FWFan Wang

Fan Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Fan Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Forest disturbance detection and spatio-temporal dynamic analysis using the GRU-LPETransformer model

    by Fan Wang, Zhijie Xue, Yueyuan Yang, Xin Tan, Jianluo Cui, Kunyong Yu, Jian Liu

  • Open Access

    A Method Coupling NDT and VGICP for Registering UAV-LiDAR and LiDAR-SLAM Point Clouds in Plantation Forest Plots

    by Fan Wang, Jiawei Wang, Yun Wu, Zhijie Xue, Xin Tan, Yueyuan Yang, Simei Lin

    The combination of UAV-LiDAR and LiDAR-SLAM (Simultaneous Localization and Mapping) technology can overcome the scanning limitations of different platforms and obtain comprehensive 3D structural information of forest stands. To address the challenges of the traditional registration algorithms, such as high initial value requirements and susceptibility to local optima, in this paper, we propose a high-precision, robust, NDT-VGICP registration method that integrates voxel features to register UAV-LiDAR and LiDAR-SLAM point clouds at the forest stand scale. First, the point clouds are voxelized, and their normal vectors and normal distribution models are computed, then the initial transformation matrix is quickly estimated based on the point pair distribution characteristics to achieve preliminary alignment. Second, high-dimensional feature weighting is introduced, and the iterative closest point (ICP) algorithm is used to optimize the distance between the matching point pairs, adjusting the transformation matrix to reduce the registration errors iteratively. Finally, the algorithm converges when the iterative conditions are met, yielding an optimal transformation matrix and achieving precise point cloud registration. The results show that the algorithm performs well in Chinese fir forest stands of different age groups (average RMSE—horizontal: 4.27 cm; vertical: 3.86 cm) and achieves high accuracy in single-tree crown vertex detection and tree height estimation (average F-score: 0.90; R2 for tree height estimation: 0.88). This study demonstrates that the NDT-VGICP algorithm can effectively fuse and collaboratively apply multi-platform LiDAR data, providing a methodological reference for accurately quantifying individual tree parameters and efficiently monitoring 3D forest stand structures.


  • Open Access

    Corrigendum: Forest stand spectrum reconstruction using spectrum spatial feature gathering and multilayer perceptron

    by Fan Wang, Linghan Song, Xiaojie Liu, Shuangwen Zhong, Jiawei Wang, Yao Zhang, Yun Wu

    Corrigendum: Forest stand spectrum reconstruction using spectrum spatial feature gathering and multilayer perceptron


  • Open Access

    Forest stand spectrum reconstruction using spectrum spatial feature gathering and multilayer perceptron

    by Fan Wang, Linghan Song, Xiaojie Liu, Shuangwen Zhong, Jiawei Wang, Yao Zhang, Yun Wu

    Introduction: Three-dimensional spectral distributions of forest stands can provide spatial information on the physiological and biochemical status of forests, which is vital for forest management. However, three-dimensional spectral studies of forest stands are limited.Methods: In this study, LiDAR and multispectral data were collected from Masson pine stands in southern Fujian Province, China, and a method was proposed for inverting forest spectra using point clouds as a unit. First, multispectral values were mapped to a point cloud, and the isolated forest algorithm combined with K-means clustering was applied to characterize fusion data. Second, five deep learning algorithms were selected for semantic segmentation, and the overall accuracy (oAcc) and mean intersection ratio (mIoU) were used to evaluate the performance of various algorithms on the fusion data set. Third, the semantic segmentation model was used to reconfigure the class 3D spectral distribution, and the model inversion outcomes were evaluated by the peaks and valleys of the curve of the predicted values and distribution gaps.Results: The results show that the correlations between spectral attributes and between spatial attributes were both greater than 0.98, while the correlation between spectral and spatial attributes was 0.43. The most applicable method was PointMLP, highest oAcc was 0.84, highest mIoU was 0.75, peak interval of the prediction curve tended to be consistent with the true values, and maximum difference between the predicted value and the true value of the point cloud spectrum was 0.83.Discussion: Experimental data suggested that combining spatial fusion and semantic segmentation effectively inverts three-dimensional spectral information for forest stands. The model could meet the accuracy requirements of local spectral inversion, and the NIR values of stands in different regions were correlated with the vertical height of the canopy and the distance from the tree apex in the region. These findings improve our understanding of the precise three-dimensional spectral distribution of forests, providing a basis for near-earth remote sensing of forests and the estimation of forest stand health.


