criteria of root mean square error (RMSE). ARIMASVR> ARIMA-ANN>SVR>ANN was the order of prediction accuracies at S K Nagar (GJ), Gulbarga (KA), and Vamban (TN). At Rahuri (MH), individual models performed better over their hybrids with ARIMA. While application of hybrid model of SVR-ARIMA is applicable under situations of SMD seasonal mean severity exceeding 1%, SVR model proves better for mean seasonal disease incidence in decimal values less than one.

Downloads

Download data is not yet available.

References

Abhijit Daspute, Fakrudin B, Shivarudrappa, Bhairappanavar B, Kavil S P, Narayana Y D, Muniswamy, Anil Kaumar, Krishnaraj P U, Abid Yerimani, and Khadi B M. 2014. Inheritance of pigeonpea sterility mosaic disease resistance in pigeonpea. Plant Pathology Journal 30(2): 188–194. DOI: https://doi.org/10.5423/PPJ.NT.10.2013.0104

Arya P, Paul R K, Kumar A, Singh K N, Sivaramne N and Chaudhary P. 2015. Predicting pest population using weather variables: an ARIMAX time series framework. International Journal of Agriculture and Statistical Sciences 11: 381-386.

Awad M and Khanna R. 2015. Support Vector Regression. (In) Efficient Learning Machines. Apress, Berkeley, CA. DOI: https://doi.org/10.1007/978-1-4302-5990-9

Box G and Jenkins G. 1970. Time Series Analysis, Forecasting and Control. Holden-Day, San Francisco, CA.

Caselli M, Trizio L, Gennaro G D and Ielpo P. 2009. A simple feed forward neural network for the PM10 forecasting: comparison with a radial basis function network and a multivariate linear regression model, Water Air Soil Pollution. 201: 365–377. DOI: https://doi.org/10.1007/s11270-008-9950-2

Cheng B and Titterington D M. 1994. Neural networks: A review from statistical perspective. Statistical Science 9: 2-54. DOI: https://doi.org/10.1214/ss/1177010638

Chowdappa P.2010. Impact of climate change on fungal diseases of Horticultural crops. (In) Challenges of Climate Change-Indian Horticulture, pp 144-151. H P Singh, J P Singh and S S Lal (Eds). Westville publishing house, New Delhi.

Jones A T, Kumar P L, Saxena K B, Kulkarni N K, Muniyappa V and Waliyar F. 2004. Sterility mosaic disease-the ‘green plague’ of pigeonpea: advances in understanding the etiology, transmission and control of a major virus disease. Plant Disease 88: 436–445. DOI: https://doi.org/10.1094/PDIS.2004.88.5.436

Kaushik D, Srivastava S, Singh J P, Chauhan V B and Singh R N. 2013. Evaluation of pigeonpea genotypes against Sterility Mosaic Disease (SMD) caused by the mite vector, Aceria cajani. Journal of Mycopathological Research 51: 225-233.

Kumar P L, Jones A T and Waliyar F. 2008. Virus diseases of pigeonpea.( In) Characterization, Diagnosis and Management of Plant Viruses. Vegetable and Pulse Crops, 3, pp 235-258. Rao G P, Kumar P L and Holguin-Pena R J (Eds). Texas, USA: Studium Press.

Lakshmikantha B P and Prabhuswamy H P. 2002. Reaction of pigeon pea varieties to mite (Aceria cajani Channabasavanna) transmitting sterility mosaic disease. Plant Protection Bulletin 54: 6-7.

Li A, Liang S, Wang A and Qin J. 2007. Estimating crop yield from multi-temporal satellite data using multivariate regression and neural network techniques. Photogrammetric Engineering & Remote Sensing 73: 1149–1157. DOI: https://doi.org/10.14358/PERS.73.10.1149

Mitra D and Paul R K. 2017. Hybrid time-series models for forecasting agricultural commodity prices. Model Assisted Statistics and Applications 12: 255–264. DOI: https://doi.org/10.3233/MAS-170400

Nene Y L, Kannaiyan J and Reddy M V. 1981. Pigeonpea diseases: resistance-screening techniques. Information Bull. No.9. Patancheru, Andhra Pradesh, India: International Crops Research Institute for the Semi-Arid Tropics, p 19.

Paul R K and Das M K. 2010. Statistical modelling of inland fish production in India. Journal of Inland Fisheries Society of India 42: 1-7.

Paul R K, Alam W and Paul A K. 2014a. Prospects of livestock and dairy production in India under time series framework. Indian Journal of Animal Sciences 84:130-134.

Paul R K, Ghosh H and Prajneshu. 2014b. Development of out-of-sample forecast formulae for ARIMAX-GARCH model and their application. Journal of the Indian Society of Agricultural Statistics 68: 85-92.

Paul R K, Prajneshu and Ghosh H. 2013. Statistical modelling for forecasting of wheat yield based on weather variables. Indian Journal of Agricultural Sciences 83:180-183.

Paul R K, Vennila S, Singh N, Chandra P, Yadav S K, Sharma O P, Sharma V K, Nisar S, Bhat M N, Rao, M S and Prabhakar M. 2018. Seasonal dynamics of sterility mosaic of pigeonpea and its prediction using statistical models for Banaskantha region of Gujarat, India. Journal of the Indian Society of Agricultural Statistics 72: 213-223.

Paul R K and Sinha K. 2016. Forecasting crop yield:a comparative assessment of ARIMAX and NARX model. RASHI 1: 77-85.

R Core Team. 2013. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL http://www.R-project.org/.

Reddy M V, Rayu T N and lanne J M. 1998. Diseases of Pigeonpea. (In) The Pathology of Food Pasture Leguenes, pp 517-58. Allen D J. and lenne J M (eds). Wallingford oxfordshire: CAB International.

Stenseth N C, Mysterud A, Ottersen G, Hurrell J W, Chan K S and Lima M. 2002. Ecological effects of climate fluctuations. Science 297: 1292-1296. DOI: https://doi.org/10.1126/science.1071281

Van Der Maesen L J G. 1990. Pigeonpea: Origin, history, evolution and taxonomy. (In) The Pigeonpea, pp 15-46. Nene Y L, Hall S D, and Sheila V K (Eds). CAB International, Wallingford, UK.

Vapnik V N. 2000. The Nature of Statistical Learning Theory. Springer-Verlag, New York. DOI: https://doi.org/10.1007/978-1-4757-3264-1

Zhang G, Patuwo B and Hu M Y. 1998. Forecasting with artificial neural networks: the state of the art. International Journal of Forecasting 14:35-62. DOI: https://doi.org/10.1016/S0169-2070(97)00044-7

Zhang G P. 2013. Time series for coming using a hybrid ARIMA and neural network model. Neuro computing 50: 159-175. DOI: https://doi.org/10.1016/S0925-2312(01)00702-0