Explore the vast range of titles available.

Urban sustainable development has attracted widespread attention worldwide as it is closely linked with human survival. However, the growth of urban areas is frequently disproportionate in relation to population growth in developing countries; this discrepancy cannot be monitored solely using statistics. In this study, we integrated earth observation (EO) and statistical data monitoring the Sustainable Development Goals (SDG) 11.3.1: “The ratio of land consumption rate to the population growth rate (LCRPGR)”. Using the EO data (including China’s Land-Use/Cover Datasets (CLUDs) and the Defense Meteorological Satellite Program/Operational Linescan System (DMSP/OLS) nighttime light data) and census, we extracted the percentage of built-up area, disaggregated the population using the geographically weighted regression (GWR) model, and depicted the spatial heterogeneity and dynamic tendency of urban expansion and population growth by a 1 km × 1 km grid at city and national levels in mainland China from 1990 to 2010. Then, the built-up area and population density datasets were compared with other products and statistics using the relative error and standard deviation in our research area. Major findings are as follows: (1) more than 95% of cities experienced growth in urban built-up areas, especially in the megacities with populations of 5–10 million; (2) the number of grids with a declined proportion of the population ranged from 47% in 1990–2000 to 54% in 2000–2010; (3) China’s LCRPGR value increased from 1.69 in 1990–2000 to 1.78 in 2000–2010, and the land consumption rate was 1.8 times higher than the population growth rate from 1990 to 2010; and (4) the number of cities experiencing uncoordinated development (i.e., where urban expansion is not synchronized with population growth) increased from 93 (27%) in 1990–2000 to 186 (54%) in 2000–2010. Using EO has the potential for monitoring the official SDGs on large and fine scales; the processes provide an example of the localization of SDG 11.3.1 in China.

This research utilized in situ soil moisture observations in a coupled grid Soil and Water Assessment Tool (SWAT) and Parallel Data Assimilation Framework (PDAF) data assimilation system, resulting in significant enhancements in soil moisture estimation. By incorporating Wireless Sensor Network (WSN) data (WATERNET), the method captured and integrated local soil moisture characteristics, thereby improving regional model state estimations. The use of varying observation search radii with the Local Error-subspace Transform Kalman Filter (LESTKF) resulted in improved spatial and temporal assimilation performance, while also considering the impact of observation data uncertainties. The best performance (improvement of 0.006 m3/m3) of LESTKF was achieved with a 20 km observation search radii and 0.01 m3/m3 observation standard error. This study assimilated wireless sensor network data into a distributed model, presenting a departure from traditional methods. The high accuracy and resolution capabilities of WATERNET’s regional soil moisture observations were crucial, and its provision of multi-layered soil temperature and moisture observations presented new opportunities for integration into the data assimilation framework, further enhancing hydrological state estimations. This study’s implications are broad and relevant to regional-scale water resource research and management, particularly for freshwater resource scheduling at small basin scales.

Wetland methane (CH₄) emissions are the largest natural source in the global CH₄ budget, contributing to roughly one third of total natural and anthropogenic emissions. As the second most important anthropogenic greenhouse gas in the atmosphere after CO₂, CH₄ is strongly associated with climate feedbacks. However, due to the paucity of data, wetland CH₄ feedbacks were not fully assessed in the Intergovernmental Panel on Climate Change Fifth Assessment Report. The degree towhich future expansion of wetlands and CH₄ emissions will evolve and consequently drive climate feedbacks is thus a question of major concern. Here we present an ensemble estimate of wetland CH₄ emissions driven by 38 general circulation models for the 21st century. We find that climate change-induced increases in boreal wetland extent and temperature-driven increases in tropical CH₄ emissions will dominate anthropogenic CH₄ emissions by 38 to 56% toward the end of the 21st century under the Representative Concentration Pathway (RCP2.6). Depending on scenarios, wetland CH₄ feedbacks translate to an increase in additional global mean radiative forcing of 0.04 W·m−2 to 0.19 W·m−2 by the end of the 21st century. Under the “worst-case” RCP8.5 scenario, with no climate mitigation, boreal CH₄ emissions are enhanced by 18.05 Tg to 41.69 Tg, due to thawing of inundated areas during the cold season (December to May) and rising temperature, while tropical CH₄ emissions accelerate with a total increment of 48.36 Tg to 87.37 Tg by 2099. Our results suggest that climate mitigation policies must consider mitigation of wetland CH₄ feedbacks to maintain average global warming below 2 °C.

Accurate estimation of crop area is essential to adjusting the regional crop planting structure and the rational planning of water resources. However, it is quite challenging to map crops accurately by high-resolution remote sensing images because of the ecological gradient and ecological convergence between crops and non-crops. The purpose of this study is to explore the combining application of high-resolution multi-temporal Sentinel-1 (S1) radar backscatter and Sentinel-2 (S2) optical reflectance images for maize mapping in highly complex and heterogeneous landscapes in the middle reaches of Heihe River, northwest China. We proposed a new two-step method of vegetation extraction and followed by maize extraction, that is, extract the vegetation-covered areas first to reduce the inter-class variance by using a Random Forest (RF) classifier based on S2 data, and then extract the maize distribution in the vegetation area by using another RF classifier based on S1 and/or S2 data. The results demonstrate that the vegetation extraction classifier successfully identified vegetation-covered regions with an overall accuracy above 96% in the study area, and the accuracy of the maize extraction classifier constructed by the combined multi-temporal S1 and S2 images is significantly improved compared with that S1 (alone) or S2 (alone), with an overall accuracy of 87.63%, F1_Score of 0.86, and Kappa coefficient of 0.75. In addition, with the introduction of multi-temporal S1 and/or S2 images in crop growing season, the constructed RF model is more beneficial to maize mapping.

In order to anticipate residual errors and improve accuracy while reducing uncertainties, this work integrates the long short-term memory (LSTM) with the Soil and Water Assessment Tool (SWAT) to create a deep learning (DL) model that is guided by physics. By forecasting the residual errors of the SWAT model, the SWAT-informed LSTM model (LSTM-SWAT) differs from typical LSTM approaches that predict the streamflow directly. Through numerical tests, the performance of the LSTM-SWAT was evaluated with both LSTM-only and SWAT-only models in the Upper Heihe River Basin. The outcomes showed that the LSTM-SWAT performed better than the other models, showing higher accuracy and a lower mean absolute error (MAE = 3.13 m3/s). Sensitivity experiments further showed how the quality of the training dataset affects the performance of the LSTM-SWAT. The results of this study demonstrate how the LSTM-SWAT may improve streamflow prediction greatly by remote sensing and in situ observations. Additionally, this study emphasizes the need for detailed consideration of specific sources of uncertainty to further improve the predictive capabilities of the hybrid model.

Accurate high-resolution gridded livestock distribution data are of great significance for the rational utilization of grassland resources, environmental impact assessment, and the sustainable development of animal husbandry. Traditional livestock distribution data are collected at the administrative unit level, which does not provide a sufficiently detailed geographical description of livestock distribution. In this study, we proposed a scheme by integrating high-resolution gridded geographic data and livestock statistics through machine learning regression models to spatially disaggregate the livestock statistics data into 1 km × 1 km spatial resolution. Three machine learning models, including support vector machine (SVM), random forest (RF), and deep neural network (DNN), were constructed to represent the complex nonlinear relationship between various environmental factors (e.g., land use practice, topography, climate, and socioeconomic factors) and livestock density. By applying the proposed method, we generated a set of 1 km × 1 km spatial distribution maps of cattle and sheep for western China from 2000 to 2015 at five-year intervals. Our projected cattle and sheep distribution maps reveal the spatial heterogeneity structures and change trend of livestock distribution at the grid level from 2000 to 2015. Compared with the traditional census livestock density, the gridded livestock distribution based on DNN has the highest accuracy, with the determinant coefficient (R2) of 0.75, root mean square error (RMSE) of 9.82 heads/km2 for cattle, and the R2 of 0.73, RMSE of 31.38 heads/km2 for sheep. The accuracy of the RF is slightly lower than the DNN but higher than the SVM. The projection accuracy of the three machine learning models is superior to those of the published Gridded Livestock of the World (GLW) datasets. Consequently, deep learning has the potential to be an effective tool for high-resolution gridded livestock projection by combining geographic and census data.

Data scarcity is a key factor impacting the current emphasis on individual indicators and the distribution of large-scale spatial objects in country-level SDG 6 research. An investigation of progress assessments and factors influencing SDG implementation in cities and counties indicates that smaller-scale regions hold greater operational significance for achieving the 2030 Agenda for Sustainable Development from the bottom up; thus, urgent attention should be given to data deficiencies and inadequate analyses related to SDG impact attribution. This study, conducted in the National Innovative Demonstration Zone for Sustainable Development of Lincang City, investigates multisource data sources such as integrated statistics, survey data, and remote sensing data to analyze the progress and status of SDG 6 achievement from 2015–2020, and employs the LMDI decomposition model to identify influential factors. The assessment results demonstrate that the SDG 6 composite index in Lincang increased from 0.47 to 0.61 between 2015 and 2020. The SDG 6 indicators and SDG 6 composite index have significant spatial heterogeneity. The water resources indexes in wealthy countries are high, the water environment and water ecology indexes in developing countries are comparatively high, and the SDG 6 composite index is high in undeveloped counties. Technological and economic advances are the main positive drivers impacting the SDG 6 composite index, and the relative contributions of technology, economy, structure, and population are 61.84%, 54.16%, −4.03%, and −11.96%, respectively. This study shows that integrated multisource data can compensate for the lack of small-scale regional statistical data when quantitative and comprehensive multi-indicator evaluations of the SDGs are conducted. And, policies related to SDG 6.1.1, SDG 6.2.1, and SDG 6.3.1 can be a priority for implementation in undeveloped regions with limited funding.

