Predicting Lettuce Growth using the Artificial Intelligence Model XGBoost

Bo Hyun Sung; Wonkyoung Lee; Shinjae Jeon; Jaehee Won; Young-Yeol Cho

doi:10.22698/jales.20240023

All Issue

2024 Vol.36, Issue 3 Preview Page

Research Article

Predicting Lettuce Growth using the Artificial Intelligence Model XGBoost XGBoost 인공지능 모델을 활용한 상추 생육 예측

30 September 2024. pp. 289-296

PDF XML

Abstract

Predicting the impacts of changes in the cultivation environment on crop growth is crucial to enhancing farm management and ensuring income stability. We aimed to predict the growth of three lettuce varieties using the XGBoost artificial intelligence model. The three selected lettuce cultivars were ‘Ezatrix’, ‘Ezabel’ (Enza Zaden Co., Ltd., The Netherlands), and ‘Sunpungpochap’ (Kwonnong Co., Ltd., Korea). Cultivars were grown in a coir-based soil-free system. Environmental variables, including air temperature, soil temperature, relative humidity, and solar radiation, were measured at 1 min intervals using a HOBO data logger. The XGBoost artificial intelligence tool was employed to analyze key hyperparameters including n_estimators (number of boosting trees), learning_rate (learning rate), and max_depth (maximum depth of trees) being optimized. The environmental variables considered were air temperature, soil temperature, relative humidity, and solar radiation. The growth of the three lettuce cultivars was predicted using the XGBoost model and model performance was validated through cross-validation. Outliers in growth measurements were identified and re-predicted using moving averages. Root mean square errors (RMSE) for shoot fresh weight of ‘Ezatrix’, ‘Ezabel’, and ‘Sunpungpochap’ cultivars were 0.913, 0.864, and 0.870, respectively. RMSE values for shoot dry weight were 0.901, 0.872, and 0.867, respectively. This study utilized the XGBoost model to predict the growth of three lettuce cultivars. Its results are expected to aid in developing crop management strategies and improving productivity.

Keywords

Artificial intelligence

Lettuce

Shoot dry weight

Shoot fresh weight

XGBoost model

References

Baek, Y. T., Sul, S. G., Cho, Y. Y. (2023) Estimation of days after transplanting using an artificial intelligence CNN (Convolutional Neural Network) model in a closed-type plant factory. Hortic Sci Technol 41:81-90. doi:10.7235/HORT.20230008.

10.7235/HORT.20230008

Chen, T., Guestrin, C. (2016) XGBoost: A scalable tree boosting system. In Proceedings of the Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. pp.785-794. San Francisco, CA, USA. doi:10.1145/2939672.2939785.

10.1145/2939672.2939785

Friedman, J. H. (1999) Greedy function approximation: A gradient boosting machine. Ann Statist 29:1189-1232. dio:10.1214/aos/103203451.

10.1214/aos/1013203451

Gachoki, P., Muraya, M., Njoroge, G. (2022) Modelling plant growth based on gompertz, logistic curve, extreme gradient boosting and light gradient boosting models using high dimensional image derived maize (Zea mays L.) phenomic data. Am J Appl Math Stat 10:52-64. doi:10.12691/ajams-10-2-3

10.12691/ajams-10-2-3

Ge, J., Zhao, L., Yu, Z., Liu, H., Zhang, L., Gong, X., Sun, H. (2022) Prediction of greenhouse tomato crop evapotranspiration using XGBoost machine learning model. Plants 11:1923. doi:10.3390/plants11151923

10.3390/plants11151923

Kim, N. E., Han, H. S., Arulmozhi, E., Moon, B. E., Choi, Y. W., Kim, H. T. (2022) Prediction of greenhouse strawberry production using machine learning algorithm. J Bio-Env Con 31:1-7. doi:10.12791/KSBEC.2022.31.1.001

10.12791/KSBEC.2022.31.1.001

Lee, S. Y., Yang, H. J., Kim, M. Y., Kim, J. K., Son, A. Y., Hong, S. H. (2023) A study on prediction of tomato production using BI-LSTM for smart farm utilization. J- KICS 48:457-468. doi:10.7840/kics.2023.48.4.457

10.7840/kics.2023.48.4.457

Mariadass, D. A. -L., Moung, E. G., Sufian, M. M., Farzamnia, A. (2022) Extreme gradient boosting (XGBoost) regressor and shapley additive explanation for crop yield prediction in agriculture. 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE). pp.219-224. Mashhad, Islamic Republic of Iran. doi:10.1109/ICCKE57176.2022.9960069

10.1109/ICCKE57176.2022.9960069

M'hamdi, O., Takács, S., Palotás, G., Ilahy, R., Helyes, L., Pék, Z. A. (2024) Comparative analysis of XGBoost and neural network models for predicting some tomato fruit quality traits from environmental and meteorological data. Plants 13:746. doi:10.3390/plants13050746

10.3390/plants13050746

Moon, T. W., Park, J. Y., Son, J. E. (2020) Estimation of sweet pepper crop fresh weight with convolutional neural network. Protected Hort Plant Fac 29:381-387. doi:10.12791/KSBEC.2020.29.4.381

10.12791/KSBEC.2020.29.4.381

Raddekar, A., Chikmurge, D., Subhedar, M. (2023) Prediction of crop yield with feature dimension reduction method using regression models. 7th Intenational Conference On Computing, Communication, Control And Automation (ICCUBEA). pp.1-6. Pune, India. doi: 10.1109/ICCUBEA58933.2023.10392189

10.1109/ICCUBEA58933.2023.10392189

Ravi, R., Baranidharan, B. (2020) Crop yield prediction using XGBoost algorithm. Int J Recent Technol Eng 8:3516-3520. doi:10.35940/ijrte.D9547.018520

10.35940/ijrte.D9547.018520

Zhang, Y., Wu, M., Li, J., Yang, S., Zheng, L., Liu, X., Wang, M. (2022) Automatic non-destructive multiple lettuce traits prediction based on DeepLabV3+. J Food Meas Charact 17:636-652. doi:10.1007/s11694-022-01660-3

10.1007/s11694-022-01660-3

Information

Publisher :Agriculture and Life Sciences Research Institute, Kangwon National University
Publisher(Ko) :강원대학교 농업생명과학대학 농업생명과학연구원
Journal Title :Journal of Agricultural, Life and Environmental Sciences
Journal Title(Ko) :농업생명환경연구
Volume : 36
No :3
Pages :289-296
Received Date : 2024-07-01
Revised Date : 2024-08-21
Accepted Date : 2024-09-19
DOI :https://doi.org/10.22698/jales.20240023

Journal of Agricultural, Life and Environmental Sciences ISSN:2233-8322(Print) 2508-870X(Online) 농업생명환경연구

All Issue