Estimating carbon sequestration potential and optimizing management strategies for Moso bamboo (Phyllostachys pubescens) forests using machine learning DOI Creative Commons

Shaofeng Lv,

Ning Yuan,

Xiaobo Sun

et al.

Frontiers in Forests and Global Change, Journal Year: 2024, Volume and Issue: 7

Published: April 4, 2024

Estimating the carbon sequestration potential of Moso bamboo ( Phyllostachys pubescens ) forests and optimizing management strategies play pivotal roles in enhancing quality promoting sustainable development. However, there is a lack methods to simulate changes capacity screen optimize best measures based on long-term time series data from fixed-sample fine surveys. Therefore, this study utilized continuous survey climate fixed sample plots Zhejiang Province spanning 2004 2019. By comparing four different algorithms, namely random forest, support vector machine, XGBoost, BP neural network, construct aboveground stock models for forests. The ultimate goal was identify optimal algorithmic model. Additionally, key driving parameters future stocks were considered predicted Then formulated an strategy these predictions. results indicated that model constructed using XGBoost algorithm, with R 2 0.9895 root mean square error 0.1059, achieved performance most influential vegetation found be age, diameter at breast height, culm density. Under measures, which involve no harvesting 1–3 du bamboo, 30% 4 80% aged 5 above. Our predictions show will peak 36.25 ± 8.47 Tg C 2046 remain stable 2060. Conversely, degradation detrimental maintenance forests, resulting 29.50 7.49 2033, followed by decline. This underscores significant influence estimating decisions sustaining

Language: Английский

Fitting Maximum Crown Width Height of Chinese fir through Ensemble Learning Combined with Fine Spatial Competition DOI Creative Commons

Zeyu Cui,

Huaiqing Zhang, Yang Liu

et al.

Plant Phenomics, Journal Year: 2025, Volume and Issue: unknown, P. 100018 - 100018

Published: Feb. 1, 2025

Language: Английский

Citations

0
Climate sensitive mixed-effects dominant height model for moso bamboo in China DOI
Xiao‐Hua Zhou, Xuan Zhang, Zhen Li

et al.

Tropical Ecology, Journal Year: 2025, Volume and Issue: unknown

Published: May 2, 2025

Language: Английский

Citations

0
The Process of Patchy Expansion for Bamboo (Phyllostachys edulis) at the Bamboo–Broadleaf Forest Interface: Spreading and Filling in Order DOI Open Access
Xiaoxia Zeng,

Huitan Luo,

Jian Lü

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(3), P. 438 - 438

Published: Feb. 25, 2024

Bamboo (Phyllostachys edulis) expansion to native adjacent forests has become an increasingly serious problem; however, patterns of bamboo are still lacking research, especially at a community scale. Quantitative research on plays significant role in understanding the process, as well prevention and control. We analyzed change pattern, index, rate bamboo-broadleaf transition zone sample plots, specifically from 2017 2021 forest (representing late stage expansion) front early expansion). found that is patchy expansion, including inner filling patch, boundary expanding transboundary leaping expansion–infill mixed stationary patch. From (year front) forest), type patches transitioned patch expansion–inner infilling Additionally, showed declining trend. 2021, (position 0–20 m) 60–80 declined by 0.53 m/2a 0.47 m/2a, respectively. Our reveals exhibits characterized sequence “first spreading outward then inward”, whether viewed pattern or rate. This process involves continuous plaque addition, merger, complete population. These findings provide valuable insights into have important implications for management control forests.

Language: Английский

Citations

3
A climate sensitive nonlinear mixed-effects height to crown base model: a study focuses on Phyllostachys pubescens DOI
Xiao Zhou, Xuan Zhang, Zhen Li

et al.

Trees, Journal Year: 2024, Volume and Issue: 38(4), P. 849 - 862

Published: June 18, 2024

Language: Английский

Citations

1
Estimating carbon sequestration potential and optimizing management strategies for Moso bamboo (Phyllostachys pubescens) forests using machine learning DOI Creative Commons

Shaofeng Lv,

Ning Yuan,

Xiaobo Sun

et al.

Frontiers in Forests and Global Change, Journal Year: 2024, Volume and Issue: 7

Published: April 4, 2024

Estimating the carbon sequestration potential of Moso bamboo ( Phyllostachys pubescens ) forests and optimizing management strategies play pivotal roles in enhancing quality promoting sustainable development. However, there is a lack methods to simulate changes capacity screen optimize best measures based on long-term time series data from fixed-sample fine surveys. Therefore, this study utilized continuous survey climate fixed sample plots Zhejiang Province spanning 2004 2019. By comparing four different algorithms, namely random forest, support vector machine, XGBoost, BP neural network, construct aboveground stock models for forests. The ultimate goal was identify optimal algorithmic model. Additionally, key driving parameters future stocks were considered predicted Then formulated an strategy these predictions. results indicated that model constructed using XGBoost algorithm, with R 2 0.9895 root mean square error 0.1059, achieved performance most influential vegetation found be age, diameter at breast height, culm density. Under measures, which involve no harvesting 1–3 du bamboo, 30% 4 80% aged 5 above. Our predictions show will peak 36.25 ± 8.47 Tg C 2046 remain stable 2060. Conversely, degradation detrimental maintenance forests, resulting 29.50 7.49 2033, followed by decline. This underscores significant influence estimating decisions sustaining

Language: Английский

Citations

0