Search

Semi-supervised multi-view learning has been an important research topic due to its capability to exploit complementary information from unlabeled multi-view data. This work proposes MMatch, a new semi-supervised discriminative representation learning method for multi-view classification. Unlike existing multi-view representation learning methods that seldom consider the negative impact caused by particular views with unclear classification structures (weak discriminative views). MMatch jointly learns view-specific representations and class probabilities of training data. The representations concatenated to integrate multiple views’ information to form a global representation. Moreover, MMatch performs the smoothness constraint on the class probabilities of the global representation to improve pseudo labels, whereas the pseudo labels regularize the structure of view-specific representations. A discriminative global representation is mined with the training process, and the negative impact of weak discriminative views is overcome. Besides, MMatch learns consistent classification while preserving diverse information from multiple views. Experiments on several multi-view datasets demonstrate the effectiveness of MMatch. [ABSTRACT FROM AUTHOR]

The self-attention mechanism has been empirically shown its effectiveness in a wide range of computer vision applications. However, it is usually criticized for the expensive computation cost. Although some revised methods are proposed in the recent past, they are not maturely applicable to remote sensing scene (RSS) images. To address this problem, in this article, we propose a simple yet effective context acquisition module, named thrifty attention, which can capture the long-range dependence efficiently and effectively. Moreover, a recurrent version for thrifty attention, termed recurrent thrifty attention (RTA), is further proposed to take the long-range multihop communications in space–time for RSS images. RTA is a general global contextual information acquisition module that can be used in any hierarchy of deep convolutional neural networks. To demonstrate its superiority, we deploy it to the classical ResNet and establish our proposed RTA Network (RTANet). Extensive experiments are carried out on two levels of the RSS recognition tasks, i.e., the image-level RSS classification and the instance-level RSS object detection. Compared with the standard self-attention mechanism, RTA can reduce at most 0.43 M model parameters while increasing a slight of model floating-point operations per second (FLOPs). Furthermore, results on RSS classification and object detection further verify the accuracy superiority of RTANet. [ABSTRACT FROM AUTHOR]

Forest canopy cover (CC) directly and indirectly influences various processes of forest ecosystems. Airborne light detection and ranging (LiDAR) can be used to characterize forest spatial structures and further obtain estimates of forest CC. However, nonreturn laser pulses from targets of interest impact the estimation accuracy of forest CC. The objective of this article was to develop a novel method of estimating the nonreturn laser pulses to improve the estimation accuracy of forest CC using LiDAR data. The improved models for estimating forest CC were developed by introducing the loss ratio of laser pulses and a CC coefficient into the original models. The forest CC reference data were collected and used to validate the forest CC estimates. The results show that the loss ratio for forested areas was much higher than that for open ground areas. The range between the sensor and a target was a crucial factor that caused the loss of returns. The relationship between the range and the loss ratio was nonlinear in both open ground and forested areas. Compared with the original models, the improved models combining the loss ratio and the CC coefficient statistically significantly increased the estimation accuracy of the forest CC. Moreover, the forest CC estimates from the canopy height model (CHM) were more accurate than those from the height normalized point cloud (NPC) data. In addition, the simplified models were more generalized than the other models. This article is novel and has great potential to improve mapping of forest CC. [ABSTRACT FROM AUTHOR]

Recently, L 1 -norm-based non-greedy linear discriminant analysis (NLDA-L 1) for feature extraction has been shown to be effective for dimensionality reduction, which obtains projection vectors by a non-greedy algorithm. However, it usually acquires unsatisfactory performances due to the utilization of L 1 -norm distance measurement. Therefore, in this brief paper, we propose a flexible non-greedy discriminant subspace feature extraction method, which is an extension of NLDA-L 1 by maximizing the ratio of L p -norm inter-class dispersion to intra-class dispersion. Besides, we put forward a powerful iterative algorithm to solve the resulted objective function and also conduct theoretical analysis on the algorithm. Finally, experimental results on image databases show the effectiveness of our method [ABSTRACT FROM AUTHOR]

Nonlinear mixed-effects (NLME) models have become popular in various disciplines over the past several decades. However, the existing methods for parameter estimation implemented in standard statistical packages such as SAS and R/S-Plus are generally limited to single- or multi-level NLME models that only allow nested random effects and are unable to cope with crossed random effects within the framework of NLME modeling. In this study, we propose a general formulation of NLME models that can accommodate both nested and crossed random effects, and then develop a computational algorithm for parameter estimation based on normal assumptions. The maximum likelihood estimation is carried out using the first-order conditional expansion (FOCE) for NLME model linearization and sequential quadratic programming (SQP) for computational optimization while ensuring positive-definiteness of the estimated variance-covariance matrices of both random effects and error terms. The FOCE-SQP algorithm is evaluated using the height and diameter data measured on trees from Korean larch (L. olgensis var. Changpaiensis) experimental plots as well as simulation studies. We show that the FOCE-SQP method converges fast with high accuracy. Applications of the general formulation of NLME models are illustrated with an analysis of the Korean larch data. [ABSTRACT FROM AUTHOR]

Recently, L1-norm distance measure based Linear Discriminant Analysis (LDA) techniques have been shown to be robust against outliers. However, these methods have no guarantee of obtaining a satisfactory-enough performance due to the insufficient robustness of L1-norm measure. To mitigate this problem, inspired by recent works on Lp-norm based learning, this paper proposes a new discriminant method, called Lp- and Ls-Norm Distance Based Robust Linear Discriminant Analysis (FLDA-Lsp). The proposed method achieves robustness by replacing the L2-norm within- and between-class distances in conventional LDA with Lp- and Ls-norm ones. By specifying the values of p and s, many of previous efforts can be naturally expressed by our objective. The requirement of simultaneously maximizing and minimizing a number of Lp- and Ls-norm terms results in a difficulty to the optimization of the formulated objective. As one of the important contributions of this paper, we design an efficient iterative algorithm to address this problem, and also conduct some insightful analysis on the existence of local minimum and the convergence of the proposed algorithm. Theoretical insights of our method are further supported by promising experimental results on several images databases. [ABSTRACT FROM AUTHOR]

Microclimate ecology is attracting renewed attention because of its fundamental importance in understanding how organisms respond to climate change. Many hot issues can be investigated in desert ecosystems, including the relationship between species distribution and environmental gradients (e.g., elevation, slope, topographic convergence index, and solar insolation). Species Distribution Models (SDMs) can be used to understand these relationships. We used data acquired from the important desert plant Nitraria tangutorum Bobr. communities and desert topographic factors extracted from LiDAR (Light Detection and Ranging) data of one square kilometer in the inner Mongolia region of China to develop SDMs. We evaluated the performance of SDMs developed with a variety of both the parametric and nonparametric algorithms (Bioclimatic Modelling (BIOCLIM), Domain, Mahalanobi, Generalized Linear Model, Generalized Additive Model, Random Forest (RF), and Support Vector Machine). The area under the receiver operating characteristic curve was used to evaluate these algorithms. The SDMs developed with RF showed the best performance based on the area under curve (0.7733). We also produced the Nitraria tangutorum Bobr. distribution maps with the best SDM and suitable habitat area of the Domain model. Based on the suitability map, we conclude that Nitraria tangutorum Bobr. is more suited to southern part with 0–20 degree slopes at an elevation of approximately 1010 m. This is the first attempt of modelling the effects of topographic heterogeneity on the desert species distribution on a small scale. The presented SDMs can have important applications for predicting species distribution and will be useful for preparing conservation and management strategies for desert ecosystems on a small scale. [ABSTRACT FROM AUTHOR]

