Prediction of Larix kaempferi Stand Growth in Gangwon, Korea, Using Machine Learning Algorithms
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this study, we sought to compare and evaluate the accuracy and predictive performance of machine learning algorithms for estimating the growth of individual Larix kaempferi trees in Gangwon Province, Korea. We employed linear regression, random forest, XGBoost, and LightGBM algorithms to predict tree growth using monitoring data organized based on different thinning intensities. Furthermore, we compared and evaluated the goodness-of-fit of these models using metrics such as the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). The results revealed that XGBoost provided the highest goodness-of-fit, with an R2 value of 0.62 across all thinning intensities, while also yielding the lowest values for MAE and RMSE, thereby indicating the best model fit. When predicting the growth volume of individual trees after 3 years using the XGBoost model, the agreement was exceptionally high, reaching approximately 97% for all stand sites in accordance with the different thinning intensities. Notably, in non-thinned plots, the predicted volumes were approximately 2.1 m3 lower than the actual volumes; however, the agreement remained highly accurate at approximately 99.5%. These findings will contribute to the development of growth prediction models for individual trees using machine learning algorithms.
Abstract
In this study, we sought to compare and evaluate the accuracy and predictive performance of machine learning algorithms for estimating the growth of individual Larix kaempferi trees in Gangwon Province, Korea. We employed linear regression, random forest, XGBoost, and LightGBM algorithms to predict tree growth using monitoring data organized based on different thinning intensities. Furthermore, we compared and evaluated the goodness-of-fit of these models using metrics such as the coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). The results revealed that XGBoost provided the highest goodness-of-fit, with an R2 value of 0.62 across all thinning intensities, while also yielding the lowest values for MAE and RMSE, thereby indicating the best model fit. When predicting the growth volume of individual trees after 3 years using the XGBoost model, the agreement was exceptionally high, reaching approximately 97% for all stand sites in accordance with the different thinning intensities. Notably, in non-thinned plots, the predicted volumes were approximately 2.1 m3 lower than the actual volumes; however, the agreement remained highly accurate at approximately 99.5%. These findings will contribute to the development of growth prediction models for individual trees using machine learning algorithms.
참고문헌 (23)
- A description of STEMS- the stand and tree evaluation and modeling system, "Belcher DM", USDA Forest Service, 1~18, pp.General Technical Report NC-79 (1982)
- GROW: a computer subroutine that projects the growth of trees in lake states’ forests, "Brand GJ", USDA Forest Service, 1~11, pp.Research paper NC-207 (1981)
- Breiman L, "Random Forests", Mach Learn, 45, pp.5~32 (2001)
- Chen T, "XGBoost: a scalable tree boosting system", KDD’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
- Growth Response Model for Major Tree Species Using Tree Ring Information of National Forest Inventory, "Choi JK", Korea Forest Service, ~ (2012)
- 강민구, "영향요인을 고려한 댐 용수공급능력 추정 회귀모형", 한국수자원학회 논문집, 45(11), pp.1131~1141 (2012), 한국수자원학회
- Ke G, "LightGBM: a highly efficient gradient boosting decision tree", NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp.3149~3157 (2017)
- Kim S, "Basics of Statistics for the Social Sciences: with R Examples" (2019), Hakjisa
- 김세원, "작물 생산량 예측을 위한 머신러닝 기법 활용 연구", 한국산학기술학회논문지, 22(7), pp.403~408 (2021), 한국산학기술학회[DOI]
- Tree Volume, Biomass, and Stand Yield Table 2021, "Korea Forest Service, National Institute of Forest Science", National Institute of Forest Science, ~ (2021)
- Statistical Yearbook of Forestry, "Korea Forest Service", Korea Forest Service, ~ (2019)
- Kwon S., "Development of a simulation model for stand-level forest management", PhD, pp.2003
- 이대성, "잣나무 인공림의 1차 및 2차 간벌에 따른 입목생장 특성 분석", 한국산림과학회지, 111(1), pp.150~164 (2022), 한국산림과학회[DOI]
- 이진형, "머신러닝을 이용한 빅데이터 품질진단 자동화에 관한 연구", 한국빅데이터학회 학회지, 2(2), pp.75~86 (2017), 사)한국빅데이터학회[DOI]
- Lee JM., "A study on statistical regression analysis", MS, pp.2002
- 이승현, "머신러닝기법을 이용한 상수리나무의 수간고별 직경추정 연구", 농업생명과학연구, 54(6), pp.29~37 (2020), 농업생명과학연구원[DOI]
- Lee WK, "Estimating the competition indices and diameter growth of individual trees through position-dependent stand survey", J Korean For Soc, 85, pp.539~551 (1996)
- Sustainable Forest Resource Management Standard Manual, "National Institute of Forest Science", National Institute of Forest Science, ~ (2005)
- Ou Q, "Individual tree diameter growth models of larch-spruce-fir mixed forests based on machine learning algorithms", Forests, 10, pp.187~ (2019)
- Pacala SW, "Forest models defined by field measurements : I. The design of a northeastern forest simulator", Can J For Res, 23, pp.1980~1988 (1993)
- Schindler DE, "Sustainability. Prediction, precaution, and policy under global change", Science, 347, pp.953~954 (2015)
- Prognosis model for stand development, "Stage AR", USDA Forest Service, 1~32, pp.Research Paper INT-137 (1973)
- 양아람, "낙엽송 벌채지 내 식재된 낙엽송 조림목의 초기 생장 특성", 한국산림과학회지, 106(1), pp.10~18 (2017), 한국산림과학회[DOI]