The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

A study on identifying factors of poultry complex odor using machine learning models

기계학습 모형을 이용한 양계 복합 악취의 요인 파악에 대한 연구

  • Doyun Kim (Department of Information Statistics, Chungbuk National University) ;
  • Jaehoon Kim (Division of Disease Control Research Planning, Korea Disease Control and Prevention Agency) ;
  • Junsu Park (Animal Environment Division, National Institute of Animal Science) ;
  • Siyoung Seo (Animal Environment Division, National Institute of Animal Science) ;
  • Jaeeun Kim (Animal Environment Division, National Institute of Animal Science) ;
  • Byeong-jun Yang (General Affairs Division, National Institute of Animal Science) ;
  • Tae-Young Heo (Department of Information Statistics, Chungbuk National University)
  • 김도윤 (충북대학교 정보통계학과) ;
  • 김재훈 (질병관리청) ;
  • 박준수 (국립축산과학원 축산환경과) ;
  • 서시영 (국립축산과학원 축산환경과) ;
  • 김재은 (국립축산과학원 축산환경과) ;
  • 양병준 (국립축산과학원 운영지원과) ;
  • 허태영 (충북대학교 정보통계학과)
  • Received : 2024.01.10
  • Accepted : 2024.04.02
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of modern society, the number of livestock is increasing, and the corresponding odor is recognized as a serious social problem. In particular, the consumption of poultry meat, such as chicken, duck, and turkey, is expected to rise steeply, making odor problems near poultry farms. To address the problem, it is important to understand the influence of odor components on the complex odor. In this study, the odor data obtained from poultry farms were used to predict the complex odor using machine learning models and analyze the influence of the components. Furthermore, we analyze the differences in the amount of the odor components at the site boundary, compost site, inside the farm, and outside the farm using analysis of variance. The analysis showed that ammonia, trimethylamine, dimethyldisulfide, and acetaldehyde have a high effect on the complex odor. In particular, ammonia, trimethylamine, and acetaldehyde have different amount of the occurence by the location.

현대 사회로 발전함에 따라 가축의 수가 증가하고 있으며, 악취는 심각한 사회 문제로 인식되어 지고 있다. 특히, 닭, 오리 및 칠면조와 같은 가금류 고기들의 소비량은 가파른 상승세를 보이고 양계축사 근처에서 악취 문제가 두각을 보인다. 악취 문제를 해결하기 위해, 악취 구성 인자들의 복합 악취에 대한 영향력을 파악하는 것이 중요하다. 본 연구에선 양계 농장에서 얻어진 복합 악취 데이터를 기계 학습 모형을 이용하여 복합 악취를 예측하고 복합 악취에 구성 인자들이 어떠한 영향을 주는 지 분석하였다. 추가적으로, 분산분석을 이용하여 부지경계, 퇴비장, 계사내부, 계사외부에서의 주요 악취 구성 인자들의 농도 차이를 분석하였다. 분석 결과, 복합 악취에 큰 영향을 미치는 구성 인자들로는 암모니아, 트라이메틸아민, 다이메틸다이설파이드, 아세트알데하이드로 나타났다. 특히, 암모니아, 트라이메틸아민, 아세트알데하이드는 양계 위치별로 농도의 차이가 있는 것으로 나타났다.

Keywords

Acknowledgement

본 결과물은 농림축산식품부 및 과학기술정보통신부, 농촌진흥청의 재원으로 농림식품기술기획평가원과 재단법인 스마트팜연구개발사업단의 스마트팜다부처패키지혁신기술개발사업의 지원을 받아 연구되었음 (421020-03).

References

  1. Cangialosi F, Bruno E, and De Santis G (2021). Application of machine learning for fenceline monitoring of odor classes and concentrations at a wastewater treatment plant, Sensors, 21, 4716.
  2. Hidayat R and Wang ZH (2021). Odor classification in cattle ranch based on electronic nose, International Journal of Data Science, 2, 104-111. https://doi.org/10.18517/ijods.2.2.104-111.2021
  3. Jang YN and Jung MW (2018). Biochemical changes and biological origin of key odor compound generations in pig slurry during indoor storage periods: A pyrosequencing approach, BioMed Research International, 2018, 1-13. https://doi.org/10.1155/2018/3503658
  4. Jensen BB and Jorgensen H (1994). Effect of dietary fiber on microbial activity and microbial gas production in various regions of the gastrointestinal tract of pigs, Applied and Environmental Microbiology, 60, 1897-1904. https://doi.org/10.1128/aem.60.6.1897-1904.1994
  5. Kang JH, Song J, Yoo SS, Lee BJ, and Ji HW (2020). Prediction of odor concentration emitted from wastewater treatment plant using an artificial neural network (ANN), Atmosphere, 11, 784.
  6. Kim G (2020). Analysis of odorous compounds from swine facilities in Jeju Island and the evaluation of their odor contributions (Master's thesis), Jeju National University, Jeju.
  7. Kim KY and Choi JH (2013). Distribution characteristics of odorous compounds concentrations according to type of pig buildings, Journal of Odor and Indoor Environment, 12, 27-37.
  8. Kuroda K, Osada T, Yonaga M, Kanematu A, Nitta T, Mouri S, and Kojima T (1996). Emissions of malodorous compounds and greenhouse gases from composting swine feces, Bioresource Technology, 56, 265-271. https://doi.org/10.1016/0960-8524(96)00047-8
  9. Lee DH, Lee SH, Woo SE, Jung MW, Kim DY, and Heo TY (2022). Prediction of complex odor from pig barn using machine learning and identifying the influence of variables using explainable artificial intelligence, Applied Sciences, 12, 12943.
  10. Mogilnicka I, Bogucki P, and Ufnal M (2020). Microbiota and malodor-etiology and management, International Journal of Molecular Sciences, 21, 2886.
  11. Mulrow J, Kshetry N, Brose DA, Kumar K, Jain D, Shah M, Kunetz TE, and Varshney LR (2020). Prediction of odor complaints at a large composite reservoir in a highly urbanized area: A machine learning approach, Water Environment Research, 92, 418-429. https://doi.org/10.1002/wer.1191
  12. Rincon CA, De Guardia A, Couvert A, Wolbert D, Le Roux S, Soutrel I, and Nunes G (2019). Odor concentration (OC) prediction based on odor activity values (OAVs) during composting of solid wastes and digestates, Atmospheric Environment, 201, 1-12. https://doi.org/10.1016/j.atmosenv.2018.12.030
  13. Saeed U, Jan SU, Lee YD, and Koo I (2021). Fault diagnosis based on extremely randomized trees in wireless sensor networks, Reliability Engineering & System Safety, 205, 107284.
  14. Tianqi C and Carlos G (2016). XGBoost: A scalable tree boosting system, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794.
  15. Breiman L (2001). Random forests, Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  16. Yasuhara A, Fuwa K, and Jimbu M (1984). Identification of odorous compounds in fresh and rotten swine manure, Agricultural and Biological Chemistry, 48, 3001-3010. https://doi.org/10.1080/00021369.1984.10866622