How trees allocate photosynthetic products to primary height growth and secondary radial growth reflects their capacity to best use environmental resources. Despite substantial efforts to explore tree height–diameter relationship empirically and through theoretical modeling, our understanding of the biological mechanisms that govern this phenomenon is still limited. By thinking of stem woody biomass production as an ecological system of apical and lateral growth components, we implement game theory to model and discern how these two components cooperate symbiotically with each other or compete for resources to determine the size of a tree stem. This resulting allometry game theory is further embedded within a genetic mapping and association paradigm, allowing the genetic loci mediating the carbon allocation of stemwood growth to be characterized and mapped throughout the genome. Allometry game theory was validated by analyzing a mapping data of stem height and diameter growth over perennial seasons in a poplar tree. Several key quantitative trait loci were found to interpret the process and pattern of stemwood growth through regulating the ecological interactions of stem apical and lateral growth. The application of allometry game theory enables the prediction of the situations in which the cooperation, competition or altruism is an optimal decision of a tree to fully use the environmental resources it owns. [ABSTRACT FROM AUTHOR]

Estimating individual tree diameters at breast height (DBH) from delineated crowns and tree heights on the basis of airborne light detection and ranging (LiDAR) data provides a good opportunity for large-scale forest inventory. Generally, ground-based measurements are more accurate, but LiDAR data and derived DBH values can be obtained over larger areas for a relatively smaller cost if a right procedure is developed. A nonlinear least squares (NLS) regression is not an appropriate approach to predict the aboveground biomass (AGB) of individual trees from the estimated DBH because both the response variable and the regressor are subject to measurement errors. In this study, a system of compatible individual tree DBH and AGB error-in-variable models was developed using error-in-variable regression techniques based on both airborne LiDAR and field-measured datasets of individual Picea crassifolia Kom. trees, collected in northwestern China. Two parameter estimation algorithms, i.e., the two-stage error-in-variable model (TSEM) and the nonlinear seemingly unrelated regression (NSUR), were proposed for estimating the parameters in the developed system of compatible individual tree DBH and AGB error-in-variable models. Moreover, two model structures were applied to estimate AGB for comparison purposes: NLS with AGB estimation depending on DBH (NLS&DD) and NLS with AGB estimation not depending on DBH (NLS&NDD). The results showed that both TSEM and NSUR led to almost the same parameter estimates for the developed system. Moreover, the developed system effectively accounted for the inherent correlation between DBH and AGB as well as for the effects of measurement errors in the DBH on the predictions of AGB, whereas NLS&DD and NLS&NDD did not. A leave-one-out cross-validation indicated that the prediction accuracy of the developed system of compatible individual tree DBH and AGB error-in-variable models with NSUR was the highest among those estimated by the four methods evaluated, but, statistically, the accuracy improvement was not significantly different from zero. The main reason might be that, except for the measurement errors, other source errors were ignored in the modeling. This study implies that, overall, the proposed method provides the potential to expand the estimations of both DBH and AGB from individual trees to stands by combining the error-in-variable modeling and LiDAR data and improve their estimation accuracies, but its application needs to be further validated by conducting a systematical uncertainty analysis of various source errors in a future study. [ABSTRACT FROM AUTHOR]

Adaptive cluster sampling (ACS) has been widely used for data collection of environment and natural resources. However, the randomness of its final sample size often impedes the use of this method. To control the final sample sizes, in this study, a -step ACS based on Horvitz-Thompson (HT) estimator was developed and an unbiased estimator was derived. The -step ACS-HT was assessed first using a simulated example and then using a real survey for numbers of plants for three species that were characterized by clustered and patchily spatial distributions. The effectiveness of this sampling design method was assessed in comparison with ACS Hansen-Hurwitz (ACS-HH) and ACS-HT estimators, and -step ACS-HT estimator. The effectiveness of using different -step sizes was also compared. The results showed that -step ACS-HT estimator was most effective and ACS-HH was the least. Moreover, stable sample mean and variance estimates could be obtained after a certain number of steps, but depending on plant species. -step ACS without replacement was slightly more effective than that with replacement. In -step ACS, the variance estimate of one-step ACS is much larger than other -step ACS (), but it is smaller than ACS. This implies that -step ACS is more effective than traditional ACS, besides, the final sample size can be controlled easily in population with big clusters. [ABSTRACT FROM AUTHOR]

Drill feed speed significantly affects the measurement accuracy and efficiency of the micro drill resistance instrument. Generally, different speeds are set according to the density of the wood to be drilled. It is necessary to convert the resistance data measured at different drill feed speeds into resistance data at a uniform speed to properly analyze resistance data. In this study, drill resistance data for a Paulownia wood block was measured with a self-made micro drill resistance instrument at different drill feed speeds. We found that the drill resistance is positively correlated with changes in its feed speed and the natural logarithm of change times for feed speed. We developed a conversion algorithm for the micro drill resistance instrument measurements at different feed speeds. The accuracy of the conversion algorithm is up to 95%. The algorithm can be used to convert the drill resistance of Paulownia wood measured at different drill feed speeds; it has reference value for the mutual conversion of other tree species' drill resistance data measured at different feed speeds. This work may provide a feasible solution to improving micro drill resistance instrument accuracy when drill feed speed error is high. [ABSTRACT FROM AUTHOR]

Microclimate ecology is attracting renewed attention because of its fundamental importance in understanding how organisms respond to climate change. Many hot issues can be investigated in desert ecosystems, including the relationship between species distribution and environmental gradients (e.g., elevation, slope, topographic convergence index, and solar insolation). Species Distribution Models (SDMs) can be used to understand these relationships. We used data acquired from the important desert plant Nitraria tangutorum Bobr. communities and desert topographic factors extracted from LiDAR (Light Detection and Ranging) data of one square kilometer in the inner Mongolia region of China to develop SDMs. We evaluated the performance of SDMs developed with a variety of both the parametric and nonparametric algorithms (Bioclimatic Modelling (BIOCLIM), Domain, Mahalanobi, Generalized Linear Model, Generalized Additive Model, Random Forest (RF), and Support Vector Machine). The area under the receiver operating characteristic curve was used to evaluate these algorithms. The SDMs developed with RF showed the best performance based on the area under curve (0.7733). We also produced the Nitraria tangutorum Bobr. distribution maps with the best SDM and suitable habitat area of the Domain model. Based on the suitability map, we conclude that Nitraria tangutorum Bobr. is more suited to southern part with 0–20 degree slopes at an elevation of approximately 1010 m. This is the first attempt of modelling the effects of topographic heterogeneity on the desert species distribution on a small scale. The presented SDMs can have important applications for predicting species distribution and will be useful for preparing conservation and management strategies for desert ecosystems on a small scale. [ABSTRACT FROM AUTHOR]

Proximal support vector machine via generalized eigenvalues (GEPSVM) is one of the most successful methods for classification problems. However, GEPSVM is vulnerable to outliers since it learns classifiers based on the squared L 2 -norm distance without a specific strategy to deal with the outliers. Motivated by existing studies that improve the robustness of GEPSVM via the L 1 -norm distance or not-squared L 2 -norm distance formulation, a novel GEPSVM formulation that minimizes the p -order of L 2 -norm distance is proposed, namely, L 2,p -GEPSVM. This formulation weakens the negative effects of both light and heavy outliers in the data. An iterative algorithm is designed to solve the general L 2,p -norm distance minimization problems and rigorously prove its convergence. In addition, we adjust the parameters of L 2,p -GEPSVM to balance the accuracy and training time. This is especially useful for larger datasets. Extensive results indicate that the L 2,p -GEPSVM improves the classification performance and robustness in various experimental settings. [ABSTRACT FROM AUTHOR]

In this study, an individual tree crown ratio (CR) model was developed with a data set from a total of 3134 Mongolian oak (Quercus mongolica) trees within 112 sample plots allocated in Wangqing Forest Bureau of northeast China. Because of high correlation among the observations taken from the same sampling plots, the random effects at levels of both blocks defined as stands that have different site conditions and plots were taken into account to develop a nested two-level nonlinear mixed-effect model. Various stand and tree characteristics were assessed to explore their contributions to improvement of model prediction. Diameter at breast height, plot dominant tree height and plot dominant tree diameter were found to be significant predictors. Exponential model with plot dominant tree height as a predictor had a stronger ability to account for the heteroskedasticity. When random effects were modeled at block level alone, the correlations among the residuals remained significant. These correlations were successfully reduced when random effects were modeled at both block and plot levels. The random effects from the interaction of blocks and sample plots on tree CR were substantially large. The model that took into account both the block effect and the interaction of blocks and sample plots had higher prediction accuracy than the one with the block effect and population average considered alone. Introducing stand density into the model through dummy variables could further improve its prediction. This implied that the developed method for developing tree CR models of Mongolian oak is promising and can be applied to similar studies for other tree species. [ABSTRACT FROM AUTHOR]

Distance Metric Learning for Large Margin Nearest Neighbor (LMNN), as a classic distance metric learning (DML) method, has attracted much attention among researchers. However, it, like most of the existing DML methods, cannot be guaranteed to achieve independent and shared feature subspaces from multiple sources or different feature subsets, such that much statistical feature information is ignored in model learning. In this paper, we propose a novel DML model, called Multi-view DML Based on Independent and Shared Feature Subspace (MVML-ISFS), which learns multiple distance metrics to unify the information from multiple views. The proposed method finds a distance metric for each view in an independent feature space to preserve its specific property as well as a sparse representation related to the distance metrics from distinct views in a shared feature space to remain their common properties. The objective problem of MVML-ISFS is formulated based on LMNN, thus encouraging a large margin for each view that makes the distance between each of the same class pairs of samples be smaller than that between each of the different class pairs of samples. The proposed model in MVML-ISFS involves multivariate variables, which are optimized by a gradient descent strategy. The experimental results show the effectiveness of our MVML-ISFS on remote sensing, face, forest fire, and UCI datasets. [ABSTRACT FROM AUTHOR]

Accurate and real-time prediction of short-term traffic states is a crucial research topic in modern intelligent transportation systems. However, effectively modeling traffic state predictions is difficult due to the complicated characteristics of stochastic and dynamic traffic processes. In addition, collected traffic data are typically influenced by external factors (e.g. , weather, traffic jams and accidents), leading to errors and missing data. This increases the difficulty in selecting an effective method for predicting traffic conditions over time. To improve the traffic state prediction performance and alleviate the negative effect of traffic data with outliers, a novel multiclass classification least squares twin support vector machine model based on the robust L 2,p -norm (0 < p ≤ 2) distance, known as PLSTSVM, was proposed. We adjusted the PLSTSVM parameters to balance the prediction accuracy and training time. To solve the optimization problem of the PLSTSVM, an iterative algorithm was developed, which has great potential for solving other optimization problems. In addition, an integrated classification indicator system based on speed, traffic volume, occupancy rate and ample degree was used, increasing the feasibility of the traffic state analysis. To improve the learning and generalization abilities of the nonlinear PLSTSVM, we combined the polynomial kernel function and the radial basis function to construct a hybrid kernel function. The results on two real traffic datasets demonstrate that our model yields better prediction performance and robustness than other competitors, which make unsatisfactory predictions. • A robust multi-class SVM is proposed to alleviate the effect of traffic data with outliers. • An iterative algorithm is designed to solve non-smooth L 2,p -norm optimization problem. • A novel classification indicator (ample degree) is utilized to forecast the traffic state. • A hybrid kernel function is built by combining polynomial and Gaussian kernel for multi-class SVM. [ABSTRACT FROM AUTHOR]

Small rodents in general and the multimammate rat Apodemus agrarius in particular, damage crops and cause major economic losses in China. Therefore, accurate predictions of the population size of A. agrarius and an efficient control strategy are urgently needed. We developed a population dynamics model by applying a Leslie matrix method, and a capture model based on optimal harvesting theory for A. agrarius. Our models were parametrized using demographic estimates from a capture-mark-recapture (CMR) study conducted on the Qinshui Forest Farm in Northwestern China. The population dynamics model incorporated 12 equally balanced age groups and included immigration and emigration parameters. The model was evaluated by assessing the predictions for four years based on the known starting population in 2004 from the 2004-2007 CMR data. The capture model incorporated two functional age categories (juvenile and adult) and used density-dependent and density-independent factors. The models were used to assess the effect of rodent control measures between 2004 and 2023 on population dynamics and the resulting numbers of rats. Three control measures affecting survival rates were considered. We found that the predicted population dynamics of A. agrarius between 2004 and 2007 compared favorably with the observed population dynamics. The models predicted that the population sizes of A. agrarius in the period between 2004 and 2023 under the control measure applied in August 2004 were very similar to the optimal population sizes, and no significant difference was found between the two population sizes. We recommend using the population dynamics and capture models based on CMR-estimated demographic schedules for rodent, provided these data are available. The models that we have developed have the potential to play an important role in predicting the effects of rodent management and in evaluating different control strategies. [ABSTRACT FROM AUTHOR]

Zero-Shot Learning (ZSL) aims to employ seen images and their related semantics to identify unseen images through knowledge transfer. Among past numerous methods, the generative methods are more prominent and achieve better results than other methods. However, we find the input for generating samples is too monotonous, there are only semantics of each class and artificially defined noise, which makes the generated visual features non-discriminative and the classifier cannot effectively distinguish them. In order to solve this problem, we propose a novel approach with cascade Generative Adversarial Network (GAN) to generate discriminative and representative features. In this method, we define a latent space where the features from different categories are orthogonal to each other and the generator for this latent space is learned with a Wasserstein GAN. In addition, in order to make up for the deficiency that the features in this latent space cannot accurately simulate the true distribution of species, we utilize another Wasserstein GAN or Cramér GAN cascaded with the previous one to generate more discriminative and representative visual features. In this way, we can not only expand the content used as input in the generation process, but also make the final generated visual features clear and separable under the influence of latent spatial orthogonality. Extensive experiments on five benchmark datasets, i.e. , AWA1, AWA2, CUB, SUN and APY, demonstrate that our proposed method can outperform most of the state-of-the-art methods on both conventional and generalized zero-shot learning settings. • Generating more representative latent and visual features to alleviate domain shift. • Features of different categories are more discriminative through orthogonal projection. • It can outperform the SOTA methods on five popular datasets. [ABSTRACT FROM AUTHOR]

Nonlinear mixed-effects (NLME) models are flexible enough to handle repeated-measures data from various disciplines. In this article, we propose both maximum-likelihood and restricted maximum-likelihood estimations of NLME models using first-order conditional expansion (FOCE) and the expectation–maximization (EM) algorithm. The FOCE-EM algorithm implemented in the ForStat procedure SNLME is compared with the Lindstrom and Bates (LB) algorithm implemented in both the SAS macro NLINMIX and the S-Plus/R function nlme in terms of computational efficiency and statistical properties. Two realworld data sets an orange tree data set and a Chinese fir (Cunninghamia lanceolata) data set, and a simulated data set were used for evaluation. FOCE-EM converged for all mixed models derived from the base model in the two realworld cases, while LB did not, especially for the models in which random effects are simultaneously considered in several parameters to account for between-subject variation. However, both algorithms had identical estimated parameters and fit statistics for the converged models. We therefore recommend using FOCE-EM in NLME models, particularly when convergence is a concern in model selection. [ABSTRACT FROM AUTHOR]

Desert vegetation is an important part of arid and semi-arid areas, which plays an important role in preventing wind and fixing sand, conserving water and soil, maintaining the balanced ecosystem. Therefore, mapping the vegetation accurately is necessary to conserve rare desert plants in the fragile ecosystems that are easily damaged and slow to recover. In mapping desert vegetation, there are some weaknesses by using traditional digital classification algorithms from high resolution data. The traditional approach is to use spectral features alone, without spatial information. With the rapid development of drones, cost-effective visible light data is easily available, and the data would be non-spectral but with spatial information. In this study, a method of mapping the desert rare vegetation was developed based on the pixel classifiers and use of Random Forest (RF) algorithm with the feature of VDVI and texture. The results indicated the accuracy of mapping the desert rare vegetation were different with different methods and the accuracy of the method proposed was higher than the traditional method. The most commonly used decision rule in the traditional method, named Maximum Likelihood classifier, produced overall accuracy (76.69%). The inclusion of texture and VDVI features with RGB (Red Green Blue) data could increase the separability, thus improved the precision. The overall accuracy could be up to 84.19%, and the Kappa index with 79.96%. From the perspective of features, VDVI is less important than texture features. The texture features appeared more important than spectral features in desert vegetation mapping. The RF method with the RGB+VDVI+TEXTURE would be better method for desert vegetation mapping compared with the common method. This study is the first attempt of classifying the desert vegetation based on the RGB data, which will help to inform management and conservation of Ulan Buh desert vegetation. [ABSTRACT FROM AUTHOR]

Multiview Generalized Eigenvalue Proximal Support Vector Machines (MvGSVMs) is an effective multi-view classification algorithm, which effectively combines multi-view learning and classification. Then it was found that in the classification learning task, the classifier combined with multi-view learning has a better classification effect than considering only a single view. In order to utilize the multi-view learning framework more fully and accurately, we further research this. We explore the internal relationship between different views between samples to replace the method of connecting different views through distance combinations. We propose a new method named Multi-view Generalized Support Vector Machine via Mining the Inherent Relationship between Views (MRMvGSVM). At the same time, we use the L2,1-norm constraint relationship matrix as a multi-view regularization term to select the most relevant sample data from different views. It not only helps to improve the accuracy of classification but also reduces the influence of extraneous factors to a certain extent and improves the robustness of the algorithm. The effectiveness of the algorithm is proved by theory and experiments on UCI, and Face and Fire Smoke image datasets. [ABSTRACT FROM AUTHOR]

Forest canopy height is one of the most important spatial characteristics for forest resource inventories and forest ecosystem modeling. Light detection and ranging (LiDAR) can be used to accurately detect canopy surface and terrain information from the backscattering signals of laser pulses, while photogrammetry tends to accurately depict the canopy surface envelope. The spatial differences between the canopy surfaces estimated by LiDAR and photogrammetry have not been investigated in depth. Thus, this study aims to assess LiDAR and photogrammetry point clouds and analyze the spatial differences in canopy heights. The study site is located in the Jigongshan National Nature Reserve of Henan Province, Central China. Six data sets, including one LiDAR data set and five photogrammetry data sets captured from an unmanned aerial vehicle (UAV), were used to estimate the forest canopy heights. Three spatial distribution descriptors, namely, the effective cell ratio (ECR), point cloud homogeneity (PCH) and point cloud redundancy (PCR), were developed to assess the LiDAR and photogrammetry point clouds in the grid. The ordinary neighbor (ON) and constrained neighbor (CN) interpolation algorithms were used to fill void cells in digital surface models (DSMs) and canopy height models (CHMs). The CN algorithm could be used to distinguish small and large holes in the CHMs. The optimal spatial resolution was analyzed according to the ECR changes of DSMs or CHMs resulting from the CN algorithms. Large negative and positive variations were observed between the LiDAR and photogrammetry canopy heights. The stratified mean difference in canopy heights increased gradually from negative to positive when the canopy heights were greater than 3 m, which means that photogrammetry tends to overestimate low canopy heights and underestimate high canopy heights. The CN interpolation algorithm achieved smaller relative root mean square errors than the ON interpolation algorithm. This article provides an operational method for the spatial assessment of point clouds and suggests that the variations between LiDAR and photogrammetry CHMs should be considered when modeling forest parameters. [ABSTRACT FROM AUTHOR]

Rapidly advancing airborne laser scanning technology has become greatly useful to estimate tree- and stand-level variables at a large scale using high spatial resolution data. Compared with that of ground measurements, the accuracy of the inferred information of diameter at breast height (DBH) from a remotely sensed database and the models developed with traditional regression approaches (e.g., ordinary least square regression) may not be sufficient. Thus, this regression approach is no longer appropriate to develop accurate models and predict DBH from remotely sensed-related variables because DBH is subject to the random effects of forest stands. This study developed a generalized nonlinear mixed-effects DBH estimation model from remotely sensed imagery data. The light detection and ranging (LiDAR)-derived stand canopy density, crown projection area, and tree height were used as predictors in the DBH estimation model. These variables can be more readily measured over an extensive forest area with higher accuracy compared to the conventional field-based methods. The airborne LiDAR data for a total of 402 Picea crassifolia Kom trees on a sample plot that were divided into 16 sub-sample plots and located in the most important distribution region of western China were used. The leave-one sub-sample plot-out cross-validation method was applied to evaluate the model's prediction accuracy. The results indicated that the random effects of the sub-sample plot on the prediction of DBH were large and their inclusion into the DBH model significantly improved the prediction accuracy. The prediction accuracy of the proposed model at the mean (M) response was also substantially improved relative to the accuracy obtained from the base model. Among several tree selection alternatives evaluated, a sample size of the two largest trees per sub-sample plot used in estimating the random effects showed a significantly higher accuracy compared to other sampling alternatives. This sample size would balance both the measurement cost and potential prediction errors. The nonlinear mixed-effects DBH estimation model at the M response can also be applied if obtaining the estimates of individual tree DBH with a relatively lower cost, and a lower prediction accuracy was the purpose of the study. [ABSTRACT FROM AUTHOR]

Research on the inversion of forest aboveground biomass based on airborne light detection and ranging (LiDAR) data focuses on finding the relationship between the two, such as established linear or nonlinear models. However, these models may have poorer estimation accuracy for tree-components biomass and cannot guarantee the additivity of each component. Therefore, we aimed to develop an error-in-variable biomass model system that ensures both the compatibility of the individual tree component biomass with the diameter at breast height and the additivity of component biomass. The system we developed used the airborne LiDAR data and field-measured data of principis-rupprechtii (Larix gmelinii var.) trees, collected from north China. Our model system not only ensured the additivity of nonlinear biomass models, it also accounted for the impact of measurement errors. We first selected the airborne LiDAR-derived variable with the highest contribution to the biomass of each component and then developed an inversion model system with that variable as an independent variable and with the biomass of each component as the dependent variable using allometric functions. Moreover, two model estimation methods, two-stage error (TSEM) and nonlinear seemingly unrelated regression (NSUR) with one-step, two-step, and summation methods, were also applied, and their performances were compared. The results showed that both NSUR-one-step and TSEM-one-step led to similar parameter estimates and performance for a system, and the fitting accuracy of a model system was not very attractive. The variance function included in a model system reduced the heteroscedasticity effectively and improved the model accuracy. Overall, this study successfully combined the error-in-variable modeling with the airborne LiDAR data, proposed methods that can be used for the extension of component biomass from an individual tree to a stand and that might improve the estimation accuracy of carbon storage. A compatible model system can be further improved if various sources of error in the variables are identified, and their impacts on the system are effectively accounted for. [ABSTRACT FROM AUTHOR]

