Challenges in Predicting Pesticide Consumption on a Global Scale Using Machine Learning

• Bruna Capistrano Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Luma Chen Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Matheus Ribeiro Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Carla Pacheco Pontifical Catholic University of Rio de Janeiro (PUC-Rio)
• Dacy Lobosco Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• João Quadros Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)
• Maria Izabel Barreto Petrobras Biocombustível
• Eduardo Ogasawara Federal Center for Technological Education of Rio de Janeiro (CEFET/RJ)

DOI: https://doi.org/10.5753/bresci.2023.233831

Abstract

The consumption of pesticides is relevant to agribusiness, government, and society on a global scale. Such consumption is a fundamental input in the food production chain and an important indicator for monitoring the levels of poisoning and residues that degrade the environment. Analyzing pesticide consumption on a global scale over time is a major challenge, as the available data are annual and recent. This work explores different ways to optimize the construction of prediction models, using different approaches through paired combinations between data pre-processing and machine learning methods. These approaches were evaluated to obtain predictions based on real data on pesticides in the top ten countries that consume them. The results showed that using machine learning models with satisfactory performance is difficult to obtain, considering this scenario of very small data and, at the same time, peculiar according to the country.

Keywords: Pesticides, Prediction, Time series, Arima, Machine learning

References

Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control. John Wiley & Sons.

Esling, P. and Agon, C. (2012). Time-series data mining. ACM Computing Surveys, 45(1).

FAO (2022).Food and Agriculture Organization of the United Nations.Technical report, http://www.fao.org.

Gomes, H. d. O., Menezes, J., da Costa, J., Coutinho, H., Teixeira, R., and do Nascimento, R. (2020). A socio-environmental perspective on pesticide use and food production. Ecotoxicology and Environmental Safety, 197.

Han, J., Kamber, M., and Pei, J. (2012). Data Mining: Concepts and Techniques.

Huang, G.-B., Zhou, H., Ding, X., and Zhang, R. (2012). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 42(2):513–529.

Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.

Júnior, D. d. O. S., Oliveira, J. d., and Neto, P. d. M. (2019). An intelligent hybridization of ARIMA with machine learning models for time series forecasting. Knowledge-Based Systems, 175:72–86.

Kitchin, R. and Lauriault, T. (2015). Small data in the era of big data. GeoJournal, 80(4):463–475.

Lee, G.-H. and Choi, K.-C. (2020). Adverse effects of pesticides on the functions of immune system. Comparative Biochemistry and Physiology Part - C: Toxicology and Pharmacology, 235.

Lindemann, B., Müller, T., Vietz, H., Jazdi, N., and Weyrich, M. (2021). A survey on long short-term memory networks for time series prediction. In Procedia CIRP, volume 99, pages 650–655.

Rao, C., Rahul, M., Dasgupta, S., and Hegde, R. (2021). Sustainable Pesticide usage in Agriculture. In 2021 IEEE Mysore Sub Section International Conference, MysuruCon 2021, pages 628–633.

Salles, R., Belloze, K., Porto, F., Gonzalez, P., and Ogasawara, E. (2019). Nonstationary time series transformation methods: An experimental review. Knowledge-Based Systems, 164:274– 291.

Shumway, R. H. and Stoffer, D. S. (2017). Time Series Analysis and Its Applications: With R Examples. Springer, New York, NY, 4 edition.

Siami-Namini, S., Tavakoli, N., and Siami Namin, A. (2019). A Comparison of ARIMA and LSTM in Forecasting Time Series. In Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, pages 1394–1401.

Tilman, D., Cassman, K., Matson, P., Naylor, R., and Polasky, S. (2002). Agricultural sustainability and intensive production practices. Nature, 418(6898):671–677.

Tsay, R. S. (2010). Analysis of Financial Time Series. Wiley, Cambridge, Mass, 3 edition.

Yu, W., Han, X., Wang, Y., and Yang, J. (2020). Prediction of pesticide residues in agricultural products based on time series model in Chengdu, China. In IOP Conference Series: Earth and Environmental Science, volume 594.