Exploring the Impact of Pesticide Usage on Crop Condition: A Causal Analysis of Agricultural Factors
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Human lifestyle is affected by the agricultural development in the last 12,000 years ago. The development of agriculture is one of the reasons that global population surged. To ensure sufficient food production for supporting human life, pesticides as a more effective and economical tools, are extensively used to enhance the yield quality and boost crop production. This study investigated the factors that affect crop production and whether the factors of pesticide usage are the most important factors in crop production using the dataset from Kaggle that provides information based on crops harvested by various farmers. Logistic regression is used to investigate the relationship between various factors and crop production. However, the logistic regression is unable to deal with predictors that are related to each other and identifying the greatest impact factor. Therefore, causal discovery is applied to address the above limitations. The result of causal discovery showed that crop condition is greatly impacted by the estimated insects count, where estimated insects count is affected by the factors of pesticide usage. This study enhances our understanding of the influence of pesticide usage on crop production and contributes to the progress of agricultural practices.
Abstract
Human lifestyle is affected by the agricultural development in the last 12,000 years ago. The development of agriculture is one of the reasons that global population surged. To ensure sufficient food production for supporting human life, pesticides as a more effective and economical tools, are extensively used to enhance the yield quality and boost crop production. This study investigated the factors that affect crop production and whether the factors of pesticide usage are the most important factors in crop production using the dataset from Kaggle that provides information based on crops harvested by various farmers. Logistic regression is used to investigate the relationship between various factors and crop production. However, the logistic regression is unable to deal with predictors that are related to each other and identifying the greatest impact factor. Therefore, causal discovery is applied to address the above limitations. The result of causal discovery showed that crop condition is greatly impacted by the estimated insects count, where estimated insects count is affected by the factors of pesticide usage. This study enhances our understanding of the influence of pesticide usage on crop production and contributes to the progress of agricultural practices.
참고문헌 (21)
- "The development of Agriculture" (2023)[URL]
- A. Sharma, "Worldwide pesticide usage and its impacts on ecosystem", SN Applied Sciences, 1, pp.1~16 (2019)
- I. Mahmood, "Effects of pesticides on environment", Plant, soil and microbes : Implications in Crop Science, 1, pp.253~269 (2016)
- F. P. Carvalho, "Agriculture, pesticides, food security and food safety", Environmental Science & Policy, 9(7-8), pp.685~692 (2006)
- P.C. Abhilash, "Pesticide use and application : an Indian scenario", Journal of Hazardous Materials, 165(1-3), pp.1~12 (2009)
- J.P.G. Webster, "Estimating the economic benefits of alternative pesticide usage scenarios : wheat production in the United Kingdom", Crop Protection, 18(2), pp.83~89 (1999)
- S. Rahman, "Farm-level pesticide use in Bangladesh : determinants and awareness", Agriculture, Ecosystems & Environment, 95(1), pp.241~252 (2003)
- T.N. Liliane, "Factors affecting yield of crops", Agronomy-climate change & food security, pp.9~ (2020)
- M. Lykogianni, "Do pesticides promote or hinder sustainability in agriculture? The challenge of sustainable use of pesticides in modern agriculture", Science of the Total Environment, 795, pp.148625~ (2021)
- A. Das, "Encyclopedia of Quality of Life and Well-Being Research", pp.1~2 (2021)
- A. Worster, "Understanding linear and logistic regression analyses", Canadian Journal of Emergency Medicine, 9(2), pp.111~113 (2007)
- J. Tolles, "Logistic regression : relating patient characteristics to outcomes", Jama, 316(5), pp.533~534 (2016)
- E. Kupek, "Beyond logistic regression: structural equations modelling for binary variables and its application to investigating unobserved confounders", BMC Medical Research Methodology, 6(1), pp.1~10 (2006)
- K.A. Bollen, "Handbook of causal analysis for social research", pp.301~328 (2013), Springer Dordrecht
- "AV JantaHack: Machine Learning in Agriculture" (2020)[URL]
- L. Metcalf, "Cybersecurity and applied mathematics", pp.43~65 (2016), Syngress
- O. Cokluk, "Logistic Regression : Concept and Application", Educational Sciences : Theory and Practice, 10(3), pp.1397~1407 (2010)
- C. Glymour, "Review of causal discovery methods based on graphical models", Frontiers in Genetics, 10, pp.524~ (2019)
- S. Shimizu, "A linear non-Gaussian acyclic model for causal discovery", Journal of Machine Learning Research, 7(10) (2006)
- S. Shimizu, "DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model", Journal of Machine Learning Research-JMLR, pp.1225~1248 (2011)
- "Causal Effect" (2023)[URL]