Estimating forest structural attributes of planted forests plays a key role in managing forest resources, monitoring carbon stocks, and mitigating climate change. High-resolution and low-cost remote-sensing data are increasingly available to measure three-dimensional (3D) canopy structure and model forest structural attributes. In this study, we compared two suites of point cloud metrics and the accuracies of predictive models of forest structural attributes using unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) and digital aerial photogrammetry (DAP) data, in a subtropical coastal planted forest of East China. A comparison between UAV-LiDAR and UAV-DAP metrics was performed across plots among different tree species, heights, and stem densities. The results showed that a higher similarity between the UAV-LiDAR and UAV-DAP metrics appeared in the dawn redwood plots with greater height and lower stem density. The comparison between the UAV-LiDAR and DAP metrics showed that the metrics of the upper percentiles (r for dawn redwood = 0.95–0.96, poplar = 0.94–0.95) showed a stronger correlation than the lower percentiles (r = 0.92–0.93, 0.90–0.92), whereas the metrics of upper canopy return density (r = 0.21–0.24, 0.14–0.15) showed a weaker correlation than those of lower canopy return density (r = 0.32–0.68, 0.31–0.52). The Weibull α parameter indicated a higher correlation (r = 0.70–0.72) than that of the Weibull β parameter (r = 0.07–0.60) for both dawn redwood and poplar plots. The accuracies of UAV-LiDAR (adjusted (Adj)R² = 0.58–0.91, relative root-mean-square error (rRMSE) = 9.03%–24.29%) predicted forest structural attributes were higher than UAV-DAP (Adj-R² = 0.52–0.83, rRMSE = 12.20%–25.84%). In addition, by comparing the forest structural attributes between UAV-LiDAR and UAV-DAP predictive models, the greatest difference was found for volume (ΔAdj-R² = 0.09, ΔrRMSE = 4.20%), whereas the lowest difference was for basal area (ΔAdj-R² = 0.03, ΔrRMSE = 0.86%). This study proved that the UAV-DAP data are useful and comparable to LiDAR for forest inventory and sustainable forest management in planted forests, by providing accurate estimations of forest structural attributes.

Developing an accurate model for estimating the forest structural parameters of planted forests is crucial for forest productivity predictions and can provide a better understanding of the carbon cycle under climate change. Unmanned aerial vehicle-light detecting and ranging (UAV-LiDAR) systems represents a promising active remote sensing technology that has the potential to be used for forest inventories. In addition, the process-based model, physiological principles predicting growth (3-PG), which is based on physiological principles and environmental factors, has been applied to estimate the growth of even-aged, mono-specific forests under the effect of different management levels, site conditions, and climate change. In this study, the performance of UAV-LiDAR metrics was assessed and applied to estimate forest structural parameters using a multivariate linear regression (MLR) method. The 3-PG was parameterized and used to simulate the diameter at breast height, stem density, volume and above-ground biomass of a planted ginkgo forest in eastern China. In addition, a sensitivity analysis was conducted on the 3-PG model's input parameters. The results demonstrated that both the MLR based on UAV-LiDAR data and a progress model of the 3-PG have a promising potential for estimating forest structural parameters (R2 > 0.70, relative root squared error >20%). A sensitivity analysis of the 3-PG parameters also confirmed that the parameter “age at canopy cover” (fullCanAge) is vital for the 3-PG model, and positively correlation with the simulated results. The method presented here represents an improvement on traditional methods for estimating forest structural parameters because it more explicitly accounts for climatic effects included in the 3-PG model.

Accurately estimating and mapping forest structural parameters are essential for monitoring forest resources and understanding ecological processes. The novel deep learning algorithm has the potential to be a promising approach to improve the estimation accuracy while combining with advanced remote sensing technology. Airborne light detection and ranging (LiDAR) has the preferable capability to characterize 3-D canopy structure and estimate forest structural parameters. In this study, we developed a deep learning-based algorithm (Deep-RBN) that combined the fully connected network (FCN) deep learning algorithm with the optimized radial basis neural network (RBN) algorithm for forest structural parameter estimation using airborne LiDAR data. The multiple iterations were used to constantly update the internal weights to achieve the optimized accuracy of model fitting, and the optimized RBN algorithm was developed for the limited training sets. We assessed the efficiency and capability of the Deep-RBN in the estimation of forest structural parameters in a subtropical planted forest of southern China, by comparing the traditional FCN algorithm and multiple linear regression. We found that Deep-RBN had the strongest capability in estimates of forest structural parameters (R ² = 0.67–0.86, rRMSE = 6.95%–20.34%). The sensitivity analysis of the key hyperparameters of Deep-RBN algorithm showed that the learning rate is one of the most important parameters that influence the performance of predictive models, and while its value equal is to 0.001, the predictive models had the highest accuracy (mean DBH: RMSE = 1.01, mean height: RMSE = 1.45, volume: RMSE = 26.49, stem density: RMSE = 121.06). With the increase of training samples added in Deep-RBN model, the predictive models performed better; however, no significant improvements of accuracy were observed while the number of training set is larger than 80. This study demonstrates the benefits of jointly using the Deep-RBN algorithm and airborne LiDAR data to improve the accuracy of forest structural parameter estimation and mapping, which provides a promising methodology for sustainable forest resources monitoring.

