Search

Global navigation satellite system (GNSS) provides users with all-weather, continuous, high-precision positioning, navigation, and timing (PNT) services. In the operation and use of GNSS, the influence of the space environment is a factor that must be considered. For example, during geomagnetic storms, a series of changes in the Earth's magnetosphere, ionosphere, and upper atmosphere affect GNSS's positioning performance. To investigate the positioning performance of global satellite navigation systems during geomagnetic storms, this study selected three geomagnetic storm events that occurred from September to December 2023. Utilizing the global positioning system (GPS)/Beidou navigation satellite system (BDS) dual-system, kinematic precise point positioning (PPP) experiments were conducted, and the raw observational data from 100 stations worldwide was analyzed. The experimental results show that the positioning accuracy of some stations in high-latitude areas decreases significantly when using the conventional Geometry Free (GF) cycle-slip detection threshold during geomagnetic storms, which means that the GF is no longer applicable to high-precision positioning services. Meanwhile, there is no significant change in the satellite signal strengths received at the stations during the period of the decrease in positioning accuracy. Analyzing the cycle-slip rates for stations where abnormal accuracy occurred, it was observed that stations experiencing a significant decline in positioning accuracy exhibited serious cycle-slip misjudgments. To improve the kinematic PPP accuracy during magnetic storms, this paper proposes an adaptive threshold for cycle-slip detection and designs five experimental strategies. After using the GF adaptive threshold, the station positioning accuracy improved significantly. It achieved the accuracy level of the quiet period, while the cycle-slip incidence reached the average level. During magnetic storms, the ionosphere changes rapidly, and the use of the traditional GF constant threshold will cause serious cycle-slip misjudgments, which makes the dynamic accuracy in high latitude areas and some mid-latitude areas uncommon, while the use of the GF adaptive threshold can alleviate this phenomenon and improve the positioning accuracy in the high-latitude regions and some of the affected mid-latitude areas during the magnetic storms. [ABSTRACT FROM AUTHOR]

Differential code bias (DCB) of satellite is an error that cannot be ignored in precise positioning, timing, ionospheric modeling, satellite clock correction, and ambiguity resolution. The completion of the third generation of BeiDou Navigation Satellite System (BDS-3) has extended DCB to multichannel code bias observations and observable-specific signal bias (OSB). In this paper, the DCB and OSB products provided by the Chinese Academy of Sciences (CAS) are analyzed and compared. The DCB parameters for the BDS satellites are applied in both single- and dual-frequency single point positioning (SPP), and the results are intensively investigated. Based on the satellite DCB parameters of the BDS, the performance of precise point positioning (PPP) with different frequency combinations is also analyzed in terms of positioning accuracy and convergence time. The standard deviations (STDs) of DCBs at each signal pair fluctuate from 0.2 ns to 1.5 ns. The DCBs of BDS-2 are slightly more stable than those of BDS-3. The mean values and STDs of C2I and C7I OSBs for BDS-2 are at the same level and are numerically smaller than their counterparts for the C6I OSBs. The mean OSBs for each signal of the BDS-3, excluding C2I, fluctuate between 12.35 ns and 12.94 ns, and the STD fluctuates between 2.11 ns and 3.10 ns. The DCBs and OSBs of the BDS-3 of the IGSO satellites are more stable than those of the MEO satellites. The corrections for TGD and DCB are able to improve the accuracy of single-frequency SPP by 44.09% and 44.07%, respectively, and improve the accuracy of dual-frequency SPP by 6.44% and 12.85%, respectively. The most significant improvements from DCB correction are seen in single-frequency positioning with B1I and dual-frequency positioning with B2a+B3I. DCB correction can improve the horizontal and three-dimensional positioning accuracy of the dual-frequency PPP of different ionosphere-free combinations by 13.53% and 13.84% on average, respectively, although the convergence is slowed. [ABSTRACT FROM AUTHOR]

Tropospheric delay (TD) parameter estimation is a critical issue underlying high-precision data processing for global navigation satellite systems (GNSSs). The most widely used TD parameter estimation methods are the random walk (RW) and piece-wise constant (PWC). The RW method can effectively track rapid variations of tropospheric delay, but it may introduce excessive noise. In contrast, the PWC method introduces less noise, but it is less adaptable to cases of large variations of tropospheric delay. To address the problem of how to choose the optimal TD parameter estimation method, this paper investigates the variation patterns of international GNSS service zenith tropospheric delay (IGS ZTD) products and proposes a combined strategy model for TD parameter estimation. Firstly, this paper avoids the day-boundary jumps problem of IGS ZTD products by grouping based on single-day data. Secondly, this paper introduces discrete point areas (DPAs) to measure the magnitude of the ZTD values and uses comprehensive indicators to reflect the variation of ZTD. Next, based on the Köppen-Geiger climate classification, this study selected five different climate classifications with a total of 20 IGS stations as experimental data. The data assessed span from day of year (DOY) 001 to DOY 365 in 2022. This paper then applied 26 different parameter estimation strategies for static precise point positioning (PPP) data processing, and the parameter estimation strategies that were used include the RW and PWC (with the piece-wise constant ranging from twenty minutes to five hundred minutes at twenty-minute intervals). Finally, ZTD and positioning results were obtained using various parameter estimation methods, and a combined strategy model was established. We selected five different climate classifications of IGS stations as validation data and designed three sets of comparative experiments: RW, PWC120, and the combined strategy model, to verify the effectiveness of the combined strategy model. The experimental results revealed that: RW and the combined strategy model have a comparable ZTD accuracy and both are superior to PWC120. The combined strategy model improves the positioning accuracy in the U direction compared to RW and PWC120. In arid (B) and polar (E) regions with a small variation of TD, the PWC120 strategy displayed a better positioning accuracy than the RW strategy; in equatorial (A) and warm-temperate (C) regions, where there are large variations of TD, the RW strategy exhibited a better positioning accuracy than the PWC120 strategy. The combined strategy model can flexibly select the optimal parameter estimation method according to the comprehensive indicator while ensuring ZTD estimation accuracy; it enhances positioning accuracy. [ABSTRACT FROM AUTHOR]

The objects in remote sensing images are normally densely packed, arbitrarily oriented, and surrounded by complex backgrounds. Great efforts have been devoted to developing oriented object detection models to accommodate such data characteristics. We argue that an effective detection model hinges on three aspects: feature enhancement, feature decoupling for classification and localization, and an appropriate bounding box regression scheme. In this article, we instantiate the three aspects on top of the classical Faster R-CNN, with three novel components proposed. First, we propose a weighted fusion and refinement (WFR) module, which adaptively weighs multi-level features and leverages the attention mechanism to refine the fused features. Second, we decouple the RoI (region of interest) features for the subsequent classification and localization via a lightweight affine transformation-based feature decoupling (ATFD) module. Third, we propose a post-classification regression (PCR) module for generating the desired quadrilateral bounding boxes. Specifically, PCR predicts the precise vertex location on each side of a predicted horizontal box, by simply learning the following: (i) classify the discretized regression range of the vertex, and (ii) revise the vertex location with an offset. We conduct extensive experiments on the DOTA, DIOR-R, and HRSC2016 datasets to evaluate our method. [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]

There is a large amount of remote sensing data available for land use and land cover (LULC) classification and thus optimizing selection of remote sensing variables is a great challenge. Although many methods such as Jeffreys-Matusita (JM) distance and random forests (RF) have been developed for this purpose, the existing methods ignore correlation and information duplication among remote sensing variables. In this study, a novel approach was proposed to improve the measures of potential class separability for the selection of remote sensing variables by taking into account correlations among the variables. The proposed method was examined with a total of thirteen spectral variables from a Gaofen-1 image, three class separability measures including JM distance, transformed divergence and B-distance and three classifiers including Bayesian discriminant (BD), Mahalanobis distance (MD) and RF for classification of six LULC types at the East Dongting Lake of Hunan, China. The results showed that (1) The proposed approach selected the first three spectral variables and resulted in statistically stable classification accuracies for three improved class separability measures. That is, the classification accuracies using three or more spectral variables statistically did not significantly differ from each other at a significant level of 0.05; (2) The statistically stable classification accuracies obtained by integrating MD and BD classifiers with the improved class separability measures were also statistically not significantly different from those by RF; (3) The numbers of the selected spectral variables using the improved class separability measures to create the statistically stable classification accuracies by MD and BD classifiers were much smaller than those from the original class separability measures and RF; and (4) Three original class separability measures and RF led to similar ranks of importance of the spectral variables, while the ranks achieved by the improved class separability measures were different due to the consideration of correlations among the variables. This indicated that the proposed method more effectively and quickly selected the spectral variables to produce the statistically stable classification accuracies compared with the original class separability measures and RF and thus improved the selection of the spectral variables for the classification. [ABSTRACT FROM AUTHOR]

For the same antenna type, numerical differences among the phase center correction (PCC) models released by different institutes can reach several millimeters, which is far beyond the nominal calibration accuracy. This contribution introduces a new method to evaluate the consistency of these PCC models. We first investigated the coupling of phase center offset (PCO) and phase center variation (PCV) through simulation experiments, and the results show that the calibrated PCO values under different strategies may result in large differences, and so do PCV values due to strong coupling with PCO. This is further confirmed by field calibration experiments. Moreover, a new datum parameter is introduced to equivalently transform the PCC models to assess the consistency of PCC models of the same antenna type calibrated under different strategies or by different facilities. It is also essential to perform consistency analysis of PCC models in the coordinate domain. We further investigated these PCC models through a simulated positioning experiment. The results show that millimeter-level consistency of PCC models will lead to the same level of positioning precision in the coordinate domain. Moreover, as a comparison, both baseline positioning and PPP were performed with an antenna-type JAV_RINGANT_G3T NONE based on real observations. Multiday results showed that the average RMS of the positioning differences between PCC models from robot and anechoic chamber calibration is less than 1 mm for the baseline solution and 4 mm for the PPP solution, although the PCC model differences can reach 6 mm in L1 and 4 mm in L2, respectively. Finally, we also investigated the distribution of position biases without PCC or with inaccurate PCC. Considering the actual GPS constellation, we found that position biases have a strong correlation with latitude, if PCV values fluctuate greatly with the users' elevation angle. [ABSTRACT FROM AUTHOR]

The broadcast ionospheric model is mainly used to correct the ionospheric delay error for single-frequency users. Since the BeiDou global ionospheric delay correction model (BDGIM) is a novel broadcast ionospheric model for BDS-3, its performance was analyzed through single point positioning (SPP) in this study. Twenty-two stations simultaneously receiving B1C, B2a, B1I and B3I signals were selected from the International GNSS Service (IGS) and the International GNSS Monitoring and Assessment System (iGMAS) tracking networks for the SPP experiments. The differential code bias (DCB) parameters were used to correct the hardware delays in the signals of B1C and B2a. The results showed that the BDGIM performs the best in high-latitude areas, and can effectively improve the positioning accuracy compared with the Klobuchar model. The average 3D positioning accuracy of the four civil signals can reach 3.58 m in high-latitude areas. The positioning accuracies with the BDGIM in the northern hemisphere are better than those in the southern hemisphere, and the global average 3D positioning accuracy of the four civil signals is 4.60 m. The performance of the BDGIM also shows some seasonal differences. The BDGIM performs better than the Klobuchar model on the days of spring equinox and winter solstice, while the opposite is true on the days of summer solstice and autumn equinox. On the day of winter solstice, the average 3D accuracies with the BDGIM on the signals of B1C, B2a, B1I and B3I are 4.13 m, 5.32 m, 4.40 m and 4.49 m, respectively. Although the SPP accuracies are to some extent affected by the geomagnetic storm, the BDGIM generally performs better and are more resistant to the geomagnetic storm than the Klobuchar model. [ABSTRACT FROM AUTHOR]

Northern China has been long threatened by aeolian desertification. In recent years, all levels of the Chinese government have performed a series of ecological protection and sand control projects. To grasp the implementation effects of these projects and adjust policies in time, it is necessary to understand the process of aeolian desertification quickly and accurately. Remote sensing technologies play an irreplaceable role in aeolian desertification monitoring. In this study, the Zhenglan Banner, which is in the hinterland of the Hunshandake Sandy Land, was considered as the research area. Based on unmanned aerial vehicle (UAV) images, ground survey data, and Landsat images called in Google Earth Engine (GEE), the aeolian desertified land (ADL) in 2000, 2004, 2010, 2015, and 2019 was extracted using spectral mixture analysis. A desertification index (DI) was constructed to evaluate the spatial and temporal dynamics of the ADL in the Zhenglan Banner. Finally, a residual analysis explored the driving forces of aeolian desertification. The results showed that (1) the ADL area in the Zhenglan Banner has been trending downwards over the past 20 years but rebounded from 2004 to 2010; (2) over the past 20 years, the area of slightly, moderately, and severely desertified land has decreased at annual rates of 0.4%, 2.7%, and 3.4%, respectively; (3) human activities had significantly positive and negative impacts on the aeolian desertification trend for 20.0% and 21.0% of the study area, respectively, but not for the rest. This paper explored new techniques for rapid aeolian desertification monitoring and is of great significance for controlling and managing aeolian desertification in this region. [ABSTRACT FROM AUTHOR]

The need for timely, spatially, and thematically accurate information regarding forests is increasing because of the key role of forests in the global carbon balance and sustainable social, economic, ecological, and cultural development. While an increasing number of countries in the world already are conducting statistically sound forest inventories, a few for 100 years, inventories in other countries are still lacking, which makes the global information about forest statistics inaccurate. This implies that remote sensing-based approaches are vulnerable to misclassification and inaccurate estimation of forest parameters and changes, such as the recognition of temporarily unstocked forest areas, forest degradation, and species composition, as well as in strictly following the globally adopted definitions. [Extracted from the article]

Deep learning classifiers exhibit remarkable performance for hyperspectral image classification given sufficient labeled samples but show deficiency in the situation of learning with limited labeled samples. Active learning endows deep learning classifiers with the ability to alleviate this deficiency. However, existing active deep learning methods tend to underestimate the feature variability of hyperspectral images when querying informative unlabeled samples subject to certain acquisition heuristics. A major reason for this bias is that the acquisition heuristics are normally derived based on the output of a deep learning classifier, in which representational power is bounded by the number of labeled training samples at hand. To address this limitation, we developed a feature-oriented adversarial active learning (FAAL) strategy, which exploits the high-level features from one intermediate layer of a deep learning classifier for establishing an acquisition heuristic based on a generative adversarial network (GAN). Specifically, we developed a feature generator for generating fake high-level features and a feature discriminator for discriminating between the real high-level features and the fake ones. Trained with both the real and the fake high-level features, the feature discriminator comprehensively captures the feature variability of hyperspectral images and yields a powerful and generalized discriminative capability. We leverage the well-trained feature discriminator as the acquisition heuristic to measure the informativeness of unlabeled samples. Experimental results validate the effectiveness of both (i) the full FAAL framework and (ii) the adversarially learned acquisition heuristic, for the task of classifying hyperspectral images with limited labeled samples. [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]

The forest growth and yield models, which are used as important decision-support tools in forest management, are commonly based on the individual tree characteristics, such as diameter at breast height (DBH), crown ratio, and height to crown base (HCB). Taking direct measurements for DBH and HCB through the ground-based methods is cumbersome and costly. The indirect method of getting such information is possible from remote sensing databases, which can be used to build DBH and HCB prediction models. The DBH and HCB of the same trees are significantly correlated, and so their inherent correlations need to be appropriately accounted for in the DBH and HCB models. However, all the existing DBH and HCB models, including models based on light detection and ranging (LiDAR) have ignored such correlations and thus failed to account for the compatibility of DBH and HCB estimates, in addition to disregarding measurement errors. To address these problems, we developed a compatible simultaneous equation system of DBH and HCB error-in-variable (EIV) models using LiDAR-derived data and ground-measurements for 510 Picea crassifolia Kom trees in northwest China. Four versatile algorithms, such as nonlinear seemingly unrelated regression (NSUR), two-stage least square (2SLS) regression, three-stage least square (3SLS) regression, and full information maximum likelihood (FIML) were evaluated for their estimating efficiencies and precisions for a simultaneous equation system of DBH and HCB EIV models. In addition, two other model structures, namely, nonlinear least squares with HCB estimation not based on the DBH (NLS and NBD) and nonlinear least squares with HCB estimation based on the DBH (NLS and BD) were also developed, and their fitting precisions with a simultaneous equation system compared. The leave-one-out cross-validation method was applied to evaluate all estimating algorithms and their resulting models. We found that only the simultaneous equation system could illustrate the effect of errors associated with the regressors on the response variables (DBH and HCB) and guaranteed the compatibility between the DBH and HCB models at an individual level. In addition, such an established system also effectively accounted for the inherent correlations between DBH with HCB. However, both the NLS and BD model and the NLS and NBD model did not show these properties. The precision of a simultaneous equation system developed using NSUR appeared the best among all the evaluated algorithms. Our equation system does not require the stand-level information as input, but it does require the information of tree height, crown width, and crown projection area, all of which can be readily derived from LiDAR imagery using the delineation algorithms and ground-based DBH measurements. Our results indicate that NSUR is a more reliable and quicker algorithm for developing DBH and HCB models using large scale LiDAR-based datasets. The novelty of this study is that the compatibility problem of the DBH model and the HCB EIV model was properly addressed, and the potential algorithms were compared to choose the most suitable one (NSUR). The presented method and algorithm will be useful for establishing similar compatible equation systems of tree DBH and HCB EIV models for other tree species. [ABSTRACT FROM AUTHOR]