Aboveground biomass (AGB) of shrub communities in the desert is a basic quantitative characteristic of the desert ecosystem and an important index to measure ecosystem productivity and monitor desertification. An accurate and efficient method of predicting the AGB of a shrub community is essential for studying the spatial patterns and ecological functions of the desert region. Even though there are several entries in the literature on the AGB prediction of desert shrub communities using remote sensing data, the applicability and accuracy of airborne LiDAR data and prediction methods have not been well studied. We first extracted the elevation, density and intensity variables based on the airborne LiDAR, and then sample plot-level AGB prediction models were constructed using the parametric regression (nonlinear regression) and nonparametric methods (Random Forest, Support Vector Machine, K-Nearest Neighbor, Gradient Boosting Machine, and Multivariate adaptive regression splines). We evaluated accuracies of all the AGB prediction models we developed based on the fit statistics. Results showed that: (1) the elevation, density and intensity variables obtained from LiDAR point cloud data effectively predicted the AGB of the desert shrub community at a sample plot level, (2) the kappa coefficient of nonlinear mixed-effects (NLME) model obtained was 0.6977 with an improvement by 13% due to the random effects included into the model, and (3) the nonparametric model, such as Support Vector Machine showed the best fit statistics (R2 = 0.8992), which is 28% higher than the NLME-model, and effectively reduced the heteroscedasticity. The AGB prediction model presented in this paper, which is based on the airborne LiDAR data and machine learning algorithm, will provide a valuable tool to the managers and researchers for evaluating desert ecosystem productivity and monitoring desertification. [ABSTRACT FROM AUTHOR]

Background: Fast and accurate forest aboveground biomass (AGB) estimation and mapping is the basic work of forest management and ecosystem dynamic investigation, which is of great significance to evaluate forest quality, resource assessment, and carbon cycle and management. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), as one of the latest launched spaceborne light detection and ranging (LiDAR) sensors, can penetrate the forest canopy and has the potential to obtain accurate forest vertical structure parameters on a large scale. However, the along-track segments of canopy height provided by ICESat-2 cannot be used to obtain comprehensive AGB spatial distribution. To make up for the deficiency of spaceborne LiDAR, the Sentinel-2 images provided by google earth engine (GEE) were used as the medium to integrate with ICESat-2 for continuous AGB mapping in our study. Ensemble learning can summarize the advantages of estimation models and achieve better estimation results. A stacking algorithm consisting of four non-parametric base models which are the backpropagation (BP) neural network, k-nearest neighbor (kNN), support vector machine (SVM), and random forest (RF) was proposed for AGB modeling and estimating in Saihanba forest farm, northern China. Results: The results show that stacking achieved the best AGB estimation accuracy among the models, with an R2 of 0.71 and a root mean square error (RMSE) of 45.67 Mg/ha. The stacking resulted in the lowest estimation error with the decreases of RMSE by 22.6%, 27.7%, 23.4%, and 19.0% compared with those from the BP, kNN, SVM, and RF, respectively. Conclusion: Compared with using Sentinel-2 alone, the estimation errors of all models have been significantly reduced after adding the LiDAR variables of ICESat-2 in AGB estimation. The research demonstrated that ICESat-2 has the potential to improve the accuracy of AGB estimation and provides a reference for dynamic forest resources management and monitoring. [ABSTRACT FROM AUTHOR]

Since remote sensing images of post-fire vegetation are characterized by high resolution, multiple interferences, and high similarities between the background and the target area, it is difficult for existing methods to detect and segment the burned area in these images with sufficient speed and accuracy. In this article, we apply salient object detection (SOD) to burned area segmentation (BAS), the first time this has been done, and propose an efficient burned area segmentation network (BASNet) to improve the performance of unmanned aerial vehicle (UAV) high-resolution image segmentation. BASNet comprises positioning module and refinement module. The positioning module efficiently extracts high-level semantic features and general contextual information via global average pooling layer and convolutional block (CB) to determine the coarse location of the salient region. The refinement module adopts the CB attention module to effectively discriminate the spatial location of objects. In addition, to effectively combine edge information with spatial location information in the lower layer of the network and the high-level semantic information in the deeper layer, we design the residual fusion module to perform feature fusion by level to obtain the prediction results of the network. Extensive experiments on two UAV datasets collected from Chongli in China and Andong in South Korea, demonstrate that our proposed BASNet significantly outperforms the state-of-the-art SOD methods quantitatively and qualitatively. BASNet also achieves a promising prediction speed for processing high-resolution UAV images, thus providing wide-ranging applicability in post-disaster monitoring and management. [ABSTRACT FROM AUTHOR]

Fractional vegetation cover (FVC) is an important indicator of ecosystem changes. Both satellite remote sensing and ground measurements are common methods for estimating FVC. However, desert vegetation grows sparsely and scantly and spreads widely in desert regions, making it challenging to accurately estimate its vegetation cover using satellite data. In this study, we used RGB images from two periods: images from 2006 captured with a small, light manned aircraft with a resolution of 0.1 m and images from 2019 captured with an unmanned aerial vehicle (UAV) with a resolution of 0.02 m. Three pixel-based machine learning algorithms, namely gradient enhancement decision tree (GBDT), k-nearest neighbor (KNN) and random forest (RF), were used to classify the main vegetation (woody and grass species) and calculate the coverage. An independent data set was used to evaluate the accuracy of the algorithms. Overall accuracies of GBDT, KNN and RF for 2006 image classification were 0.9140, 0.9190 and 0.9478, respectively, with RF achieving the best classification results. Overall accuracies of GBDT, KNN and RF for 2019 images were 0.8466, 0.8627 and 0.8569, respectively, with the KNN algorithm achieving the best results for vegetation cover classification. The vegetation coverage in the study area changed significantly from 2006 to 2019, with an increase in grass coverage from 15.47 ± 1.49% to 27.90 ± 2.79%. The results show that RGB images are suitable for mapping FVC. Determining the best spatial resolution for different vegetation features may make estimation of desert vegetation coverage more accurate. Vegetation cover changes are also important in terms of understanding the evolution of desert ecosystems. [ABSTRACT FROM AUTHOR]

Using unmanned aerial vehicles (UAV) as platforms for light detection and ranging (LiDAR) sensors offers the efficient operation and advantages of active remote sensing; hence, UAV-LiDAR plays an important role in forest resource investigations. However, high-precision individual tree segmentation, in which the most appropriate individual tree segmentation method and the optimal algorithm parameter settings must be determined, remains highly challenging when applied to multiple forest types. This article compared the applicability of methods based on a canopy height model (CHM) and a normalized point cloud (NPC) obtained from UAV-LiDAR point cloud data. The watershed algorithm, local maximum method, point cloud-based cluster segmentation, and layer stacking were used to segment individual trees and extract the tree height parameters from nine plots of three forest types. The individual tree segmentation results were evaluated based on experimental field data, and the sensitivity of the parameter settings in the segmentation methods was analyzed. Among all plots, the overall accuracy F of individual tree segmentation was between 0.621 and 1, the average RMSE of tree height extraction was 1.175 m, and the RMSE% was 12.54%. The results indicated that compared with the CHM-based methods, the NPC-based methods exhibited better performance in individual tree segmentation; additionally, the type and complexity of a forest influence the accuracy of individual tree segmentation, and point cloud-based cluster segmentation is the preferred scheme for individual tree segmentation, while layer stacking should be used as a supplement in multilayer forests and extremely complex heterogeneous forests. This research provides important guidance for the use of UAV-LiDAR to accurately obtain forest structure parameters and perform forest resource investigations. In addition, the methods compared in this paper can be employed to extract vegetation indices, such as the canopy height, leaf area index, and vegetation coverage. [ABSTRACT FROM AUTHOR]