Tree diameter distributions are essential for the calculation of stem volume and biomass, as well as simulation of growth and yield and to understand timber assortments. Accurate and reliable prediction of tree diameter distributions is critical for optimizing forest structure compositions, scheduling silvicultural operations and promoting sustainable management. In this study, we investigated the potential of airborne Light Detection and Ranging (LiDAR) data for predicting tree diameter distributions using a bimodal finite mixture model (FMM) and a multimodal k-nearest neighbor (KNN) model (compared to the unimodal Weibull model (UWM)) over a subtropical planted forest in southern China. To do so, we first evaluated the capability of various LiDAR predictions (i.e., the bimodality coefficient (BC) and Lorenz-based indicators) to stratify forest structural types into unimodal and multimodal stands. Once the best LiDAR prediction for the differentiation was determined, the parameters of UWM (in non-specific and species-specific models) and FMM (in structure-specific models) were estimated by LiDAR-derived metrics and the tree diameter distributions of stands were generated by the estimated LiDAR parameters. When KNN was applied for constructing diameter distributions, optimal KNN strategies, including number of neighbors k, response configurations and imputation methods (i.e., Most Similar Neighbor (MSN) and Random Forest (RF)) for different species were heuristically determined. Finally, the predictive performance of estimated LiDAR the parameters of UWM, FMM and KNN for predicting diameter distributions were assessed. The results showed that LiDAR-predicted Lorenz-based indicators performed best for differentiation. Parameters of UWM and FMM were predicted well and the species-specific models had higher accuracies than the non-specific models. Overall, RF imputation from KNN with an optimal response set (i.e., DBH) were was stable than MSN imputation when k = 5 neighbors. In addition, the inclusion of bimodal FMM for differentiated all plots generally produced a more accurate result (Mean e_R = 40.85, Mean e_P = 0.20) than multimodal KNN (Mean e_R = 52.19, Mean e_P = 0.26), whereas the UWM produced the lowest performance (Mean e_R = 52.31, Mean e_P = 0.26). This study demonstrated the benefits of multimodal models with LiDAR for estimating diameter distributions for supporting forest inventory and sustainable forest management in subtropical planted forests.

Monitoring and evaluating floods is crucial for geographic information systems (GISs). The low backscattering coefficient of flood surfaces makes them appear darker in synthetic aperture radar (SAR) images, which is advantageous for flood segmentation. In recent years, with the advancement of deep learning, semantic segmentation of flood regions in SAR images using convolutional neural networks (CNNs) has become a focal point in earth observation tasks. However, challenges, such as the similarity between the texture and shape of flood regions and the background in SAR images, the segmentation discontinuity at flood edges, the loss of information on small water bodies, and the variability of flood regions in different scales and morphologies, remain inadequately addressed. To tackle these issues, we propose a transformer model based on an encoder–decoder architecture for precise segmentation of flooded areas in SAR images. First, we utilize the mix transformer as the model’s encoder to compensate for CNNs’ limitations in global modeling, enhancing the discrimination of similar features in the image. Second, we introduce a noise filtering module (NFM) to filter redundant semantic information within low-level feature maps during the feature fusion process, thereby mitigating segmentation discontinuities at flood edges and the loss of small water body information. Finally, we design a multiscale depth-wise convolution module (MDCM) to boost the network’s multiscale feature representation capability, addressing issues arising from flood scale variability. Experimental results demonstrate that our method surpasses other mainstream approaches on the Sen1Floods11 dataset.

Remote-sensing-assisted estimates of Moso bamboo forest structure are imperative for supporting sustainable forest management (SFM). Passive sensors have limited usages in characterizing continuous vertical structures of Moso bamboos since they have difficulty in penetrating dense upper canopies. Airborne full-waveform (FWF) Light Detection and Ranging (LiDAR) technology has shown significant potentials in providing an improved representation of 3-D structures in much denser canopies, while the capability of FWF to assess the structure of the unique Moso bamboo forests is less known. Many previous studies commonly assume perfectly vertical waveforms and do not account for slanted penetrations of waveforms in canopies. This study presented a framework for investigating the availability of FWF to assess subtropical Moso bamboo forest structures. We used a physical-based approach for radiometric calibration and an advanced voxel-based pseudo-vertical waveform approach to assign waveforms into voxels and reconstruct composite waveforms for extracting FWF metrics. Second, the differences in FWF-derived metrics in response to canopy structures across various management strategies were compared. Finally, the capability of FWF metrics for estimating bamboo structural parameters was evaluated by parametric and nonparametric models. The results showed that the FWF metrics varied significantly ( $p$ -values < 0.05) in response to different management strategies. In general, nonparametric approaches (locally weighted linear regression and k-nearest neighbor) outperformed parametric approaches (multiple linear regression). This study demonstrated that the pseudo-vertical waveform approach could improve the performances of FWF metrics for characterizing 3-D Bamboo forest structure and provide new insights on accurately estimating bamboo structural parameters across different management strategies.