As an important vegetation canopy parameter, the leaf area index (LAI) plays a critical role in forest growth modeling and vegetation health assessment. Estimating LAI is helpful for understanding vegetation growth and global ecological processes. Machine learning methods such as k-nearest neighbors (kNN) and random forest (RF) with remote sensing images have been widely used for mapping LAI. However, the accuracy of mapping LAI in arid and semi-arid areas using these methods is limited due to remote and large areas, the high cost of collecting field data, and the great spatial variability of the vegetation canopy. Here, a novel and modified kNN method was presented for mapping LAI in arid and semi-arid areas of China using Sentinel-2 and Landsat 8 images with field data collected in Ganzhou and Kangbao of China. The modified kNN was developed by integrating the traditional kNN estimation and RF classification. The results were compared with those from kNN and RF regression alone using three sets of input predictors: (i) spectral reflectance bands (input 1); (ii) vegetation indices (input 2); and (iii) a combination of spectral reflectance bands and vegetation indices (input 3). Our analysis showed that in Ganzhou, the red-edge bands of the Sentinel-2 image had a high correlation with LAI. Using the red-edge band-derived vegetation indices increased the accuracy of mapping LAI compared with using other spectral variables. Among the three sets of input predictors, input 3 resulted in the highest prediction accuracy. Based on the combination, the values of RMSE obtained by the traditional kNN, RF, and modified kNN were 0.526, 0.523, and 0.372, respectively, and the modified kNN significantly improved the accuracy of LAI prediction by 29.3% and 28.9% compared with the kNN and RF alone, respectively. A similar improvement was achieved for input 1 and input 2. In Kangbao, the improvement of the prediction accuracy obtained by the modified kNN was 31.4% compared with both the kNN and RF. Therefore, this study implied that the modified kNN provided the potential to improve the accuracy of mapping LAI in arid and semi-arid regions using the images. [ABSTRACT FROM AUTHOR]

There has been substantial research for estimating and mapping soil moisture content (SMC) of large areas using remotely sensed images by developing models of soil thermal inertia (STI). However, it is still a great challenge to accurately estimate SMC because of the impact of vegetation canopies and vegetation-induced shadows in mixed pixels on the estimates. In this study, a new method was developed to increase the estimation accuracy of SMC for an irrigated area located in YingKe of Heihe, China, using ASTER data. In the method, an original model of estimating bare STI was modified by decomposing a mixed pixel into three components, bare soil, vegetated soil, and shaded soil, as well as extracting their fractions using a spectral unmixing analysis and then deriving their fluxes. Moreover, the 90 m spatial resolution thermal images were scaled down to the 15 m spatial resolution by data fusion of a discrete wavelet transform (DWT) and re-sampling using the nearest neighbor method (NNM). The modified model was compared with the original model based on the mean absolute error (MAE) and relative root mean square error (RRMSE) between the SMC estimates and observations from 30 validation soil samples. The results indicated that compared to the original model based on the parallel dual layer, the modified STI model based on the serial dual layer statistically significantly decreased the MAE and RRMSE of the SMC estimates by 63.0–63.2% and 63.0–63.5%, respectively. The 15 m spatial resolution thermal bands obtained by the DWT data fusion provided more detailed information of SMC but did not significantly improve its estimation accuracy than the 15 m spatial resolution thermal bands by re-sampling using NNM. This implied that the novel method offered insights on how to increase the accuracy of retrieving SMC estimates in vegetated areas. [ABSTRACT FROM AUTHOR]

Unplanned urban settlements exist worldwide. The geospatial information of these areas is critical for urban management and reconstruction planning but usually unavailable. Automatically characterizing individual buildings in the unplanned urban village using remote sensing imagery is very challenging due to complex landscapes and high-density settlements. The newly emerging deep learning method provides the potential to characterize individual buildings in a complex urban village. This study proposed an urban village mapping paradigm based on U-net deep learning architecture. The study area is located in Guangzhou City, China. The Worldview satellite image with eight pan-sharpened bands at a 0.5-m spatial resolution and building boundary vector file were used as research purposes. There are ten sites of the urban villages included in this scene of the Worldview image. The deep neural network model was trained and tested based on the selected six and four sites of the urban village, respectively. Models for building segmentation and classification were both trained and tested. The results indicated that the U-net model reached overall accuracy over 86% for building segmentation and over 83% for the classification. The F1-score ranged from 0.9 to 0.98 for the segmentation, and from 0.63 to 0.88 for the classification. The Interaction over Union reached over 90% for the segmentation and 86% for the classification. The superiority of the deep learning method has been demonstrated through comparison with Random Forest and object-based image analysis. This study fully showed the feasibility, efficiency, and potential of the deep learning in delineating individual buildings in the high-density urban village. More importantly, this study implied that through deep learning methods, mapping unplanned urban settlements could further characterize individual buildings with considerable accuracy. [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]

