FORECASTING OF PESTICIDE USAGE IN PAKISTAN: AN APPLICATION OF THE UNIVARIATE ARIMA MODEL AND ARTIFICIAL NEURAL NETWORK
DOI:
https://doi.org/10.31413/nat.v13i1.18546
Palavras-chave:
ARIMA model, Artificial Neural Network (ANN), AIC, BIC, MSE, pesticides usageResumo
The agriculture sector is one of the important parts of an economy, and the production of crops is beneficial for a country or nation in earning profit. On the other hand, if insects or pests destroy the crops, it will badly influence the country's economy. The most widely exported crops in Pakistan are rice, wheat, and cotton. To save crops, appropriate pesticides should be used. Pesticides are chemical substances meant to kill pests and play a vital role in protecting crop productivity. The purpose of this study is to forecast the usage of pesticides in the agriculture sector for the safety of crops. The time series data from 1961 to 2017 is taken from FORCAST and analyzed using traditional ARIMA and artificial neural network (ANN) methodology. The results revealed that ANN can be suggested as the best among the two methods because it has the least mean square error (MSE). Furthermore, the predicted values through ANN are very close to actual values. It can be concluded that the use of Pesticides in Pakistan will increase in the upcoming years.
Keywords: ARIMA Model; pesticides usage; Artificial Neural Network (ANN); AIC; BIC; MSE.
Previsão do uso de pesticidas no Paquistão: uma aplicação do modelo ARIMA univariado e da rede neural artificial
RESUMO: O setor agrícola é uma das partes importantes de uma economia, e a produção de safras é benéfica para um país ou nação na obtenção de lucro. Por outro lado, se insetos ou pragas destruírem as safras, isso influenciará negativamente a economia do país. As safras mais exportadas no Paquistão são arroz, trigo e algodão. Para salvar as safras, pesticidas apropriados devem ser usados. Pesticidas são substâncias químicas que visam matar pragas e desempenham um papel vital na proteção da produtividade das safras. O objetivo deste estudo é prever o uso de pesticidas no setor agrícola para a segurança das safras. Os dados da série temporal de 1961 a 2017 foram retirados do FORCAST e analisados usando a metodologia tradicional ARIMA e rede neural artificial (ANN). Os resultados revelaram que a ANN pode ser sugerida como a melhor entre os dois métodos porque tem o menor erro quadrático médio (MSE). Além disso, os valores previstos por meio da ANN são muito próximos dos valores reais. Pode-se concluir que o uso de pesticidas no Paquistão aumentará nos próximos anos.
Palavras-chave: modelo ARIMA; uso de pesticidas; Rede Neural Artificial (RNA); AIC; BIC; MSE.
Referências
ADEWUMI, A. O.; AYO, C. K. Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction. Journal of Applied Mathematics, v. 2014, e614342, 2014. https://doi.org/10.1155/2014/614342
AFFAN, M. F.; ABDULLAH, A. G.; SURYA, W. Forecasting of wind speed using Exponential Smoothing and Artificial Neural Networks (ANN). Journal of Physics: Conference Series, v. 1402, n. 3, e033082, 2019. https://doi.org/10.1088/1742-6596/1402/3/033082
AKTAR, W.; SENGUPTA, D.; CHOWDHURY, A. Impact of pesticides use in agriculture: their benefits and hazards. Interdisciplinary Toxicology, v. 2, n. 1, p. 1-12, 2009. https://doi.org/10.1063/5.0193979
AL-FATTAH, S. M. Time series modeling for US natural gas forecasting. In: International Petroleum Technology Conference. Proceedings… Doha, Qatar, 2005. (Paper Number IPTC-10592-MS). https://doi.org/10.2523/IPTC-10592-MS
AMIN, M.; AMANULLAH, M.; AKBAR, A. Time series modeling for forecasting wheat production of Pakistan. The Journal of Animal & Plant Sciences, v. 24, n. 5, p. 1444-1451, 2014.
ASI, M. R.; HUSSAIN, A.; MUHMOOD, S. T. Solid phase extraction of pesticide residues in water samples: DDT and its metabolites. International Journal of Environmental Research, v. 2, n. 1, p. 43-48, 2008.
BADAR, N.; FATIMA, H.; JABBAR, A.; ASIF, M. Major food crops production and yield forecast in Pakistan. Pakistan Journal of Agricultural Research, v. 28, n. 3, p. 295-303, 2015.