Moderate Resolution Imaging Spectroradiometer (MODIS) snow cover product is one of the prevailing datasets for global snow monitoring, but cloud obscuration leads to the discontinuity of ground coverage information in spatial and temporal. To solve this problem, a novel spatial-temporal missing information reconstruction model based on U-Net with partial convolutions (PU-Net) is proposed to recover the cloud gaps in the MODIS Normalized Difference Snow Index (NDSI) products. Taking the Yellow River Source Region as a study case, in which the snow cover is characterized by shallow, fast-changing and complex heterogeneity, the MODIS NDSI product in the 2018–2019 snow season is reconstructed, and the reconstruction accuracy is validated with simulated cloud mask and in situ snow depth (SD) observations. The results show that under the simulated cloud mask scenario, the mean absolute error (MAE) of the reconstructed missing pixels is from 4.22% to 18.81% under different scenarios of the mean NDSI of the patch and the mask ratio of the applied mask, and the coefficient of determination (R2) ranges from 0.76 to 0.94. The validation based on in situ SD observations at 10 sites shows good consistency, the overall accuracy is increased by 25.66% to 49.25% compared with the Aqua-Terra combined MODIS NDSI product, and its value exceeds 90% at 60% of observation stations.

We present a novel inversion approach using a neural network to locate subsurface targets and evaluate their backscattering properties from ground penetrating radar (GPR) data. The presented inversion strategy constructs an adaptive linear element (ADALINE) neural network, whose configuration is related to the unknown properties of the targets. The GPR data is reconstructed (compression) to fit the structure of the neural network. The constructed neural network works with a supervised training mode, where a series of primary functions derived from the GPR signal model are used as the input, and the reconstructed GPR data is the expected/target output. In this way, inverting the GPR data is the equivalent of training the network. The back-propagation (BP) algorithm is employed for the training of the neural network. The numerical experiments show that the proposed approach can return an exact estimation for the target’s location. Under sparse conditions, an inverted backscattering intensity with a relative error lower than 3% was achieved, whereas for the multi-dominating point scenario, a higher error rate was observed. Finally, the limitations and further developments for the inverting GPR data with the neural network are discussed.

Precipitation monitoring is important for earth system modeling and environmental management. Low spatial representativeness limits gauge measurements of rainfall and low spatial resolution limits satellite-derived rainfall. SM2RAIN-based products, which exploit the inversion of the water balance equation to derive rainfall from soil moisture (SM) observations, can be an alternative. However, the quality of SM data limits the accuracy of rainfall. The goal of this work was to improve the accuracy of rainfall estimation through merging multiple soil moisture (SM) datasets. This study proposed an integration framework, which consists of multiple machine learning methods, to use satellite and ground-based soil moisture observations to derive a precipitation product. First, three machine learning (ML) methods (random forest (RF), long short-term memory (LSTM), and convolutional neural network (CNN)) were used, respectively to generate three SM datasets (RF-SM, LSTM-SM, and CNN-SM) by merging satellite (SMOS, SMAP, and ASCAT) and ground-based SM observations. Then, these SM datasets were merged using the Bayesian model averaging method and validated by wireless sensor network (WSN) observations. Finally, the merged SM data were used to produce a rainfall dataset (SM2R) using SM2RAIN. The SM2R dataset was validated using automatic meteorological station (AMS) rainfall observations recorded throughout the Upper Heihe River Basin (China) during 2014–2015 and compared with other rainfall datasets. Our results revealed that the quality of the SM2R data outperforms that of GPM-SM2RAIN, Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), ERA5-Land (ERA5) and multi-source weighted-ensemble Precipitation (MSWEP). Triple-collocation analysis revealed that SM2R outperformed China Meteorological Data and the China Meteorological Forcing Dataset. Ultimately, the SM2R rainfall product was considered successful with acceptably low spatiotemporal errors (RMSE = 3.5 mm, R = 0.59, and bias = −1.6 mm).