DOI QR코드

DOI QR Code

Modeling Optimized Cucumber Prediction Using AI-Based Automatic Control System Data

  • Heung-Sup Sim (Computer & Military Department, Dongyang University)
  • 투고 : 2024.08.20
  • 심사 : 2024.10.10
  • 발행 : 2024.11.29

초록

본 논문에서는 AI 기반 오이 생육 자동 제어시스템을 활용한 최적화된 착과수 예측 모델을 제안한다. 순천대학교 실험 농장과 순천만 오이 농장에서 수집된 데이터를 기반으로, 랜덤 포레스트, XGBoost, LightGBM 등 세 가지 머신러닝 알고리즘을 적용하여 모델을 구축하고 성능을 비교 분석하였다. 온도, 습도, CO2 농도 등 19개의 환경 및 생육 관련 변수를 활용하여 모델을 훈련시켰다. 결과적으로 LightGBM 모델이 가장 우수한 성능(RMSE: 1.9803, R-squared: 0.5891)을 보였다. 그러나 모든 모델의 R-squared 값이 0.6 미만으로, 데이터의 비선형성과 시간적 의존성을 충분히 반영하지 못한 한계가 있었다. 향후 연구에서는 추가 데이터 수집, 복잡한 특성 엔지니어링, 시계열 분석 기법 도입 등을 통해 모델의 성능을 개선할 필요가 있다. 본 연구는 스마트팜 기술의 실용화와 데이터 기반 농업 의사결정 지원 시스템 개발에 기여할 것으로 기대된다.

This paper proposes an optimized fruit set prediction model for cucumbers using an AI-based automatic growth control system. Based on data collected from experimental farms at Sunchon National University and Suncheon Bay cucumber farms, we constructed and compared the performance of models using three machine learning algorithms: Random Forest, XGBoost, and LightGBM. The models were trained using 19 environmental and growth-related variables, including temperature, humidity, and CO2 concentration. The LightGBM model showed the best performance (RMSE: 1.9803, R-squared: 0.5891). However, all models had R-squared values below 0.6, indicating limitations in capturing data nonlinearity and temporal dependencies. The study identified key factors influencing cucumber fruit set prediction through feature importance analysis. Future research should focus on collecting additional data, applying complex feature engineering, introducing time series analysis techniques, and considering data augmentation and normalization to improve model performance. This study contributes to the practical application of smart farm technology and the development of data-driven agricultural decision support systems.

키워드

참고문헌

  1. D. B. Lobell, et al., "Climate Change and Agriculture: Impacts, Adaptation and Mitigation," Science, Vol. 372, No. 6546, pp. 239-250, May 2021. DOI: 10.1126/science.aat4343 
  2. J. Smith, et al., "Smart Farming: The Future of Agriculture," Journal of Agricultural Technology, Vol. 37, No. 2, pp. 145-160, April 2022. DOI: 10.1007/s13593-022-00755-x 
  3. Y. S. Kim, et al., "IoT-Based Environmental Monitoring in Greenhouse Horticulture," Sensors, Vol. 20, No. 3, pp. 771-790, February 2020. DOI: 10.3390/s20030771 
  4. S. C. Kim, J. H. Park, and S. K. Lee, "Development of Machine Learning-Based Prediction Model for Cucumber Yield in Protected Cultivation," Journal of The Korean Society of Agricultural Engineers, Vol. 63, No. 2, pp. 69-77, March 2021. DOI: 10.5389/KSAE.2021.63.2.069 
  5. Y. S. Kim, et al., "Development of AI-based Cucumber Disease Diagnosis System," Korean Journal of Agricultural Science, Vol. 48, No. 3, pp. 677-688, September 2021. DOI: 10.7744/kjoas.20210056 
  6. H. J. Park, S. Y. Lee, and J. E. Son, "Development of a Machine Learning Model for Predicting Optimal Environmental Conditions in Cucumber Cultivation," Journal of Biosystems Engineering, Vol. 46, No. 4, pp. 405-414, December 2021. DOI: 10.1007/s42853-021-00110-0 
  7. L. Breiman, "Random forests," Machine Learning, Vol. 45, No. 1, pp. 5-32, October 2001. DOI: 10.1023/A:1010933404324 
  8. T. Chen, and C. Guestrin, "XGBoost: A scalable tree boosting system," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794, August 2016. DOI: 10.1145/2939672.2939785 
  9. M. Kuhn, and K. Johnson, "Applied predictive modeling," Springer, New York, NY, 2013. DOI: 10.1007/978-1-4614-6849-3 
  10. Y. S. Kim, S. Y. Lee, and J. I. Son, "Development of a Deep Learning-Based Cucumber Disease Diagnosis System," Korean Journal of Agricultural Science, Vol. 48, No. 3, pp. 677-688, September 2021. DOI: 10.7744/kjoas.20210056 
  11. H. J. Park, S. Y. Lee, and J. I. Son, "Development of a Machine Learning Model for Predicting Optimal Environmental Conditions in Cucumber Cultivation," Korean Journal of Bio-Environment Control, Vol. 30, No. 4, pp. 405-414, December 2021. DOI: 10.12791/KSBEC.2021.30.4.405