Accurately estimating growing stem volume (GSV) is very important for forest resource management. The GSV estimation is affected by remote sensing images, variable selection methods, and estimation algorithms. Optical images have been widely used for modeling key attributes of forest stands, including GSV and aboveground biomass (AGB), because of their easy availability, large coverage and related mature data processing and analysis technologies. However, the low data saturation level and the difficulty of selecting feature variables from optical images often impede the improvement of estimation accuracy. In this research, two GaoFen-2 (GF-2) images, a Landsat 8 image, and fused images created by integrating GF-2 bands with the Landsat multispectral image using the Gram–Schmidt method were first used to derive various feature variables and obtain various datasets or data scenarios. A DC-FSCK approach that integrates feature variable screening and a combination optimization procedure based on the distance correlation coefficient and k-nearest neighbors (kNN) algorithm was proposed and compared with the stepwise regression analysis (SRA) and random forest (RF) for feature variable selection. The DC-FSCK considers the self-correlation and combination effect among feature variables so that the selected variables can improve the accuracy and saturation level of GSV estimation. To validate the proposed approach, six estimation algorithms were examined and compared, including Multiple Linear Regression (MLR), kNN, Support Vector Regression (SVR), RF, eXtreme Gradient Boosting (XGBoost) and Stacking. The results showed that compared with GF-2 and Landsat 8 images, overall, the fused image (Red_Landsat) of GF-2 red band with Landsat 8 multispectral image improved the GSV estimation accuracy of Chinese pine and larch plantations. The Red_Landsat image also performed better than other fused images (Pan_Landsat, Blue_Landsat, Green_Landsat and Nir_Landsat). For most of the combinations of the datasets and estimation models, the proposed variable selection method DC-FSCK led to more accurate GSV estimates compared with SRA and RF. In addition, in most of the combinations obtained by the datasets and variable selection methods, the Stacking algorithm performed better than other estimation models. More importantly, the combination of the fused image Red_Landsat with the DC-FSCK and Stacking algorithm led to the best performance of GSV estimation with the greatest adjusted coefficients of determination, 0.8127 and 0.6047, and the smallest relative root mean square errors of 17.1% and 20.7% for Chinese pine and larch, respectively. This study provided new insights on how to choose suitable optical images, variable selection methods and optimal modeling algorithms for the GSV estimation of Chinese pine and larch plantations. [ABSTRACT FROM AUTHOR]

China has been facing serious land degradation and desertification in its north and northwest arid and semi-arid areas. Monitoring the dynamics of percentage vegetation cover (PVC) using remote sensing imagery in these areas has become critical. However, because these areas are large, remote, and sparsely populated, and also because of the existence of mixed pixels, there have been no accurate and cost-effective methods available for this purpose. Spectral unmixing methods are a good alternative as they do not need field data and are low cost. However, traditional linear spectral unmixing (LSU) methods lack the ability to capture the characteristics of spectral reflectance and scattering from endmembers and their interactions within mixed pixels. Moreover, existing nonlinear spectral unmixing methods, such as random forest (RF) and radial basis function neural network (RBFNN), are often costly because they require field measurements of PVC from a large number of training samples. In this study, a cost-effective approach to mapping PVC in arid and semi-arid areas was proposed. A method for selection and purification of endmembers mainly based on Landsat imagery was first presented. A probability-based spectral unmixing analysis (PBSUA) and a probability-based optimized k nearest-neighbors (PBOkNN) approach were then developed to improve the mapping of PVC in Duolun County in Inner Mongolia, China, using Landsat 8 images and field data from 920 sample plots. The proposed PBSUA and PBOkNN methods were further validated in terms of accuracy and cost-effectiveness by comparison with two LSU methods, with and without purification of endmembers, and two nonlinear approaches, RF and RBFNN. The cost-effectiveness was defined as the reciprocal of cost timing relative root mean square error (RRMSE). The results showed that (1) Probability-based spectral unmixing analysis (PBSUA) was most cost-effective and increased the cost-effectiveness by 29.3% 29.3%, 33.5%, 50.8%, and 53.0% compared with two LSU methods, PBOkNN, RF, and RBFNN, respectively; (2) PBSUA, RF, and RBFNN gave RRMSE values of 22.9%, 21.8%, and 22.8%, respectively, which were not significantly different from each other at the significance level of 0.05. Compatibly, PBOkNN and LSU methods with and without purification of endmembers resulted in significantly greater RRMSE values of 27.5%, 32.4%, and 43.3%, respectively; (3) the average estimates of the sample plots and predicted maps from PBSUA, PBOkNN, RF, and RBFNN fell in the confidence interval of the test plot data, but those from two LSU methods did not, although the LSU with purification of endmembers improved the PVC estimation accuracy by 25.2% compared with the LSU without purification of endmembers. Thus, this study indicated that the proposed PBSUA had great potential for cost-effectively mapping PVC in arid and semi-arid areas. [ABSTRACT FROM AUTHOR]

Uncertainties in forest aboveground biomass (AGB) estimates resulting from over- and underestimations using remote sensing data have been widely studied. The uncertainties may occur due to the spatial effects of the plot data. In this study, we collected AGB data from a total of 147 Pinus densata forest sample plots in Yunnan of southwestern China and analyzed the spatial effects on the estimation of AGB. An ordinary least squares (OLS) and four spatial regression methods were compared for the estimation using Landsat 8-OLI images. Through the spatial analysis of AGB and residuals of model predictions, it was found that the spatial autocorrelation and heterogeneity of the plot data could not be ignored. Compared with the OLS, the impact of the spatial effects on AGB estimation could be reduced slightly by the spatial lag model (SLM) and the spatial error model (SEM) and greatly reduced by the linear mixed effects model (LMM) and geographically weighted regression (GWR) based on the distributions of prediction residuals, global Moran's I, and Z score. The spatial regression models had better performance for model fitting and prediction because of the reduction in overestimations and underestimations for the forests with small and large AGB values, respectively. However, the reductions in the overestimations and underestimations varied depending on the spatial regression models. The GWR provided the most accurate predictions with the largest R2 (0.665), the smallest root mean square error (34.507), and mean relative error (−9.070%) by greatly reducing the AGB interval for overestimations occurring and significantly increasing the threshold of AGB from 150 Mg/ha to 200 Mg/ha for underestimations. Thus, GWR offered the greatest potential of improving the estimation of Pinus densata forest AGB in Yunnan of southwestern China. [ABSTRACT FROM AUTHOR]

