Accurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables from Sentinel-1 synthetic aperture radar (SAR), Sentinal-2 multispectral instrument (MSI) and SRTM digital elevation model (DEM) data were composed into four groups and evaluated for their effectiveness in prediction of AGB. Five evaluated algorithms include linear regression such as stepwise regression (SWR) and geographically weighted regression (GWR); machine learning (ML) such as artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that the RF model used predictors from both the Sentinel series and SRTM DEM performed the best, based on the independent validation set. The RF model achieved accuracy with the mean error, mean absolute error, root mean square error, and correlation coefficient in 1.39, 25.48, 61.11 Mg·ha⁻¹ and 0.9769, respectively. Texture characteristics, reflectance, vegetation indices, elevation, stream power index, topographic wetness index and surface roughness were recommended predictors for AGB prediction. Predictor variables were more important than algorithms for improving the accuracy of AGB estimates. The study demonstrated encouraging results in the optimal combination of predictors and algorithms for forest AGB mapping, using openly accessible and fine-resolution data based on RF algorithms.

Accurate digital soil mapping (DSM) of soil organic carbon (SOC) is still a challenging subject because of its spatial variability and dependency. This study is aimed at comparing six typical methods in three types of DSM techniques for SOC mapping in an area surrounding Changchun in Northeast China. The methods include ordinary kriging (OK) and geographically weighted regression (GWR) from geostatistics, support vector machines for regression (SVR) and artificial neural networks (ANN) from machine learning, and geographically weighted regression kriging (GWRK) and artificial neural networks kriging (ANNK) from hybrid approaches. The hybrid approaches, in particular, integrated the GWR from geostatistics and ANN from machine learning with the estimation of residuals by ordinary kriging, respectively. Environmental variables, including soil properties, climatic, topographic, and remote sensing data, were used for modeling. The mapping results of SOC content from different models were validated by independent testing data based on values of the mean error, root mean squared error and coefficient of determination. The prediction maps depicted spatial variation and patterns of SOC content of the study area. The results showed the accuracy ranking of the compared methods in decreasing order was ANNK, SVR, ANN, GWRK, OK, and GWR. Two-step hybrid approaches performed better than the corresponding individual models, and non-linear models performed better than the linear models. When considering the uncertainty and efficiency, ML and two-step approach are more suitable than geostatistics in regional landscapes with the high heterogeneity. The study concludes that ANNK is a promising approach for mapping SOC content at a local scale.

Drastic urbanization has resulted in numerous problems worldwide, and many studies were devoted to individual cities. There is an urgent need to quantify urbanization patterns and illustrate their driving forces in the regional area on a large scale over a longer time period. This study produced a land cover dataset to characterize sequential urban land expansion in Northeast China from 1990 to 2015 using object-based backdating classification and calculating the expansion index. The drivers were investigated using Pearson correlation analysis and the multiple linear stepwise regression model. The results revealed that the total area of urban land increased by 43.15% from 1990 to 2015, mainly in the middle part of the study area, and especially in the coastal area of Liaoning. Liaoning had the fastest growth rate, while Heilongjiang showed a decrease in growth rate rankings. Urban land expanded northward and southward within Harbin City, towards the west and east within Changchun City, and relatively equally in all directions within Shenyang City. Expansion patterns changed from edge expansion (42%) to outlying expansion (47%). Urban land of Liaoning and the Eastern Inner Mongolia Autonomous region expanded with similar patterns as the entire area, but that of Heilongjiang grew in an opposite pattern, and Jilin maintained outlying major expansion. The influence of factors on urban land sprawl varied temporally. Tertiary industry product, gross domestic product, secondary industry product, total population and urban population were driving factors of urban land sprawl in Northeast China from 1990 to 2015. This research provides quantitative methods for better understanding urban land dynamics and devising feasible strategies for sustainable urban development.

Accurate and effective mapping of forest aboveground biomass (AGB) in heterogeneous mountainous regions is a huge challenge but an urgent demand for resource managements and carbon storage monitoring. Conventional studies have related the plot-measured or LiDAR-based biomass to remote sensing data using pixel-based approaches. The object-based relationship between AGB and multi-source data from LiDAR, multi-frequency radar, and optical sensors were insufficiently studied. It deserves the further exploration that maps forest AGB using the object-based approach and combines LiDAR data with multi-sensor images, which has the smaller uncertainty of positional discrepancy and local heterogeneity, in heterogeneous mountainous regions. To address the improvement of mapping accuracy, satellite LiDAR data from GEDI and ICEsat-2, and images of ALOS-2 yearly mosaic L band SAR (Synthetic Aperture Radar), Sentinel-1 C band SAR, Sentinel-2 MSI, and ALOS-1 DSM were combined for pixel- and object-based forest AGB mapping in a vital heterogeneous mountainous forest. For the object-based approach, optimized objects during a multiresolution segmentation were acquired by the ESP (Estimation of the Scale Parameter) tool, and suitable predictors were selected using an algorithm named VSURF (Variable Selection Using Random Forests). The LiDAR variables at the footprint-level were extracted to connect field plots to the multi-sensor objects as a linear bridge. It was shown that forests’ AGB values varied by elevations with a mean value of 142.58 Mg/ha, ranging from 12.61 to 514.28 Mg/ha. The north slope with the lowest elevation (<1100 m) had the largest mean AGB, while the smallest mean AGB was located in the south slope with the altitude above 2000 m. Using independent validation samples, it was indicated by the accuracy comparison that the object-based approach performed better on the precision with relative improvement based on root-mean-square errors (RI_RMSE) of 4.46%. The object-based approach also selected more optimized predictors and markedly decreased the prediction time than the pixel-based analysis. Canopy cover and height explained forest AGB with their effects on biomass varying according to the elevation. The elevation from DSM and variables involved in red-edge bands from MSI were the most contributive predictors in heterogeneous temperate forests. This study is a pioneering exploration of object-based AGB mapping by combining satellite data from LiDAR, MSI, and SAR, which offers an improved methodology for regional carbon mapping in the heterogeneous mountainous forests.

Comparative evaluation of cross-boundary wetland protected areas is essential to underpin knowledge-based bilateral conservation policies and funding decisions by governments and managers. In this paper, wetland change monitoring for the Wusuli River Basin in the cross-boundary zone of China and Russia from 1990 to 2015 was quantitatively analyzed using Landsat images. The spatial-temporal distribution of wetlands was identified using a rule-based object-oriented classification method. Wetland dynamics were determined by combining annual land change area (ALCA), annual land change rate (ALCR), landscape metrics and spatial analysis in a geographic information system (GIS). A Mann–Kendall test was used to evaluate changing climate trends. Results showed that natural wetlands in the Wusuli River Basin have declined by 5625.76 km² in the past 25 years, especially swamp/marsh, which decreased by 26.88%. Specifically, natural wetlands declined by 49.93% in the Chinese section but increased with an ALCA of 16.62 km²/y in the Russian section during 1990–2015. Agricultural encroachment was the most important reason for the loss and degradation of natural wetlands in the Wusuli River Basin, especially in China. Different population change trends and conservation policies in China and Russia affected natural wetland dynamics. The research offers an efficient and effective method to evaluate cross-boundary wetland change. This study provides important scientific information necessary for developing future ecological conservation and management of cross-boundary wetlands.

The accurate characterization of tree species distribution in forest areas can help significantly reduce uncertainties in the estimation of ecosystem parameters and forest resources. Deep learning algorithms have become a hot topic in recent years, but they have so far not been applied to tree species classification. In this study, one-dimensional convolutional neural network (Conv1D), a popular deep learning algorithm, was proposed to automatically identify tree species using OHS-1 hyperspectral images. Additionally, the random forest (RF) classifier was applied to compare to the algorithm of deep learning. Based on our experiments, we drew three main conclusions: First, the OHS-1 hyperspectral images used in this study have high spatial resolution (10 m), which reduces the influence of mixed pixel effect and greatly improves the classification accuracy. Second, limited by the amount of sample data, Conv1D-based classifier does not need too many layers to achieve high classification accuracy. In addition, the size of the convolution kernel has a great influence on the classification accuracy. Finally, the accuracy of Conv1D (85.04%) is higher than that of RF model (80.61%). Especially for broadleaf species with similar spectral characteristics, such as Manchurian walnut and aspen, the accuracy of Conv1D-based classifier is significantly higher than RF classifier (87.15% and 71.77%, respectively). Thus, the Conv1D-based deep learning framework combined with hyperspectral imagery can efficiently improve the accuracy of tree species classification and has great application prospects in the future.