Due to better boundary adherence and low computational cost, the superpixel segmentation algorithm SLIC (simple linear iterative clustering) has been widely applied in vision-based applications. However, limit to unavoidable over-segmentation problem, one has to consider region-merging to reconstruct entire objects from the segmented superpixels (or called regions). The existing region-merging methods are generated from data clustering, and avoidably suffer from error-merging, slow convergence speed, or easily dropping in LOCAL optimal problems, especially for high-resolution RS (remote sensing) images. In this paper, instead of data clustering, we propose a fast GLOBAL method based on Set Maximum Coverage, termed as MaxCov-merging. Theoretically, the existence of the maximum coverage is proved by using Bayes optimal decision principle. To speed up MaxCov-merging, some heuristic strategies are also provided. Finally, extensive verification and comparison are carried on the public and our collected high-resolution images. Compared with the state-of-the-art methods, the comparison shows the superiority of our MaxCov in terms of the performance of globality, ease of use and fast region-merging speed. [ABSTRACT FROM AUTHOR]

• To guarantee high fire detection rate, a L0 norm constraint is introduced into the model. • To speed training and reduce error warning rate, L1 norm PreVM and its nonlinear version is also provided. • Theoretically, we prove the existence of dual representation for the general Lp (p>=1) norm regularization problems and the kernelization of L1 norm problem with implicit feature map. • Compared to the state-of-the-art, our proposed PreVMs are superior in fire detection rate, error warning rate, and real-time fire detection. Machine learning-based fire detection/recognition is very popular in forest-monitoring systems. However, without considering the prior knowledge, e.g., equal attention on both classes of the fire and non-fire samples, fire miss-detected phenomena frequently appeared in the current methods. In this work, considering model's interpretability and the limited data for model-training, we propose a novel pixel-precision method, termed as PreVM (Preferred Vector Machine). To guarantee high fire detection rate under precise control, a new L 0 norm constraint is introduced to the fire class. Computationally, instead of the traditional L 1 re-weighted techniques in L 0 norm approximation, this L 0 constraint can be converted into linear inequality and incorporated into the process of parameter selection. To further speed up model-training and reduce error warning rate, we also present a kernel-based L 1 norm PreVM (L 1 -PreVM). Theoretically, we firstly prove the existence of dual representation for the general L p (p ≥ 1) norm regularization problems in RKHS (Reproducing Kernel Hilbert Space). Then, we provide a mathematical evidence for L 1 norm kernelization to conquer the case when feature samples do not appear in pairs. The work also includes an extensive experimentation on the real forest fire images and videos. Compared with the-state-of-art methods, the results show that our PreVM is capable of simultaneously achieving higher fire detection rates and lower error warning rates, and L 1 -PreVM is also superior in real-time detection. [ABSTRACT FROM AUTHOR]

Multiview Generalized Eigenvalue Proximal Support Vector Machine (MvGEPSVM) is an effective method for multiview data classification proposed recently. However, it ignores discriminations between different views and the agreement of the same view. Moreover, there is no robustness guarantee. In this paper, we propose an improved multiview GEPSVM (IMvGEPSVM) method, which adds a multi-view regularization that can connect different views of the same class and simultaneously considers the maximization of the samples from different classes in heterogeneous views for promoting discriminations. This makes the classification more effective. In addition, L1-norm rather than squared L2-norm is employed to calculate the distances from each of the sample points to the hyperplane so as to reduce the effect of outliers in the proposed model. To solve the resulting objective, an efficient iterative algorithm is presented. Theoretically, we conduct the proof of the algorithm's convergence. Experimental results show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Accurate estimate of tree biomass is essential for forest management. In recent years, several climate-sensitive allometric biomass models with diameter at breast height (D) as a predictor have been proposed for various tree species and climate zones to estimate tree aboveground biomass (AGB). But the allometric models only account for the potential effects of climate on tree biomass and do not simultaneously explain the influence of climate on D growth. In this study, based on the AGB data from 256 destructively sampled trees of three larch species randomly distributed across the five secondary climate zones in northeastern and northern China, we first developed a climate-sensitive AGB base model and a climate-sensitive D growth base model using a nonlinear least square regression separately. A compatible simultaneous model system was then developed with the climate-sensitive AGB and D growth models using a nonlinear seemingly unrelated regression. The potential effects of several temperature and precipitation variables on AGB and D growth were evaluated. The fitting results of climatic sensitive base models were compared against those of their compatible simultaneous model system. It was found that a decreased isothermality ([mean of monthly (maximum temperature-minimum temperature)]/(Maximum temperature of the warmest month-Minimum temperature of the coldest month)) and total growing season precipitation, and increased annual precipitation significantly increased the values of AGB; an increase of temperature seasonality (a standard deviation of the mean monthly temperature) and precipitation seasonality (a standard deviation of the mean monthly precipitation) could lead to the increase of D. The differences of the model fitting results between the compatible simultaneous system with the consideration of climate effects on both AGB and D growth and its corresponding climate-sensitive AGB and D growth base models were very small and insignificant (p > 0. 0 5). Compared to the base models, the inherent correlation of AGB with D was taken into account effectively by the proposed compatible model system developed with the climate-sensitive AGB and D growth models. In addition, the compatible properties of the estimated AGB and D were also addressed substantially in the proposed model system. [ABSTRACT FROM AUTHOR]

Most existing low-rank and sparse representation models cannot preserve the local manifold structures of samples adaptively, or separate the locality preservation from the coding process, which may result in the decreased performance. In this paper, we propose an inductive Robust Auto-weighted Low-Rank and Sparse Representation (RALSR) framework by joint feature embedding for the salient feature extraction of high-dimensional data. Technically, the model of our RALSR seamlessly integrates the joint low-rank and sparse recovery with robust salient feature extraction. Specifically, RALSR integrates the adaptive locality preserving weighting, joint low-rank/sparse representation and the robustness-promoting representation into a unified model. For accurate similarity measure, RALSR computes the adaptive weights by minimizing the joint reconstruction errors over the recovered clean data and salient features simultaneously, where L1-norm is also applied to ensure the sparse properties of learnt weights. The joint minimization can also potentially enable the weight matrix to have the power to remove noise and unfavorable features by reconstruction adaptively. The underlying projection is encoded by a joint low-rank and sparse regularization, which can ensure it to be powerful for salient feature extraction. Thus, the calculated low-rank sparse features of high-dimensional data would be more accurate for the subsequent classification. Visual and numerical comparison results demonstrate the effectiveness of our RALSR for data representation and classification. [ABSTRACT FROM AUTHOR]

Conventional ground survey data are very accurate, but expensive. Airborne lidar data can reduce the costs and effort required to conduct large-scale forest surveys. It is critical to improve biomass estimation and evaluate carbon stock when we use lidar data. Bayesian methods integrate prior information about unknown parameters, reduce the parameter estimation uncertainty, and improve model performance. This study focused on predicting the independent tree aboveground biomass (AGB) with a hierarchical Bayesian model using airborne LIDAR data and comparing the hierarchical Bayesian model with classical methods (nonlinear mixed effect model, NLME). Firstly, we chose the best diameter at breast height (DBH) model from several widely used models through a hierarchical Bayesian method. Secondly, we used the DBH predictions together with the tree height (LH) and canopy projection area (CPA) derived by airborne lidar as independent variables to develop the AGB model through a hierarchical Bayesian method with parameter priors from the NLME method. We then compared the hierarchical Bayesian method with the NLME method. The results showed that the two methods performed similarly when pooling the data, while for small sample sizes, the Bayesian method was much better than the classical method. The results of this study imply that the Bayesian method has the potential to improve the estimations of both DBH and AGB using LIDAR data, which reduces costs compared with conventional measurements. [ABSTRACT FROM AUTHOR]