BAKAR, N. A.; ROSBI, S. Autoregressive Integrated Moving Average (ARIMA) model for forecasting cryptocurrency exchange rate in high volatility environment: a new insight of bitcoin transaction. International Journal of Advanced Engineering Research and Science, v. 4, n. 11, p. 130-137, 2017. https://doi.org/10.22161/ijaers.4.11.20
BORKAR, P.; BODADE, V. M. Application of ARIMA Model for Forecasting Pulses Productivity in India. Journal of Agricultural Engineering and Food Technology, v. 4, n. 1, p. 22-26, 2017.
BOX, G. E. P.; JENKINS, G. M. Time Series Analysis: Forecasting and control. Rev. ed. San Francisco: Holden-Day, 1976. 575p.
BROWN, C. D.; BELLAMY, P. H.; DUBUS, I. G. Prediction of pesticide concentrations found in rivers in the UK. Pest Management Science: formerly Pesticide Science, v. 58, n. 4, p. 363-373, 2002. https://doi.org/10.1002/ps.466
BUÈS, R.; BUSSIÈRES, P.; DADOMO, M.; DUMAS, Y.; GARCIA-POMAR, M. I.; LYANNAZ, J. P. Assessing the environmental impacts of pesticides used on processing tomato crops. Agriculture, Ecosystems & Environment, v. 102, n. 2, p. 155-162, 2004. https://doi.org/10.1016/j.agee.2003.08.007
CHAI, T.; DRAXLER, R. R. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, v. 7, n. 3, p. 1247-1250, 2014. https://doi.org/10.5194/gmd-7-1247-2014
CROSS, P. Pesticide hazard trends in orchard fruit production in Great Britain from 1992 to 2008: a time‐series analysis. Pest Management Science, v. 69, n. 6, p. 768-774, 2013. https://doi.org/10.1002/ps.3436
CROSS, P.; EDWARDS-JONES, G. Variation in pesticide hazard from arable crop production in Great Britain from 1992 to 2008: an extended time-series analysis. Crop Protection, v. 30, n. 12, p. 1579-1585, 2011. https://doi.org/10.1016/j.cropro.2011.08.003
DAMALAS, C. A.; ELEFTHEROHORINOS, I. G. (2011). Pesticide Exposure, Safety Issues, and Risk Assessment Indicators. International Journal of Environmental Research and Public Health, v. 8, p. 1402-1419, 2011. https://doi.org/10.3390/ijerph8051402
DE SILVA, V. A.; SENANAYAKE, S. M.; DIAS, P.; HANWELLA, R. From pesticides to medicinal drugs: time series analyses of methods of self-harm in Sri Lanka. Bulletin of the World Health Organization, v. 90, p. 40-46, 2012.
DEVI, B. U.; SUNDAR, D.; ALLI, D. P. An effective time series analysis for stock trend prediction using ARIMA model for Nifty Midcap-50. International Journal of Data Mining & Knowledge Management Process, v. 3, n. 1, p. 65-78, 2013. https://doi.org/10.5121/ijdkp.2013.3106
DIN, M. A. ARIMA by Box Jenkins Methodology for Estimation and Forecasting Models in Higher Education. In: ATINER'S Conference. Paper Series… Athens, 2016. Paper EMS2015-1846. https://doi.org/10.13140/RG.2.1.1259.6888
FAISAL, F. Forecasting Bangladesh's Inflation Using Time Series ARIMA Models. World Review of Business. Research, v. 2, n. 3, p. 100-117, 2012.
HANKE, J. E.; WICHERN, D. W. Business Forecasting. 9th Ed. New Jersey: Pearson Education, Inc., 2009. 584p.
HIGLEY, L. G.; WINTERSTEEN, W. K. A novel approach to environmental risk assessment of pesticides as a basis for incorporating environmental costs into economic injury levels. American Entomologist, v. 38, n. 1, p. 34-39, 1992. https://doi.org/10.1093/ae/38.1.34
HO, S. L.; XIE, M.; GOH, T. N. A Comparative Study of Neural Network and Box-Jenkins ARIMA Modeling in time series prediction. Computers & Industrial Engineering, v. 42, p. 371-375, 2002. https://doi.org/10.1016/S0360-8352(02)00036-0
IORIATTI, C.; AGNELLO, A. M.; MARTINI, F.; KOVACH, J. Evaluation of the environmental impact of apple pest control strategies using pesticide risk indicators. Integrated Environmental Assessment and Management, v. 7, n. 4, p. 542-549, 2011. https://doi.org/10.1002/ieam.185
KHAN, M. J.; ZIA, M. S.; QASIM, M. Use of pesticides and their role in environmental pollution. International Scholarly and Scientific Research & Innovation, v. 4, n. 12, p. 85-91, 2010.
