Forecasting rice blast disease severity using weather-dependent regression and time series models

A G Meena; C Gopalakrishnan; Santosh Ganapati Patil; A Kamalakannan; R Jagadeeswaran; N K Sathyamoorthy; S Manonmani

doi:10.14719/pst.4974

Authors

A G Meena Department of Plant Pathology, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0009-0009-0460-7663
C Gopalakrishnan Department of Plant Pathology, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0001-5019-2715
Santosh Ganapati Patil Agricultural Statistics, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0002-5370-3522
A Kamalakannan Department of Plant Pathology, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0002-9835-5808
R Jagadeeswaran Department of Soil Science, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0002-8658-9260
N K Sathyamoorthy Department of Agronomy, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0002-7296-4808
S Manonmani Department of Rice, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamil Nadu, India https://orcid.org/0000-0003-3532-3363

DOI:

https://doi.org/10.14719/pst.4974

Keywords:

Rice blast, Magnaporthe oryzae, Prediction, Stepwise regression, Multiple Linear Regression, ARIMA

Abstract

Rice (Oryza sativa) is a staple food crucial for food security and economic stability, especially in developing countries. However, rice cultivation faces significant challenges, with rice blast disease, caused by the fungal pathogen Magnaporthe oryzae, being one of the most severe threats, potentially leading to yield losses of up to 30 %. This study aims to develop and apply regression models, including stepwise regression, multiple linear regression (MLR) and ARIMA (Autoregressive Integrated Moving Average), to predict the severity of rice blast disease based on weather parameters. Weekly data over 7 years (2017-2023) were collected from the Paddy Breeding Station at Tamil Nadu Agricultural University, Coimbatore, encompassing various weather factors such as temperature, relative humidity, rainfall and solar radiation. Data pre-processing included handling missing values, detecting outliers and creating time-lagged variables. The study revealed distinct seasonal patterns in rice blast incidence, with peak occurrences observed from mid-November to late January. Among the regression models, the ARIMA model incorporating weather variables as external regressors demonstrated superior performance with an R-squared value of 0.92, compared to 0.55 for stepwise regression and 0.57 for MLR. Accurate predictions of rice blast outbreaks could enable farmers and agricultural managers to implement timely and targeted disease management strategies, reducing dependence on broad-spectrum fungicides and minimizing crop losses. This study contributes to data-driven agriculture and disease management, potentially leading to more effective, economically viable and environmentally sustainable rice cultivation practices.

Downloads

Download data is not yet available.

References

Muthayya S, Sugimoto JD, Montgomery S, Maberly GF. An overview of global rice production, supply, trade and consumption. Annals of the New York Academy of Sciences. 2014;1324:7-14. https://doi.org/10.1111/nyas.12540 PubMed: 25224455.

Mohanty S. Trends in global rice consumption. Rice Today. 2013;12:44-45.

Wilson RA, Talbot NJ. Under pressure: Investigating the biology of plant infection by Magnaporthe oryzae. Nature Reviews Microbiology. 2009;7:185-95. https://doi.org/10.1038/nrmicro2032 PubMed: 19219052.

Groth DE. Azoxystrobin rate and timing effects on rice yield and rice disease control. Agronomy Journal. 2006;98:389-94. https://doi.org/10.1094/PD-90-1055

Kumar A. Forewarning models for Alternaria blight in mustard (Brassica juncea) crop. Indian Journal of Agricultural Sciences. 2013;81:116-18. https://doi.org/10.54386/jam.v24i1.782.

Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture: A review. Sensors. 2018;18:2674. https://doi.org/10.3390/s18082674 PubMed: 30110960.

Nettleton DF, Katsantonis D, Kalaitzidis A, Sarafijanovic-Djukic N, Puigdollers P, Confalonieri R. Predicting rice blast disease: Machine learning versus process-based models. BMC Bioinformatics. 2019;20:514. https://doi.org/10.1186/s12859-019-3065-1 PubMed: 31640541.

Kim Y, Roh JH, Kim HY. Early forecasting of rice blast disease using long short-term memory recurrent neural networks. Sustainability. 2017;10:34. https://doi.org/10.3390/su10010034.

Bebber DP, Ramotowski MAT, Gurr SJ. Crop pests and pathogens move polewards in a warming world. Nature Climate Change. 2013;3:985-88. https://doi.org/10.1038/nclimate1990.

