Disentangling the Factors That Contribute to the Growth of Betula spp. and Cunninghami lanceolata in China Based on Machine Learning Algorithms

Abstract

Forests are indispensable materials and spiritual foundations for promoting ecosystem circulation and human survival. Exploring the environmental impact mechanism on individual-tree growth is of great significance. In this study, the effects of biogeoclimate, competition, and topography on the growth of Betula spp. and Cunninghamia lanceolata (Lamb.) Hook., two tree species with high importance value in China, were explored by gradient boosting regression tree (GBRT), k-nearest neighbor (KNN), and random forest (RF) machine learning (ML) algorithms. The results showed that the accuracy of RF was better than KNN, which was better than GBRT. All ML algorithms performed well for future diameter at breast height (DBH) predictions; the Willmott’s indexes of agreement (WIA) of each ML algorithm in predicting the future DBH were all higher than 0.97, and the R2 was higher than 0.98 and 0.90, respectively. The individual tree annual growth rate is mainly affected by the single-tree size, and the external environment can promote or inhibit tree growth. Climate and stand structure variables were relatively more important for tree growth than the topographic factors. Lower temperature and precipitation, higher stand density, and canopy closure were more unfavorable for their growth. In afforestation, the following factors should be considered in order: geographic location, meteorological climate, stand structure, and topography.

Predicting and Mapping Dominant Height of Oriental Beech Stands Using Environmental Variables in Sinop, Northern Turkey

“…The partial dependency plots, showing nonlinear relations, indicated that the SDH increased with the ELEV increasing up to 1000 m and then decreased (Figure 6), which could be proof of the optimum altitudinal zone being below 1000 m for oriental beech stands. Similar results on the effect of the ELEV on stand productivity were found in other studies [7,12,14,58,71]. For example, Alavi et al [7] also attributed increased productivity in oriental beech stands of Hyrcania, Iran, to increasing the ELEV to the optimum altitudinal zone, above 1500 m. Güner et al [72] linked this positive effect of the ELEV on Anatolian black pine productivity to improved precipitation at higher altitudes.…”

“…The smoothed PDPs were created for each explanatory variable using the pdp package in the R programming language [50]. The PDPs demonstrated whether each predictor affected the response variable while preserving the average of the remaining predictors [8,14]. After determining the correlations between the variables, MLR and RT analyses were performed to model the SDH using the site variables.…”

“…For example, Alavi et al [7] also attributed increased productivity in oriental beech stands of Hyrcania, Iran, to increasing the ELEV to the optimum altitudinal zone, above 1500 m. Güner et al [72] linked this positive effect of the ELEV on Anatolian black pine productivity to improved precipitation at higher altitudes. However, other authors [4,14,15] reported conflicting findings due to deteriorated ecological conditions with increasing ELEV, such as shortening the growing period, decreasing fine-textured soil, and reducing decomposition due to the condensing temperature. The reducing effect of LAT on stand productivity was also reported in some studies [14,73].…”

Anomalous Warm Temperatures Recorded Using Tree Rings in the Headwater of the Jinsha River during the Little Ice Age

“…While the traditional reconstruction methods primarily rely on constructing linear regression equations [50][51][52], the interplay between tree growth and climatic factors is highly complex and exhibits non-linear characteristics [53]. The previous studies have shown the efficacy of machine learning techniques in capturing non-linear regression relationships between tree growth and climatic factors [54][55][56]. Therefore, this study used three machine learning algorithms-K-nearest neighbors (KNNs), support vector machines (SVMs), and random forest (RF)-for modeling and reconstruction purposes.…”

Research on the Current Situation of Employment Mobility and Retention Rate Predictions of “Double First-Class” University Graduates Based on the Random Forest and BP Neural Network Models

“…The machine learning method [20], the PDE model [21], system dynamics [22], the exponential smoothing forecasting model [23], the grey model [24], random forest [25][26][27][28], and neural network [29][30][31][32] are the main tools used in population forecasting research. The majority of scholars utilize gray models, random forests, and neural networks [33].…”