KHOOHARO, A. A.; MEMON, R. A.; MALLAH, M. U. An empirical analysis of pesticide marketing in Pakistan. Pakistan Economic and Social Review, v. 46, n. 1, p. 57-74, 2008.
KILLEEN, S. Development and use of environmental quality standards (EQSs) for priority pesticides. Pesticide Science, v. 49, n. 2, p. 191-195, 1997. https://doi.org/10.1002/(SICI)1096-9063(199702)49:2<191::AID-PS494>3.0.CO;2-K
KUMAR, A.; CORRELL, R.; GROCKE, S.; BAJET, C. Toxicity of selected pesticides to freshwater shrimp, Paratya australiensis (Decapoda: Atyidae): use of time series acute toxicity data to predict chronic lethality. Ecotoxicology and Environmental Safety, v. 73, n. 3, p. 360-369, 2010. https://doi.org/10.1016/j.ecoenv.2009.09.001
KUMAR, S.; SHARMA, A. K.; RAWAT, S. S.; JAIN, D. K.; GHOSH, S. Use of pesticides in agriculture and livestock animals and its impact on environment of India. Asian Journal of Environmental Science, v. 8, n. 1, p. 51-57, 2013.
MAHMOOD, A. Pests of Pesticides Trade. Dawn: The Business and Finance Weekly. Published at 2019, 19 August. Available on: https://www.dawn.com/news/1500249
MAKRIDAKIS, S., WHEELWRIGHT, S. C.; HYNDMAN, R.J. Forecasting: methods and applications. 3rd Ed. New Jersey: Wiley India Pvt. Limited, 2003. 656p.
MAZARI, R. B. FAOSTAT - latest data entry between 1998 and 2002. Available on: http://www.fao.org/3/af340e/af340e0g.htm
MEHMOOD, Q.; SIAL, M. H.; RIAZ, M.; SHAHEEN, N. Forecasting the production of sugarcane in Pakistan for the year 2018-2030, using Box-Jenkin’s methodology. The Journal of Animal & Plant Sciences, v. 29, n. 5, p. 1396-1401, 2019.
MONTGOMERY, D. C.; JENNINGS, C. L.; KULANCHI, M. (Eds.). Introduction to Time Series Analysis and Forecasting. New Jersey: Wiley Series in Probability and Statistics, 2008. 469p.
MUSA, Y.; JOSHUA, S. Analysis of ARIMA-Artificial Neural Network Hybrid model in forecasting of stock market returns. Asian Journal of Probability and Statistics, v. 6, n. 2, p. 42-53, 2020. https://doi.org/10.9734/ajpas/2020/v6i230157
NAFEES, M. J.; RASUL, M.; HIZBULLAH, K. “Pesticide Use in Swat Valley, Pakistan”. Mountain Research and Development, v. 28, n. 3, p. 201-204, 2008. https://doi.org/10.1659/mr d.1042
OKASHA, M. K.; YASEEN, A. A. Comparison between ARIMA Models and Artificial Neural Networks in Forecasting Al-Quds indicies of Palestine stock exchange market. In: Annual International Conference on Statistics and Modeling in Human and Social Sciences, 25. Proceedings… 2016. Cairo University: Faculty of Economics and Political Science, 2016. 23p.
