Yeqiao Wang

The new year brings new challenges, hopes, resolutions and solutions. It is encouraging to recall some of the efforts and progress achieved in the past year towards improving understanding about th...

Mangrove-forest classification by using deep learning algorithms has attracted increasing attention but remains challenging. The current studies on the transfer classification of mangrove communities between different regions and different sensors are especially still unclear. To fill the research gap, this study developed a new deep-learning algorithm (encoder–decoder with mixed depth-wise convolution and cascade upsampling, MCCUNet) by modifying the encoder and decoder sections of the DeepLabV3+ algorithm and presented three transfer-learning strategies, namely frozen transfer learning (F-TL), fine-tuned transfer learning (Ft-TL), and sensor-and-phase transfer learning (SaP-TL), to classify mangrove communities by using the MCCUNet algorithm and high-resolution UAV multispectral images. This study combined the deep-learning algorithms with recursive feature elimination and principal component analysis (RFE–PCA), using a high-dimensional dataset to map and classify mangrove communities, and evaluated their classification performance. The results of this study showed the following: (1) The MCCUNet algorithm outperformed the original DeepLabV3+ algorithm for classifying mangrove communities, achieving the highest overall classification accuracy (OA), i.e., 97.24%, in all scenarios. (2) The RFE–PCA dimension reduction improved the classification performance of deep-learning algorithms. The OA of mangrove species from using the MCCUNet algorithm was improved by 7.27% after adding dimension-reduced texture features and vegetation indices. (3) The Ft-TL strategy enabled the algorithm to achieve better classification accuracy and stability than the F-TL strategy. The highest improvement in the F1–score of Spartina alterniflora was 19.56%, using the MCCUNet algorithm with the Ft-TL strategy. (4) The SaP-TL strategy produced better transfer-learning classifications of mangrove communities between images of different phases and sensors. The highest improvement in the F1–score of Aegiceras corniculatum was 19.85%, using the MCCUNet algorithm with the SaP-TL strategy. (5) All three transfer-learning strategies achieved high accuracy in classifying mangrove communities, with the mean F1–score of 84.37~95.25%.

Water is the basis of all life on this planet. Yet, approximately one in seven people in the world do not have access to safe water. Water can become unsafe due to contamination by various organic and inorganic compounds due to various natural and anthropogenic processes. Identifying and monitoring water quality changes in space and time remains a challenge, especially when contamination events occur over large geographic areas. This study investigates recent advances in remote sensing that allow us to detect and monitor the unique spectral characteristics of water quality events over large areas. Based on an extensive literature review, we focus on three critical water quality problems as part of this study: algal blooms, acid mine drainage, and suspended solids. We review the advances made in applications of remote sensing in each of these issues, identify the knowledge gaps and limitations of current studies, analyze the existing approaches in the context of global environmental changes, and discuss potential ways to combine multi-sensor methods and different wavelengths to develop improved approaches. Synthesizing the findings of these studies in the context of the three specific tracks will help stakeholders to utilize, share, and embed satellite-derived earth observations for monitoring and tracking the ever-evolving water quality in the earth’s limited freshwater reserves.

Rapid and accurate estimation of maize biomass is critical for predicting crop productivity. The launched Sentinel-1 (S-1) synthetic aperture radar (SAR) and Sentinel-2 (S-2) missions offer a new opportunity to map biomass. The selection of appropriate response variables is crucial for improving the accuracy of biomass estimation. We developed models from SAR polarization indices, vegetation indices (VIs), and biophysical variables (BPVs) based on gaussian process regression (GPR) and random forest (RF) with feature optimization to retrieve maize biomass in Changchun, Jilin province, Northeastern China. Three new predictors from each type of remote sensing data were proposed based on the correlations to biomass measured in June, July, and August 2018. The results showed that a predictor combined by vertical-horizontal polarization (VV), vertical-horizontal polarization (VH), and the difference of VH and VV (VH-VV) derived from S-1 images of June, July, and August, respectively, with GPR and RF, provided a more accurate estimation of biomass (R² = 0.81–0.83, RMSE = 0.40–0.41 kg/m²) than the models based on single SAR polarization indices or their combinations, or optimized features (R² = 0.04–0.39, RMSE = 0.84–1.08 kg/m²). Among the S-2 VIs, the GPR model using a combination of ratio vegetation index (RVI) of June, normalized different infrared index (NDII) of July, and normalized difference vegetation index (NDVI) of August achieved a result with R² = 0.83 and RMSE = 0.39 kg/m², much better than single VIs or their combination, or optimized features (R² of 0.31–0.77, RMSE of 0.47–0.87 kg/m²). A BPV predictor, combined with leaf chlorophyll content (CAB) in June, canopy water content (CWC) in July, and fractional vegetation cover (FCOVER) in August, with RF, also yielded the highest accuracy (R² = 0.85, RMSE = 0.38 kg/m²) compared to that of single BPVs or their combinations, or optimized subset. Overall, the three combined predictors were found to be significant contributors to improving the estimation accuracy of biomass with GPR and RF methods. This study clearly sheds new insights on the application of S-1 and S-2 data on maize biomass modeling.