Hossain M, Ali MD, Hossain D. Occurrence of blast disease in rice in Bangladesh. American Journal of Agricultural Science. 2017;4:74-80. http://www.aascit.org/journal/ajas.

Stekhoven DJ, Buhlmann P. Miss_Forest--non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28(1):112-18. https://doi.org/10.1093/bioinformatics/btr597.

Akaike H. A new look at the statistical model identification. IEEE Transactions on Automatic Control. 1974;19(6):pp. 716-23. https:// doi.org/10.1109 /TAC. 1974. 1100705.

Liu ZY, Huang JF, Shi JJ, Tao RX, Zhou W, Zhang LL. Characterizing and estimating rice brown spot disease severity using stepwise regression, principal component regression and partial least-square regression. Journal of Zhejiang University Science B. 2007 Sep; 8(10):738-44. https://doi.org/10.1631/jzus.2007.B0738.

Neetoo H, Chuttur Y, Nazurally A, Takooree S, Mamode Ally N. Crop disease prediction using multiple linear regression modelling. International Conference on Soft Computing and its Engineering Applications. 2021;pp. 312-26. https://doi.org/10.1007/978-3-031-05767-0_25.

Hyndman RJ, Khandakar Y. Automatic time series forecasting: the forecast package for R. Journal of Statistical Software. 2008;27(1):1-22. https://doi.org/10.18637/jss.v027.i03

Ling AS, Darmesah G, Chong KP, Ho CM. Application of ARIMAX model to forecast weekly cocoa black pod disease incidence. Mathematics and Statistics. 2019;7(4):29-40. https://doi.org /10.13189/ms.2019.070705.

Pujol G, Iooss B, Janon A. With contributions from Laurent T. Package ‘sensitivity’. R Package Version 1.61. 2015. http://cran.nexr.com/web/packages/sensitivity/sensitivity.pdf

Wickham H, Chang W. ggplot2: Create elegant data visualisations using the grammar of graphics. Version 2.1. Journal of Statistical Software. 2016;189:1-89. https://doi.org/10.1007/978-3-319-24277-4.

Yohana JM, Yunxian Y. Analysis of seasonal pattern and variation of rice prices in Tanzania. Asian Journal of Agricultural Extension Economics and Sociology. 2019;37(3):1-10. https://doi.org/10.9734/ajaees/2019/v37i330267.

Rotem J, Aust HJ. The effect of ultraviolet and solar radiation and temperature on survival of fungal propagules. Journal of Phytopathology. 1991;133(1):76-84. https://doi.org/10.1111/j.1439-0434.1991.tb00139.x.

Sriwanna K. Weather-based rice blast disease forecasting. Computers and Electronics in Agriculture. 2022;193:106685. https://doi.org/10.1016/j.compag.2022.106685.

Greer CA, Webster RK. Occurrence, distribution, epidemiology, cultivar reaction and management of rice blast disease in California. Plant Disease. 2001;85(10):1096-102. https://doi.org/10.1094/PDIS.2001.85.10.1096.

Kirtphaiboon S, Humphries U, Khan A, Yusuf A. Model of rice blast disease under tropical climate conditions. Chaos Solitons and Fractals. 2021;143:110530. https://doi.org/10.1016/j.chaos.2020.110530.

Ali Y, Qin A, Aatif HM, Ijaz M, Khan AA, Ahmad S, et al. A stepwise multiple regression model to predict Fusarium wilt in lentil. Meteorological Applications. 2022;29. https://doi.org/10.1002/met.2088.

Fernandez-Gonzalez M, Rodríguez-Rajo FJ, Jato V, Aira MJ, Ribeiro H, Oliveira M, Abreu I. Forecasting ARIMA models for atmospheric vineyard pathogens in Galicia and Northern Portugal: Botrytis cinerea spores. Annals of Agricultural and Environmental Medicine. 2012;19:255-62. PubMed: 22742797.

Atugala DM, Deshappriya N. Effect of endophytic fungi on plant growth and blast disease incidence of two traditional rice varieties. Journal of the National Science Foundation of Sri Lanka. 2015;43(2). https://doi.org/10.4038/JNSFSR.V43I2.7945.

Pajor R, Falconer R, Hapca S, Otten W. Modelling and quantifying the effect of heterogeneity in soil physical conditions on fungal growth. Bio-geosciences. 2010;7(11):3731-40. https://doi.org/10.5194/bg-7-3731-2010.