What question did this study set out to answer?

This study aims to improve the accuracy of mean stand diameter at breast height (DBH) predictions for Pinus yunnanensis using machine learning methods.

June 21, 2026Open Access

A Model for Estimating Average Diameter at Breast Height of Pinus yunnanensis Stands Based on Machine Learning Approaches

Key Points

This study aims to improve the accuracy of mean stand diameter at breast height (DBH) predictions for Pinus yunnanensis using machine learning methods.
Utilized data from 854 forest plots with stand age, site class index (SCI), and stand density index (SDI) as independent variables.
Compared predictive performance of traditional growth equations with several machine learning and deep learning models.
Applied ensemble learning strategies to optimize model performance.
The ensemble model showed the highest goodness-of-fit with R2 = 0.893, outperforming all individual models.
Incorporating SCI and SDI improved model explanatory capability to R2 = 0.838, while XGBoost and CNN achieved R2 = 0.852 and 0.861.
Machine learning models demonstrated superior predictive capability compared to linear regression.

Abstract

The mean stand diameter at breast height (DBH) is a key indicator of stand structure and productivity and is widely used in forest resource inventory and management planning. When using regional inventory data, nonlinear interactions between plot-level conditions and predictor variables can undermine the stability of traditional empirical equations across varying site qualities and stand densities. To improve the accuracy and robustness of inventory-scale predictions of mean stand DBH, this study utilized data from 854 forest plots and employed stand age, site class index (SCI), and stand density index (SDI) as independent variables. The predictive performance of traditional growth equations, machine learning models (Random Forest, XGBoost, LightGBM, and support vector machine), and deep learning models (MLP and CNN, ResNet, RNN) was systematically compared, and ensemble learning strategies were further applied to optimize model performance. The results indicated that the Weibull model based solely on stand age achieved the best fit (R2 = 0.669). Incorporating SCI and SDI greatly improved model explanatory capability with R2 rising to 0.838. XGBoost and CNN further improved predictive performance (R2 = 0.852 and 0.861, respectively), while the ensemble model exhibited the highest goodness-of-fit (R2 = 0.893), outperforming all individual models. Compared with linear regression, machine learning models demonstrated superior predictive capability. A feature importance analysis indicated that stand age, site quality and stand density together drive mean stand DBH prediction, among which stand age and stand structural characteristics are the dominant influencing factors, whereas SCI and SDI have comparatively weaker effects. Overall, the ensemble model substantially enhanced the prediction accuracy of mean DBH in Pinus yunnanensis stands, thereby providing for precision forest management and ecological function assessment.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper