Long-term changes of forest biomass and its driving factors in karst area, Guizhou, China

Qian, Chunhua; Qiang, Hequn; Zhang, Guangming; Li, Mingyang

doi:10.1177/15501477211039137

Cited by 8 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deep learning-based methods for processing forest UAV images ( Xie et al, 2022 ) and LiDAR data ( Hu et al, 2020 ) also encounter similar sensitivity and susceptibility challenges in tree crown recognition caused by the complexity of forest environments ( Qian et al, 2021 ), image-capture angles ( Yin et al, 2021 ) and interferences stemming from local solar radiation ( Kattenborn et al, 2019 ). Furthermore, the predicted bounding boxes produced by common small-target detection networks, e.g., You Only Look Once (YOLO) and Faster Regional-based Convolutional Neural Network (R-CNN), have regular rectangular shapes, making it difficult to detect the anisotropic shapes of tree crowns.…”

Section: Introductionmentioning

confidence: 99%

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

et al. 2022

View full text Add to dashboard Cite

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.

show abstract

Section: Introductionmentioning

confidence: 99%

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The terrain slopes gradually downward from west to east, spanning the Yangtze and Pearl Rivers ( Figure 1 ). More than 90% of the land in this area is mountains or hills, with an average altitude of 1100 m [ 31 , 32 ]. This area has one of the highest concentrations of karsts in the world, with the largest continuous outcrop of carbonate rocks and densely developed karst [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

“…More than 90% of the land in this area is mountains or hills, with an average altitude of 1100 m [ 31 , 32 ]. This area has one of the highest concentrations of karsts in the world, with the largest continuous outcrop of carbonate rocks and densely developed karst [ 32 ]. The population pressure is enormous and many people live in poverty in remote mountain villages [ 31 ].…”

Section: Methodsmentioning

confidence: 99%

Millennial Evolution of a Karst Socio-Ecological System: A Case Study of Guizhou Province, Southwest China

Zhang

2022

IJERPH

View full text Add to dashboard Cite

The dynamic changes in socio-ecological system (SES) have exerted increasing pressures on the natural environment, leading to observable changes in terrestrial surface structure. Therefore, understanding the historical evolution mechanism of social ecosystems is crucial for the future sustainable management of karst regions. However, detailed quantitative analyses of karst socio-ecological system at a long-term scale are lacking. Here, we applied a comprehensive research framework for the SES of karst region to visually analyze the evolution of karst SES over the past 1000 years in Guizhou Province, defining five evolution stages of the karst SES. Concurrently, we characterized the interactive effects of drivers on karst socio-ecological system during every evolutionary stage, and then assess major influences between these stages. Despite rocky desertification as the main effect of karst SES driven by many indicators, the quantitative analysis indicated that human-dominated land-use change explained the expansion of rocky desertification. Although effective implementation of relevant policies partly compensated for increased environmental pressures, continued structure and function shifts in local ecosystem can challenge progress towards sustainability in karst region. Our findings provide scientific references for managers and policymakers to assist them to identify how environmental issues emerged in karst areas and how they should be addressed.

show abstract

“…There is a linear relationship between the forest volume in the stand and the aboveground forest biomass [56,57]. The details can be obtained from the literature [58], the formula is:…”

Section: Data 221 the Ground Survey Datamentioning

confidence: 99%

Estimation of Forest Aboveground Biomass in Karst Areas Using Multi-Source Remote Sensing Data and the K-DBN Algorithm

et al. 2021

Self Cite

View full text Add to dashboard Cite

Accurate estimation of forest biomass is the basis for monitoring forest productivity and carbon sink function, which is of great significance for the formulation of forest carbon neutralization strategy and forest quality improvement measures. Taking Guizhou, a typical karst region in China, as the research area, this study used Landsat 8 OLI, Sentinel-1A, and China national forest resources continuous inventory data (NFCI) in 2015 to build a deep belief network (DBN) model for aboveground biomass (AGB) estimation. Based on the introduction of forest canopy density (FCD), we improved the DBN model to design the K-DBN model with the highest estimation accuracy is selected for AGB inversion and spatial mapping. The results showed that: (1) The determination coefficients R2 of DBN is 0.602, which are 0.208, 0.101 higher than that of linear regression (LR) and random forest (RF) model. (2) The K-DBN algorithm was designed based on FCD to optimize the DBN model, which can alleviate the common problems of low-value overestimation and high-value underestimation in AGB estimation to a certain extent to improve the estimation accuracy. The maximum R2 of the model reached 0.848, and we mapped the forest AGB using the K-DBN model in the study area in 2015. The conclusion of this study: Based on multi-source optical and radar data, the retrieval accuracy of forest AGB can be improved by considering the FCD, and the deep learning algorithm K-DBN is excellent in forest AGB remote sensing estimation. These research results provide a new method and data support for the spatio-temporal dynamic remote sensing monitoring of forest AGB in karst areas.

show abstract

Long-term changes of forest biomass and its driving factors in karst area, Guizhou, China

Cited by 8 publications

References 35 publications

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

Millennial Evolution of a Karst Socio-Ecological System: A Case Study of Guizhou Province, Southwest China

Estimation of Forest Aboveground Biomass in Karst Areas Using Multi-Source Remote Sensing Data and the K-DBN Algorithm

Contact Info

Product

Resources

About