Spectral reflectance distortions caused by terrain and solar illumination seriously reduce the accuracy of mapping forest carbon density, especially in mountainous regions. Many models have been developed for mitigating or eliminating the terrain effects on the quality of remote sensing images in hilly and mountainous areas. However, these models usually use global parameters, which may lead to overcorrections for regions with poor illumination and steep slopes. In this study, we present a local parameter estimation (LPE) method based on a pixel-moving window for topographic correction (TC), which can be considered as a general optimization framework for most semiempirical TC models. We set seven kernel sizes for the presented framework, which are 15 pixels, 25 pixels, 50 pixels, 100 pixels, 250 pixels, 500 pixels, and 1000 pixels, respectively. The proposed method was then applied to four traditional TC models, Minnaert (MIN), C Correction (CC), Sun Canopy Sensor + C (SCSC) and Statistical Empirical Correction (SEC), to form four new TC models. These new models were used to estimate forest carbon density of a mountainous area in Southern China using field plot data and a Landsat 8 image. Four evaluation methods, including correlation analysis, the stability of land covers, comparison of reflectance between sunlit and shaded slopes, and accuracy assessment of forest carbon density, were employed to evaluate the contributions of moving window sizes, and assess the performance of the TC models for forest carbon density estimation. The results show that the four TC models with LPE perform much better than the traditional TC models in reducing the topographic effects and improving the estimation accuracy of forest carbon density for the study area. Among the traditional TC models, SEC performs slightly better than SCSC, CC, and MIN. Therefore, the SEC-based model with LPE, that is, LPE-SEC, gets greater R2 and smaller relative RMSE values in estimating forest carbon density than other models. Moreover, all the means of the predicted forest carbon density values fall in the confidence interval of the validation data at a significant level of 0.05. Overall, this study implies that the proposed method with LPE provides great potential to improve the performance of TC and forest carbon density estimation for the study area. It is expected that the improved TC method can be applied to other mountainous areas to improve the quality of remotely sensed images. [ABSTRACT FROM AUTHOR]

For the planning and sustainable management of forest resources, well-managed plantations are of great significance to mitigate the decrease of forested areas. Monitoring these planted forests is essential for forest resource inventories. In this study, two ALOS PALSAR-2 quad-polarimetric synthetic aperture radar (SAR) images and ground measurements were employed to estimate growing stem volume (GSV) of Chinese fir plantations located in a hilly area of southern China. To investigate the relationships between forest GSV and polarization characteristics, single and fused variables were derived by the Yamaguchi decomposition and the saturation value of GSV was estimated using a semi-exponential empirical model as a base model. Based on the estimated saturation values and relative root mean square error (RRMSE), the single and fused characteristics and corresponding models were selected and integrated, which led to a novel saturation-based multivariate method used to improve the GSV estimation and mapping of Chinese fir plantations. The new findings included: (1) All the original polarimetric characteristics, statistically, were not significantly correlated with the forest GSV, and their logarithm and ratio transformation fused variables greatly improved the correlations, thus the estimation accuracy of the forest GSV. (2) The logarithm transformation of surface scattering resulted in the greatest saturation, value but the logarithm transformation of double-bounce scattering resulted in the smallest RRMSE of the GSV estimates. (3) Compared with the single transformations, the fused variables led to more reasonable saturation values and obviously reduced the values of RRMSE. (4) The saturation-based multivariate method led to more accurate estimates of the forest GSV than the univariate method, with the smallest value (29.64%) of RRMSE achieved using the set of six variables. This implied that the novel saturation-based multivariate method provided greater potential to improve the estimation and mapping of the forest GSV. [ABSTRACT FROM AUTHOR]

Quickly and efficiently monitoring soil heavy metal content is crucial for protecting the natural environment and for human health. Estimating heavy metal content in soils using hyperspectral data is a cost-efficient method but challenging due to the effects of complex landscapes and soil properties. One of the challenges is how to make a lab-derived model based on soil samples applicable to mapping the contents of heavy metals in soil using air-borne or space-borne hyperspectral imagery at a regional scale. For this purpose, our study proposed a novel method using hyperspectral data from soil samples and the HuanJing-1A (HJ-1A) HyperSpectral Imager (HSI). In this method, estimation models were first developed using optimal relevant spectral variables from dry soil spectral reflectance (DSSR) data and field observations of soil heavy metal content. The relationship of the ratio of DSSR to moisture soil spectral reflectance (MSSR) with soil moisture content was then derived, which built up the linkage of DSSR with MSSR and provided the potential of applying the models developed in the laboratory to map soil heavy metal content at a regional scale using hyperspectral imagery. The optimal relevant spectral variables were obtained by combining the Boruta algorithm with a stepwise regression and variance inflation factor. This method was developed, validated, and applied to estimate the content of heavy metals in soil (As, Cd, and Hg) in Guangdong, China, and the Conghua district of Guangzhou city. The results showed that based on the validation datasets, the content of Cd could be reliably estimated and mapped by the proposed method, with relative root mean square error (RMSE) values of 17.41% for the point measurements of soil samples from Guangdong province and 17.10% for the Conghua district at the regional scale, while the content of heavy metals As and Hg in soil were relatively difficult to predict with the relative RMSE values of 32.27% and 28.72% at the soil sample level and 51.55% and 36.34% at the regional scale. Moreover, the relationship of the DSSR/MSSR ratio with soil moisture content varied greatly before the wavelength of 1029 nm and became stable after that, which linked DSSR with MSSR and provided the possibility of applying the DSSR-based models to map the soil heavy metal content at the regional scale using the HJ-1A images. In addition, it was found that overall there were only a few soil samples with the content of heavy metals exceeding the health standards in Guangdong province, while in Conghua the seriously polluted areas were mainly distributed in the cities and croplands. This study implies that the new approach provides the potential to map the content of heavy metals in soil, but the estimation model of Cd was more accurate than those of As and Hg. [ABSTRACT FROM AUTHOR]