Wetlands provide various ecosystem services to urban areas, which are crucial for sustainable urban management. With intensified urbanization, there has been marked loss of urban natural wetland, degradation, and related urban disasters in the past several decades. Rapid and accurate mapping of urban wetland extent and change is thus critical for improving urban planning toward sustainability. Here, we have developed a rapid method for continuous mapping of urban wetlands (MUW) by combining automatic sample migration and the random forest algorithm (SM&RF), the so-called MUW_SM&RF. Using time series Landsat images, annual training samples were generated through spectral angular distance (SAD) and time series analysis. Combined with the RF algorithm, annual wetland maps in urban areas were derived. Employing the Google Earth Engine platform (GEE), the MUW_SM&RF was evaluated in four metropolitan areas in different geographical and climatic regions of China from 1990 to 2020, including Tianjin, Hangzhou, Guangzhou, and Wuhan. In all four study areas, the generated annual wetland maps had an overall accuracy of over 87% and a Kappa coefficient above 0.815. Compared with previously published datasets, the urban wetland areas derived using the MUW_SM&RF approach achieved improved accuracy and thus demonstrated its robustness for rapid mapping of urban wetlands. Urban wetlands in all four cities had variable distribution patterns and showed significantly decreased trends in the past three decades. The annual urban wetland data product generated by the MUW_SM&RF can provide invaluable information for sustainable urban planning and management, so as for assessment related to the United Nation’s sustainable development goals.

At the anniversary of launching All Earth as a new open access forward-looking and broad-science journal publishing in all disciplines of Earth sciences, it is important to emphasise that All Earth...

Land surface albedo (LSA) directly affects the radiation balance and the surface heat budget. LSA is a key variable for local and global climate research. The complexity of LSA variations and the driving factors highlight the importance of continuous spatial and temporal monitoring. Snow, vegetation and soil are the main underlying surface factors affecting LSA dynamics. In this study, we combined Global Land Surface Satellite (GLASS) products and ERA5 reanalysis products to analyze the spatiotemporal variation and drivers of annual mean blue-sky albedo for stable land cover types in the middle-high latitudes of the Northern Hemisphere (30~90°N) from 1982 to 2015. Snow cover (SC) exhibited a decreasing trend in 99.59% of all pixels (23.73% significant), with a rate of −0.0813. Soil moisture (SM) exhibited a decreasing trend in 85.66% of all pixels (22.27% significant), with a rate of −0.0002. The leaf area index (LAI) exhibited a greening trend in 74.38% of all pixels (25.23% significant), with a rate of 0.0014. Blue-sky albedo exhibited a decreasing trend in 98.97% of all pixels (65.12% significant), with a rate of −0.0008 (OLS slope). Approximately 98.16% of all pixels (57.01% significant) exhibited a positive correlation between blue-sky albedo and SC. Approximately 47.78% and 67.38% of all pixels (17.13% and 25.3% significant, respectively) exhibited a negative correlation between blue-sky albedo and SM and LAI, respectively. Approximately 10.31%, 20.81% and 68.88% of the pixel blue-sky albedo reduction was mainly controlled by SC, SM and LAI, respectively. The decrease in blue-sky albedo north of 40°N was mainly caused by the decrease in SC. The decrease in blue-sky albedo south of 40°N was mainly caused by SM reduction and vegetation greening. The decrease in blue-sky albedo in the western Tibetan Plateau was caused by vegetation greening, SM increase and SC reduction. The results have important scientific significance for the study of surface processes and global climate change.

All Earth is a reinvention of an existing JCR- and Scopus-listed peer-reviewed fully open access journal, i.e. Geodinamica Acta, and re-launched as a new forward-looking and broad-science journal p...