Twin support vector machine (TWSVM) is a classical and effective classifier for binary classification. However, its robustness cannot be guaranteed due to the utilization of squared L2-norm distance that can usually exaggerate the influence of outliers. In this paper, we propose a new robust capped L1-norm twin support vector machine (CTWSVM), which sustains the advantages of TWSVM and promotes the robustness in solving a binary classification problem with outliers. The solution of the proposed method can be achieved by optimizing a pair of capped L1-norm related problems using a newly-designed effective iterative algorithm. Also, we present some theoretical analysis on existence of local optimum and convergence of the algorithm. Extensive experiments on an artificial dataset and several UCI datasets demonstrate the robustness and feasibility of our proposed CTWSVM. [ABSTRACT FROM AUTHOR]

Premise of the Study: A novel set of EST‐SSR markers was developed for Phyllanthus emblica (Phyllanthaceae) to investigate the genetic structure and gene flow, identify novel genes of interest, and develop markers for assisted breeding. Methods and Results: Based on the transcriptome data of P. emblica, 83 EST‐SSR primer pairs were designed; 52 primer pairs were successfully amplified, with 20 showing polymorphisms in 90 individuals from three populations of P. emblica. The number of alleles per locus varied from 11 to 44. The observed and expected levels of heterozygosity for the 20 loci ranged from 0.240 to 0.868 and 0.754 to 0.933, respectively. Cross‐species amplification was successful for all 20 loci in each of the two related species, P. reticulatus and Leptopus chinensis. Conclusions: These markers will be valuable for studying the population genetics and for mining genes of P. emblica, and may be useful for studies of related species. [ABSTRACT FROM AUTHOR]

In this paper, we construct a least squares version of the recently proposed twin bounded support vector machine (TBSVM) for binary classification. As a valid classification tool, TBSVM attempts to seek two non-parallel planes that can be produced by solving a pair of quadratic programming problems (QPPs), but this is time-consuming. Here, we solve two systems of linear equations rather than two QPPs to avoid this deficiency. Furthermore, the distance in least squares TBSVM (LSTBSVM) is measured by L2-norm, but L1-norm distance is usually regarded as an alternative to L2-norm to improve model robustness in the presence of outliers. Inspired by the advantages of least squares twin support vector machine (LSTWSVM), TBSVM and L1-norm distance, we propose a LSTBSVM based on L1-norm distance metric for binary classification, termed as L1-LSTBSVM, which is specially designed for suppressing the negative effect of outliers and improving computational efficiency in large datasets. Then, we design a powerful iterative algorithm to solve the L1-norm optimal problems, and it is easy to implement and its convergence to an optimum solution is theoretically ensured. Finally, the feasibility and effectiveness of L1-LSTBSVM are validated by extensive experimental results on both UCI datasets and artificial datasets. [ABSTRACT FROM AUTHOR]

• A method for accurate individual tree segmentation (ITS) and tree-counting problem is proposed, based on supervised clustering. We highlight the main contributions as follows. • Instead of image preprocessing, tree pixels or superpixels are identified by a pixel classifier. • The similarity for tree pixel location and color values is learned from supervised clustering. • Theoretically, we prove the equivalence between this similarity and the derived covariance. • Our method can obtain individuals from the crowns, isolated or overlapped or both. Individual tree segmentation (ITS), or tree counting, is a fundamental work in precision forestry and agriculture processes. Rather than the time-consuming and labor-intensive manual inspection, computer vision has shown substantial prospects in unmanned aerial vehicle (UAV)-based applications; one such application includes the automatic tree-counting problem in the forest resource inventory. However, it is difficult to obtain individual trees owing to the particularity of tree canopy crowns, such as color graduality, shape uncertainty, and overlapping. In this study, we propose a learning framework based on supervised data clustering. Here, both ITS and tree counting can be obtained accurately and simultaneously from a two-dimensional (2D) top-view tree canopy crowns whether they are isolated, overlapped, or both. A pixel-precision classifier is used to recognize tree pixels or superpixels (a set of meaningful pixels), rather than using complex image preprocessing or feature construction techniques. The obtained tree superpixels are then grouped into individual trees by the proposed supervised clustering method. To obtain accurate ITS and tree counts, the similarity used for the clustering is "learned" from the user-supplied supervisions, rather than "pre-specified" or "grid-search" as in the existing state-of-the-art methods. This study also includes an extensive experimental comparison of homogenous and heterogeneous high-resolution images. The results demonstrate that our method is superior to the state-of-the-art methods in both visualized ITS and numeric tree-counting results, even comparable to human vision. It achieves a counting accuracy of 99.16 % in terms of the R 2 value and 2.2923 in terms of the pixel mean absolute error (MAE). These are 22.04 % higher and 8.727 lower, respectively, than those of the second-best method. [ABSTRACT FROM AUTHOR]

• ICESat-2 has the potential to improve the estimation accuracy and efficiency of forest aboveground biomass on a large scale. • The Google Earth Engine cloud platform was used for Sentinel-2 images acquisition and composition. • The optimized extreme learning machine achieved the highest estimation accuracy and reasonable forest aboveground biomass spatial distribution. Natural forests have the most complex structure and richest biodiversity among terrestrial ecosystems and are essential for maintaining the carbon balance and stability of the biosphere. Aboveground biomass (AGB) is a primary indicator used to evaluate forests and can directly measure forest growth and the quality of natural forests. Accurate and rapid AGB estimations can significantly improve the efficiency of forest management and deepen the understanding of the forest carbon cycle. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), one of the most recently launched spaceborne light detection and ranging (LiDAR) instruments, can penetrate forest canopies and obtain accurate, large-scale forest vertical parameter measurements. However, the discrete footprints offered by ICESat-2 cannot provide comprehensive spatial AGB distribution data. In this study, an optimized extreme learning machine (ELM) method was proposed to estimate the AGB of natural forests on the eastern Qinghai-Xizang Plateau, China. The synthetic Sentinel-2 images acquired from the Google Earth Engine (GEE) were synergized with ICESat-2 to realize continuous AGB mapping. To verify the effectiveness of the optimized method, support vector machine (SVM), k-nearest neighbor (kNN), and backpropagation (BP) neural network models were also established for comparison. The measured AGB data extracted from the forest management inventory (FMI) were used for model accuracy evaluation. The results show that the optimized ELM achieved the best estimation effect among all the analyzed models, with an R2 value of 0.68 and a root mean square error (RMSE) value of 25.14 mg/ha. The optimized ELM obtained the minimum RMSE and greatly improved the AGB prediction efficiency. These findings prove the ability of ICESat-2 in estimating the AGB of natural forests, which can provide a new way for large-scale forest resources investigation in high-altitude areas with a harsh environment. [ABSTRACT FROM AUTHOR]

Estimating the change in the magnitude and distribution of forest biomass is important for monitoring carbon dynamics and understanding the implications on the terrestrial carbon cycle. In this study, we assessed the capacity of multi-temporal airborne Light Detection and Ranging (LiDAR) data to estimate forest biomass dynamics at a mixed subtropical forest of southeast China, and analyzed the magnitude and spatial patterns of the above ground biomass (AGB) change over a 6-year period. To do so, we evaluated different approaches to estimate change in AGB, specifically direct (i.e., predicting biomass change using the differences in LiDAR metrics) and indirect (i.e., modeling biomass for each point in time and predicting the change as their differences) approaches. Once models were developed, the change in AGB was mapped across the study site and examined in relation to forest type and age. Our results demonstrated that the direct approach (CV- R 2 = 0.63, CV-rRMSE = 25.64%) produced more accurate estimates in change of AGB than the indirect approach (CV- R 2 = 0.59, CV-rRMSE = 28.35%). Canopy height metrics of delta mean height (∆ h mean ) and a number of upper percentile heights (i.e., ∆ h 75 and ∆ h 95 ) , calculated from the LiDAR first returns, were found to be most sensitive to changes in biomass, whereas metrics based on maximum canopy height or canopy density had less predictive power. Furthermore, differences in point cloud densities did not significantly impact the estimations of AGB and change of AGB at the plot-scale (30 × 30 m). Spatial extrapolation of the AGB change indicated that, in general, most of the forest area had an overall gain in biomass. The middle-aged stands (typically dominated by Quercus acutissima between 41 and 60 years old) show marked growth of biomass (median ∆ AGB = 2.29 Mg ha − 1 year − 1 ), followed by mature (typically dominated by Pinus massoniana between 31 and 60 years old) (median ∆ AGB = 1.72 Mg ha − 1 year − 1 ) and young stands (typically consisting of regenerated broadleaved trees younger than 40 years old) (median ∆ AGB = 1.48 Mg ha − 1 year − 1 ), whereas over-mature stands (typically dominated by Cunninghamia lanceolata older than 35 years) show the lowest growth (median ∆ AGB = 0.76 Mg ha − 1 year − 1 ). This study demonstrates benefits of using multi-temporal LiDAR data to help identify specific areas for management interventions, to enhance forest productivity, maintain biomass stocks and optimize carbon sequestration. [ABSTRACT FROM AUTHOR]