Surface urban heat islands (SUHIs) have been investigated in many regions around the world, but little attention has been given with regard to SUHIs in South America. In this study, Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) data was used to investigate the diurnal, seasonal, and interannual variations in the SUHI intensity (SUHII, the urban LST minus the rural LST) in 44 South American cities in different climate zones and types of rural land. To examine the effects of factors that may influence the SUHII, correlations between the SUHII and the enhanced vegetation index (EVI), urban area, population, altitude, and anthropogenic heat emissions were performed. The results showed that the SUHI effect was obvious in South America. The mean daytime SUHII was higher than the mean night-time SUHII in all areas except for the arid climate zone. In the daytime, the summer displayed a stronger SUHII in the warm temperate climate zone than the other seasons. The night-time SUHII showed less obvious seasonal variations. In addition, the surrounding land cover influenced the SUHII. During the day, the SUHII was therefore stronger in rural areas that were covered by forests than in other types of rural land. Interannually, most cities showed an insignificant temporal trend in the SUHII from 2003 to 2016. The daytime SUHII was significantly and negatively correlated with the ∆EVI (the urban EVI minus the rural EVI) across the 44 cities, but a poor relationship was observed at night. In addition, anthropogenic heat emissions were positively correlated with the night-time SUHII. Urban area, population, and altitude were weakly correlated with the SUHII, which suggested that these factors may not have a significant impact on the spatial variations in the SUHII in South America. [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]

Optical remote sensing data have been widely used for estimating forest aboveground biomass (AGB). However, the use of optical images is often restricted by the saturation of spectral reflectance for forests that have multilayered and complex canopy structures and high AGB values and by the effect of spectral reflectance from underlayer shrub, grass, and bare soil for young stands. This usually leads to overestimations and underestimations for smaller and larger values, respectively, and makes it very challenging to improve the estimation accuracy of forest AGB. In this study, a novel methodology was proposed by incorporating stand age as a dummy variable into four models to improve the estimation accuracy of the Pinus densata forest AGB in Yunnan of Southwestern China. A total of eight models, including two parametric models (LM: linear regression model and LMC: LM with combined variables), two nonparametric models (RF: random forest and ANN: artificial neural network) without the age dummy variable, and four corresponding models with the age dummy variable (DLM, DLMC, DRF, and DANN), were compared to estimate AGB. Landsat 8 Operational Land Imager (OLI) images and 147 sample plots were acquired and utilized. The results showed that (1) compared with the two parametric models, the two nonparametric algorithms resulted in significantly greater estimation accuracies of Pinus densata forest AGB, and the increases of accuracy varied from 8% to 32% for 100 modeling plots and from 12% to 35% for 47 test plots based on root mean square error (RMSE); (2) compared with the models without the age dummy variable, the models with the age dummy variable greatly reduced the overestimations for the plots with AGB values smaller than 70 Mg/ha and the underestimations for the plots with AGB values larger than 180 Mg/ha and, thus, significantly improved the overall estimation accuracy by 14% to 42% for the modeling plots and by 32% to 44% for the test plots based on RMSE; and (3) the texture measures derived from the Landsat 8 OLI images contributed more to improving the estimation accuracy than the original spectral bands and other transformations. This implied that two nonparametric models, coupled with the use of the age dummy variable and texture measures, offered a great potential for improving the estimation accuracy of Pinus densata forest AGB. [ABSTRACT FROM AUTHOR]

Estimating the net primary production (NPP) of vegetation is essential for eco-environment conservation and carbon cycle research. Remote sensing techniques, combined with algorithm models, have been proven to be promising methods for NPP estimation. High-precision and real-time NPP monitoring in heterogeneous areas requires high spatio-temporal resolution remote sensing data, which are not easy to acquire by single remote sensors, especially in cloudy weather. This study proposes to fuse images of different sensors to provide high spatio-temporal resolution data for NPP estimation in cloud-prone areas. Firstly, the time series Normalized Difference Vegetation Index (NDVI) with a spatial resolution of 30 m and a temporal resolution of 16 days, are obtained by the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM). Then, the time series NDVI data, combined with meteorological data are input into an improved Carnegie–Ames–Stanford Approach (CASA) model for NPP estimation. This method is validated by a case study of a heavily urbanized area, in the middle reaches of the Yangtze River in China. The results indicate that the NPP estimated by the fused NDVI data has more detailed spatial information than by using the MODIS data. The results show a strong correlation between the actual Landsat8 NDVI and the fused NDVI images, which means that the accuracy of synthetic NDVI images (a 16 day interval and a 30 m resolution) is reliable, and it can provide superior inputs for accurate estimations of a NPP time series. The correlation coefficient (R) and root mean square error between the NPP, based on the fused NDVI and the measured NPP, are 0.66 and 14.280 g C/(m2·yr), respectively, indicating a good consistency. The small discrepancy is caused by the uncertainties of fused NDVI, measurement errors, conversion errors, and other factors in the CASA model. In this study, we achieved NPP with high spatial and temporal resolutions, which can provide higher accuracies of NPP data for analyzing the carbon cycling heavily urbanized areas, compared with similar studies using mono-temporal NPP data. The spatio-temporal fusion technique is an effective way of generating high spatio-temporal resolution images from different sensors, thereby providing enough data for NPP monitoring in urbanized areas. [ABSTRACT FROM AUTHOR]