  • Open Access

    Spatio-Temporal Multi-Scale Analysis of Landscape Ecological Risk in Minjiang River Basin Based on Adaptive Cycle

    by Tiantian Bao, Ruifan Wang, Linghan Song, Xiaojie Liu, Shuangwen Zhong, Jian Liu, Kunyong Yu, Fan Wang

    Landscape ecological security is an environmental requirement for social and economic development. Understanding the dynamic mechanisms of landscape change and the associated ecological risks in regional socioecological systems is necessary for promoting regional sustainable development. Using the Minjiang River Basin as the research area, the Google Earth Engine platform, random forest (RF) model, and FLUS model were employed for land use classification and future multi-scenario prediction. Multisource remote sensing data were used to establish a three-dimensional evaluation index system for an adaptive cycle. Additionally, the “potential-connection-resilience” framework was adopted to explore the spatial and temporal variations in landscape ecological risk in the basin from 2001 to 2035 under different administrative scales and development scenarios. The results showed that from 2001 to 2020, the building and forest areas increased significantly, whereas grassland and plowland areas decreased significantly. Moreover, the spatial fragmentation of the watershed improved significantly with the transformation of large amounts of grassland into forests. The construction area continued to expand in 2035 under different scenarios. Under the economic development scenario, the grassland and plowland areas decreased considerably, but the forest area increased slowly. Under the ecological protection scenario, the expansion of land use was restrained, and the reduction rate of grassland and cultivated land was moderated. From 2001 to 2020, the overall ecological risk was at a medium-low level and showed a decreasing trend, and the fragmentation degree of the forest had a significant impact on ecological risk. By 2035, landscape ecological risks increased under different development scenarios, and construction land expansion had become the dominant factor affecting the risk level. By evaluating the distribution and development trend of ecologically high-risk areas in the Minjiang River Basin, the results of this study provide basic support for the rational planning of land resources in the basin and decision making for future sustainable development efforts.


  • Open Access

    Quantifying Understory Vegetation Cover of Pinus massoniana Forest in Hilly Region of South China by Combined Near-Ground Active and Passive Remote Sensing

    by Ruifan Wang, Tiantian Bao, Shangfeng Tian, Linghan Song, Shuangwen Zhong, Jian Liu, Kunyong Yu, Fan Wang

    Understory vegetation cover is an important indicator of forest health, and it can also be used as a proxy in the exploration of soil erosion dynamics. Therefore, quantifying the understory vegetation cover in hilly areas in southern China is crucial for facilitating the development of strategies to address local soil erosion. Nevertheless, a multi-source data synergy has not been fully revealed in the remote sensing data quantifying understory vegetation in this region; this issue can be attributed to an insufficient match between the point cloud 3D data obtained from active and passive remote sensing systems and the UAV orthophotos, culminating in an abundance of understory vegetation information not being represented in two dimensions. In this study, we proposed a method that combines the UAV orthophoto and airborne LiDAR data to detect the understory vegetation. Firstly, to enhance the characterization of understory vegetation, the point CNN model was used to decompose the three-dimensional structure of the pinus massoniana forest. Secondly, the point cloud was projected onto the UAV image using the point cloud back-projection algorithm. Finally, understory vegetation cover was estimated using a synthetic dataset. Canopy closure was divided into two categories: low and high canopy cover. Slopes were divided into three categories: gentle slopes, inclined slopes, and steep slopes. To clearly elucidate the influence of canopy closure and slope on the remote sensing estimation of understory vegetation coverage, the accuracy for each category was compared. The results show that the overall accuracy of the point CNN model to separate the three-dimensional structure of the pinus massoniana forest was 74%, which met the accuracy requirement of enhancing the understory vegetation. This method was able to obtain the understory vegetation cover more accurately at a low canopy closure level (Rlow2 = 0.778, RMSElow = 0.068) than at a high canopy closure level (RHigh2 = 0.682, RMSEHigh = 0.172). The method could also obtain high accuracy in version results with R2 values of 0.875, 0.807, and 0.704, as well as RMSE of 0.065, 0.106, and 0.149 for gentle slopes, inclined slopes, and steep slopes, respectively. The methods proposed in this study could provide technical support for UAV remote sensing surveys of understory vegetation in the southern hilly areas of China.


  • Open Access

    Extraction of Broad-Leaved Tree Crown Based on UAV Visible Images and OBIA-RF Model: A Case Study for Chinese Olive Trees

    by Kaile Yang, Houxi Zhang, Fan Wang, Riwen Lai

    Chinese olive trees (Canarium album L.) are broad-leaved species that are widely planted in China. Accurately obtaining tree crown information provides important data for evaluating Chinese olive tree growth status, water and fertilizer management, and yield estimation. To this end, this study first used unmanned aerial vehicle (UAV) images in the visible band as the source of remote sensing (RS) data. Second, based on spectral features of the image object, the vegetation index, shape, texture, and terrain features were introduced. Finally, the extraction effect of different feature dimensions was analyzed based on the random forest (RF) algorithm, and the performance of different classifiers was compared based on the features after dimensionality reduction. The results showed that the difference in feature dimensionality and importance was the main factor that led to a change in extraction accuracy. RF has the best extraction effect among the current mainstream machine learning (ML) algorithms. In comparison with the pixel-based (PB) classification method, the object-based image analysis (OBIA) method can extract features of each element of RS images, which has certain advantages. Therefore, the combination of OBIA and RF algorithms is a good solution for Chinese olive tree crown (COTC) extraction based on UAV visible band images.