PALOMARES-SALAS, J. C.; DE LA ROSA, J. J. G.; RAMIRO, J. G.; MELGAR, J.; AGUERA, A.; MORENO, A. ARIMA vs. Neural networks for wind speed forecasting. In: IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Proceedings… 2009. Hong Kong, China: IEEE, p. 129-133. https://doi.org/10.1109/CIMSA.2009.5069932
RASHID, S.; RASHID, W.; TULCAN, R. X. S.; HUANG, H. Use, exposure, and environmental impacts of pesticides in Pakistan: a critical review. Environmental Science and Pollution Research, v. 29, p. 43675-43689, 2022. https://doi.org/10.1007/s11356-022-20164-7
RIJAL, J. P.; REGMI, R.; GHIMIRE, R.; PURI, K. D.; GYAWALY, S.; POUDEL, S. Farmers’ knowledge on pesticide safety and pest management practices: a case study of vegetable growers in Chitwan, Nepal. Agriculture, v. 8, n. 1, e16, 2018. https://doi.org/10.3390/agriculture8010016
SAEED, N.; SAEED, A.; ZAKRIA, M.; BAJWA, T. M. Forecasting of Wheat Production in Pakistan using Arima Models. International Journal of Agriculture & Biology, v. 2, n. 4, p. 352–353, 2000.
SHOKRZADEH, M.; SARAVI, S. S. S. Pesticides in agricultural products: analysis, reduction, prevention. In: STOYTECHEVA, M. Pesticides: Formulations, Effects, Fate. London: IntechOpen, 2011. p. 226-242.
SOCORRO, J.; DURAND, A.; TEMIME-ROUSSEL, B.; GLIGOROVSKI, S.; WORTHAM, H.; QUIVET, E. The persistence of pesticides in atmospheric particulate phase: An emerging air quality issue. Scientific Reports, v. 6, n. 1, e33456, 2016. https://doi.org/10.1038/srep33456
STENRØD, M.; HEGGEN, H. E.; BOLLI, R. I.; EKLO, O. M. Testing and comparison of three pesticide risk indicator models under Norwegian conditions - a case study in the Skuterud and Heiabekken catchments. Agriculture, Ecosystems & Environment, v. 123, n. 1-3, p. 15-29, 2008. https://doi.org/10.1016/j.agee.2007.03.003
TARIQ, M. I.; AFZAL, S.; HUSSAIN, I.; SULTANA, N. Pesticides exposure in Pakistan: a review. Environment International, v. 33, n. 8, p. 1107-1122, 2007.
TSAY, R. S. Analysis of Financial Time Series. 3rd Ed. Hoboken. New Jersey: John Wiley & Sons Inc., 2010. 720p.
UTAILE, Y. U.; CROSS, P. Time-series analysis of variations in pesticide use and hazard from vegetable production in Great Britain. Journal of Hill Agriculture, v. 7, n. 1, p. 102-109, 2016. https://doi.org/10.5958/2230-7338.2016.00002.1
WHO_World Health Organization. Children's health and the environment - WHO training package for the health sector. 2008. Available on: https://www.who.int/ceh/capacity/Pesticides.pdf
WILSON, C.; TISDELL, C. Why farmers continue to use pesticides despite environmental, health and sustainability costs. In: Working Papers on Economics, Ecology and the Environment. 2000. 25p. (Working Paper, 53). Available on: https://ageconsearch.umn.edu/record/48363/?v=pdf
WILSON, C.; TISDELL, C. Why farmers continue to use pesticides despite environmental, health and sustainability costs. Ecological Economics, v. 39, n. 3, p. 449-462, 2001. https://doi.org/10.1016/S0921-8009(01)00238-5
YUSOF, N. M.; RASHID, R. S. A.; MOHAMED, Z. Malaysia crude oil production estimation: an application of ARIMA model. In: International Conference on Science and Social Research, CSSR. Proceedings… 2010. Kuala Lumpur, Malaysia, IEEE. p. 1255-1259. https://doi.org/10.1109/CSSR.2010.5773729
Downloads
Publicado
Edição
Seção
Licença
Copyright (c) 2025 Nativa
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial 4.0 International License.
Direitos Autorais para artigos publicados nesta revista são do autor, com direitos de primeira publicação para a revista. Em virtude de a aparecerem nesta revista de acesso público, os artigos são de uso gratuito, com atribuições próprias, em aplicações educacionais e não-comerciais.
A artigos publicados nessa revista, podem ser reproduzidos parcialmente ou utilizados como referência por outros autores, desde que seja cita a fonte, ou seja, a Revista Nativa.
Copyright for articles published in this journal are the authors, with first publication rights granted to the journal. The journal shows open access, and articles are free to use, with proper attribution, in educational and non-commercial.
The articles published in this journal may be reproduced in part or used as a reference by other authors, provided that the source is quoted.