Rice is one of the world's major staple foods, especially in China. Highly accurate monitoring on rice-producing land is, therefore, crucial for assessing food supplies and productivity. Recently, the deep-learning convolutional neural network (CNN) has achieved considerable success in remote-sensing data analysis. A CNN-based paddy-rice mapping method using the multitemporal Landsat 8, phenology data, and land-surface temperature (LST) was developed during this study. First, the spatial–temporal adaptive reflectance fusion model (STARFM) was used to blend the moderate-resolution imaging spectroradiometer (MODIS) and Landsat data for obtaining multitemporal Landsat-like data. Subsequently, the threshold method is applied to derive the phenological variables from the Landsat-like (Normalized difference vegetation index) NDVI time series. Then, a generalized single-channel algorithm was employed to derive LST from the Landsat 8. Finally, multitemporal Landsat 8 spectral images, combined with phenology and LST data, were employed to extract paddy-rice information using a patch-based deep-learning CNN algorithm. The results show that the proposed method achieved an overall accuracy of 97.06% and a Kappa coefficient of 0.91, which are 6.43% and 0.07 higher than that of the support vector machine method, and 7.68% and 0.09 higher than that of the random forest method, respectively. Moreover, the Landsat-derived rice area is strongly correlated (R2 = 0.9945) with government statistical data, demonstrating that the proposed method has potential in large-scale paddy-rice mapping using moderate spatial resolution images. [ABSTRACT FROM AUTHOR]

The international GNSS monitoring and assessment system (iGMAS) tracking network has been established by China to track multi-GNSS satellites. A key feature of iGMAS stations is the capability to fully track new navigation signals from the recently deployed BDS-3 satellites. In addition to the B1I and B3I signals inherited from BDS-2 satellites, the BDS-3 satellites are capable of transmitting new open service signals, including B1C at 1575.42 MHz, B2a at 1176.45 MHz, and B2b at 1207.14 MHz. In this contribution, we present a comprehensive analysis and characterization of GNSS signals tracked by different receivers and antennas equipped in the iGMAS network, especially as they relate to BDS-3 signals. Signal characteristics are analyzed in terms of the carrier-to-noise density ratio for the different signals as measured by the receiver, as well as pseudo-range noise and multipath. Special attention is given to discussion of the satellite-induced code bias, which has been identified to exist in the code observations of BDS-2, and the inter-frequency clock bias (IFCB), which has been observed in the triple-frequency carrier phase combinations of GPS Block IIF and BDS-2 satellites. The results indicate that the satellite-induced code bias is negligible for all signals of BDS-3 satellites, while small IFCB variations with peak amplitudes of about 1 cm can be recognized in BDS-3 triple-carrier combinations. [ABSTRACT FROM AUTHOR]

Land degradation and desertification in arid and semi-arid areas is of great concern. Accurately mapping percentage vegetation cover (PVC) of the areas is critical but challenging because the areas are often remote, sparsely vegetated, and rarely populated, and it is difficult to collect field observations of PVC. Traditional methods such as regression modeling cannot provide accurate predictions of PVC in the areas. Nonparametric constant k-nearest neighbors (Cons_kNN) has been widely used in estimation of forest parameters and is a good alternative because of its flexibility. However, using a globally constant k value in Cons_kNN limits its ability of increasing prediction accuracy because the spatial variability of PVC in the areas leads to spatially variable k values. In this study, a novel method that spatially optimizes determining the spatially variable k values of Cons_kNN, denoted with Opt_kNN, was proposed to map the PVC in both Duolun and Kangbao County located in Inner Mongolia and Hebei Province of China, respectively, using Landsat 8 images and sample plot data. The Opt_kNN was compared with Cons_kNN, a linear stepwise regression (LSR), a geographically weighted regression (GWR), and random forests (RF) to improve the mapping for the study areas. The results showed that (1) most of the red and near infrared band relevant vegetation indices derived from the Landsat 8 images had significant contributions to improving the mapping accuracy; (2) compared with LSR, GWR, RF and Cons_kNN, Opt_kNN resulted in consistently higher prediction accuracies of PVC and decreased relative root mean square errors by 5%, 11%, 5%, and 3%, respectively, for Duolun, and 12%, 1%, 23%, and 9%, respectively, for Kangbao. The Opt_kNN also led to spatially variable and locally optimal k values, which made it possible to automatically and locally optimize k values; and (3) the RF that has become very popular in recent years did not perform the predictions better than the Opt_kNN for the both areas. Thus, the proposed method is very promising to improve mapping the PVC in the arid and semi-arid areas. [ABSTRACT FROM AUTHOR]

Remote sensing–based forest aboveground biomass (AGB) estimation has been extensively explored in the past three decades, but how to effectively combine different sensor data and modeling algorithms is still poorly understood. This research conducted a comparative analysis of different datasets (e.g., Landsat Thematic Mapper (TM), ALOS PALSAR L-band data, and their combinations) and modeling algorithms (e.g., artificial neural network (ANN), support vector regression (SVR), Random Forest (RF), k-nearest neighbor (kNN), and linear regression (LR)) for AGB estimation in a subtropical region under non-stratification and stratification of forest types. The results show the following: (1) Landsat TM imagery provides more accurate AGB estimates (root mean squared error (RMSE) values in 27.7–29.3 Mg/ha) than ALOS PALSAR (RMSE values in 30.3–33.7 Mg/ha). The combination of TM and PALSAR data has similar performance for ANN and SVR, worse performance for RF and KNN, and slightly improved performance for LR. (2) Overestimation for small AGB values and underestimation for large AGB values are major problems when using the optical (e.g., Landsat) or radar (e.g., ALOS PALSAR) data. (3) LR is still an important tool for AGB modeling, especially for the AGB range of 40–120 Mg/ha. Machine learning algorithms have limited effects on improving AGB estimation overall, but ANN can improve AGB modeling when AGB values are greater than 120 Mg/ha. (4) Forest type and AGB range are important factors that influence AGB modeling performance. (5) Stratification based on forest types improved AGB estimation, especially when AGB was greater than 160 Mg/ha, using the LR approach. This research provides new insight for remote sensing-based AGB modeling for the subtropical forest ecosystem through a comprehensive analysis of different source data, modeling algorithms, and forest types. It is critical to develop an optimal AGB modeling procedure, including the collection of a sufficient number of sample plots, extraction of suitable variables and modeling algorithms, and evaluation of the AGB estimates. [ABSTRACT FROM AUTHOR]