• Based on the encoder-decoder architecture, we propose a block-specific unabridged channel attention mechanism, such that features within each block can be recalibrated. • A top-down adjacent modulation for decoder network is proposed so that the lowlevel features substantially contain abundant semantic contexts. • We demonstrate the effectiveness of UAM-Net via two challenging benchmarks. Results declare that we can achieve a new state-of-the-art on colorful fashion parsing dataset and comparable performance on modified fashion clothing dataset with less computation overhead. Clothing parsing has made tremendous progress in the domain of computer vision recently. Most state-of-the-art methods are based on the encoder-decoder architecture. However, the existing methods mainly neglect problems of feature uncalibration within blocks and semantics dilution between blocks. In this work, we propose an unabridged adjacent modulation network (UAM-Net) to aggregate multi-level features for clothing parsing. We first build an unabridged channel attention (UCA) mechanism on feature maps within each block for feature recalibration. We further design a top-down adjacent modulation (TAM) for decoder blocks. By deploying TAM, high-level semantic information and visual contexts can be gradually transferred into lower-level layers without loss. The joint implementation of UCA and TAM ensures that the encoder has an enhanced feature representation ability, and the low-level features of the decoders contain abundant semantic contexts. Quantitative and qualitative experimental results on two challenging benchmarks (i.e., colorful fashion parsing and the modified fashion clothing) declare that our proposed UAM-Net can achieve competitive high-accurate performance with the state-of-the-art methods. The source codes are available at: https://github.com/ctzuo/UAM-Net. [ABSTRACT FROM AUTHOR]

Oil tea (Camellia oleifera) is one of the world's major woody edible oil plants and is vital in providing food and raw materials and ensuring water conservation. The yield of oil tea can directly reflect the growth condition of oil tea forests, and rapid and accurate yield measurement is directly beneficial to efficient oil tea forest management. Light detection and ranging (LiDAR), which can penetrate the canopy to acquire the geometric attributes of targets, has become an effective and popular method of yield identification for agricultural products. However, the common geometric attribute information obtained by LiDAR systems is always limited in terms of the accuracy of yield identification. In this study, to improve yield identification efficiency and accuracy, the red-green-blue (RGB) and luminance-bandwidth-chrominance (i.e., YUV color spaces) were used to identify the point clouds of oil tea fruits. An optimized mean shift clustering algorithm was constructed for oil tea fruit point cloud extraction and product identification. The point cloud data of oil tea trees were obtained using terrestrial laser scanning (TLS), and field measurements were conducted in Changsha County, central China. In addition, the common mean shift, density-based spatial clustering of applications with noise (DBSCAN), and maximum–minimum distance clustering were established for comparison and validation. The results showed that the optimized mean shift clustering algorithm achieved the best identification in both the RGB and YUV color spaces, with detection ratios that were 9.02%, 54.53%, and 3.91% and 7.05%, 62.35%, and 10.78% higher than those of the common mean shift clustering, DBSCAN clustering, and maximum-minimum distance clustering algorithms, respectively. In addition, the improved mean shift clustering algorithm achieved a higher recognition rate in the YUV color space, with an average detection rate of 81.73%, which was 2.4% higher than the average detection rate in the RGB color space. Therefore, this method can perform efficient yield identification of oil tea and provide a new reference for agricultural product management. [ABSTRACT FROM AUTHOR]

The survival rate of seedlings is a decisive factor of afforestation assessment. Generally, ground checking is more accurate than any other methods. However, the survival rate of seedlings can be higher in the growing season, and this can be estimated in a larger area at a relatively lower cost by extracting the tree crown from the unmanned aerial vehicle (UAV) images, which provides an opportunity for monitoring afforestation in an extensive area. At present, studies on extracting individual tree crowns under the complex ground vegetation conditions are limited. Based on the afforestation images obtained by airborne consumer-grade cameras in central China, this study proposes a method of extracting and fusing multiple radii morphological features to obtain the potential crown. A random forest (RF) was used to identify the regions extracted from the images, and then the recognized crown regions were fused selectively according to the distance. A low-cost individual crown recognition framework was constructed for rapid checking of planted trees. The method was tested in two afforestation areas of 5950 m2 and 5840 m2, with a population of 2418 trees (Koelreuteria) in total. Due to the complex terrain of the sample plot, high weed coverage, the crown width of trees, and spacing of saplings vary greatly, which increases both the difficulty and complexity of crown extraction. Nevertheless, recall and F-score of the proposed method reached 93.29%, 91.22%, and 92.24% precisions, respectively, and 2212 trees were correctly recognized and located. The results show that the proposed method is robust to the change of brightness and to splitting up of a multi-directional tree crown, and is an automatic solution for afforestation verification. [ABSTRACT FROM AUTHOR]

We propose an automatic annotation method for forest fire images in the level of pixel, where supervise information is introduced by interactive convex hulls. Instead of usual rectangle-/ regular -shaped regions, we propose a convex hull algorithm for visually selecting polygonal (irregular) fire and no-fire regions. Guided by the goals of forest fire monitoring systems: high fire detection rate (true-positive) and then low false alarm rate (false-positive), we construct a k-nearest neighbor (kNN) based KD-tree to speed annotation. Compared to state-of-the-art, the proposed method not only widens the view of fire detection from conventional two-class to multi-class classification problem to meet complex forest image background, but also relaxes the limit of i.i.d (independent and identical distribution) hypothesis on machine learning methods. Furthermore, it is simple to use, which just relies on pixel information and avoids considering additional auxiliary features from multiple color spaces. Experimental evaluations are carrying on forest fire images, MIVIA dead-directional videos, and more challenging omni-directional videos. The comparison demonstrates that the proposed pixel-level annotation method is able to achieve higher fire detection rate and lower false alarm rate at the same time. • To select training samples easily and accurately, we proposed a fast convex hull method. • To relax the i.i.d hypothesis, a K-d tree KNN classifier is adopted for pixel annotation. • To overcome classic two-class, our method is oriented from multi-class classification. • Experimentally it can achieve both high fire detection rate and low false alarm rate. [ABSTRACT FROM AUTHOR]

Discriminative Feature Selection (DFS) is an algorithm, proposed recently for effective feature selection by considering both joint linear discriminant analysis and row sparsity regularization. However, this method is not robust enough to protect the data from outliers, because it utilizes the squared L 2 -norm distance metric. To overcome this problem, we present in this paper, a novel discriminative feature selection algorithm, which uses the robust L 2 , 1 -norm for measuring the distances in DFS. Although the algorithm is apparently simple, it should not be considered trivial because of its non-convexity. Also, we present an analysis of the convergence, both theoretical and empirical. More importantly, we proposed an iterative algorithm to achieve optimal results. Experimental results, using various data sets, demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]