Search

Accurate and timely crop yield prediction over large spatial regions is critical to national food security and sustainable agricultural development. However, designing a robust model for crop yield prediction over a large spatial region remains challenging due to inadequate surveyed samples and an under-development of deep-learning frameworks. To tackle this issue, we integrated multi-source (remote sensing, weather, and soil properties) data into a dual-stream deep-learning neural network model for winter wheat in China's major planting regions. The model consists of two branches for robust feature learning: one for sequential data (remote sensing and weather series data) and the other for statical data (soil properties). The extracted features by both branches were aggregated through an adaptive fusion model to forecast the final wheat yield. We trained and tested the model by using official county-level statistics of historical winter wheat yields. The model achieved an average R2 of 0.79 and a root-mean-square error of 650.21 kg/ha, superior to the compared methods and outperforming traditional machine-learning methods. The dual-stream deep-learning neural network model provided decent in-season yield prediction, with an error of about 13% compared to official statistics about two months before harvest. By effectively extracting and aggregating features from multi-source datasets, the new approach provides a practical approach to predicting winter wheat yields at the county scale over large spatial regions. [ABSTRACT FROM AUTHOR]

Grassland aboveground biomass is crucial for evaluating grassland desertification, degradation, and grassland and livestock balance. Given the lack of understanding of mechanical processes and limited simulation accuracy for grassland aboveground biomass estimation, especially at the regional scale, this study investigates a new method combining remote sensing data assimilation technology and a grassland process-based model to estimate regional grassland biomass, focusing on improving the simulation accuracy by modeling and revealing the mechanism interpretability of grassland growth processes. Xilinhot City of Inner Mongolia was used as the study area. The ModVege model was selected as the grass dynamic simulation model. A likelihood function was constructed composed of the LAI, grassland aboveground biomass, and daily measurements wherein the accumulated temperature reached ST2 (the temperature sum defining the end of reproductive growth). Then, the Markov chain Monte Carlo (MCMC) methodology was adapted to calibrate the ModVege model by maximizing the likelihood function. The time-series LAI from MOD15A3H was assimilated into the ModVege model, and the model parameters ST2 and BMGV0 (initial biomass and green vegetative tissues, respectively) were optimized at a 500 m pixel scale based on the four-dimensional variational method (4DVar) method. Compared with August 15th, the RMSE and MAPE of aboveground biomass were 242 kg/ha and 10%, respectively, after calibration. Data assimilation improved this accuracy, with the RMSE decreasing to 214 kg/ha. Overall, the aboveground grassland biomass of Xilinhot City shows spatial distribution patterns of high value in the northeast and low value in the central and southeast areas. Generally, the method implemented in this study provides an important reference for the aboveground biomass estimation of regional grassland. [ABSTRACT FROM AUTHOR]

Human Footprint, the pressure imposed on the eco-environment by changing ecological processes and natural landscapes, is raising worldwide concerns on biodiversity and ecological conservation. Due to the lack of spatiotemporally consistent datasets of Human Footprint over a long temporal span, many relevant studies on this topic have been limited. Here, we mapped the annual dynamics of the global Human Footprint from 2000 to 2018 using eight variables that reflect different aspects of human pressures. The accuracy assessment revealed a good agreement between our mapped results and the previously developed datasets in different years. We found more than two million km2 of wilderness (i.e., regions with Human Footprint values below one) were lost over the past two decades. The biome dominated by mangroves experienced the most significant loss (i.e., above 5%) of wilderness, likely attributed to intensified human activities in coastal areas. The derived annual and spatiotemporally consistent global Human Footprint can be a fundamental dataset for many relevant studies about human activities and natural resources. Measurement(s) human footprint Technology Type(s) remote sensing Factor Type(s) Built Environment • Population Density • Nighttime lights • Croplands • Pastures • Roads • Railways • Navigable waterways [ABSTRACT FROM AUTHOR]

Understanding the spatiotemporal dynamics of global urbanization over a long time series is increasingly important for sustainable development goals. The harmonized nighttime light (NTL) time-series composites created by fusing multi-source NTL observations provide a long and consistent record of the nightscape for characterizing and understanding global urban dynamics. In this study, we generated a global dataset of annual urban extents (1992–2020) using consistent NTL observations and analyzed the spatiotemporal patterns of global urban dynamics over nearly 30 years. The urbanized areas associated with locally high intensity human activities were mapped from the global NTL time-series imagery using a new stepwise-partitioning framework. This framework includes three components: (1) clustering of NTL signals to generate potential urban clusters, (2) identification of optimal thresholds to delineate annual urban extents, and (3) check of temporal consistency to correct pixel-level urban dynamics. We found that the global urban land area percentage of the Earth's land surface rose from 0.22 % to 0.69 % between 1992 and 2020. Urban dynamics over the past 3 decades at the continent, country, and city levels exhibit various spatiotemporal patterns. Our resulting global urban extents (1992–2020) were evaluated using other urban remote sensing products and socioeconomic data. The evaluations indicate that this dataset is reliable for characterizing spatial extents associated with intensive human settlement and high-intensity socioeconomic activities. The dataset of global urban extents from this study can provide unique information to capture the historical and future trajectories of urbanization and to understand and tackle urbanization impacts on food security, biodiversity, climate change, and public well-being and health. This dataset can be downloaded from 10.6084/m9.figshare.16602224.v1 (Zhao et al., 2021). [ABSTRACT FROM AUTHOR]

Impervious surfaces are the most significant feature of human settlements. Timely, accurate, and frequent information on impervious surfaces is critical in both social-economic and natural environment applications. Over the past 40 years, impervious surface areas in China have grown rapidly. However, annual maps of impervious areas in China with high spatial details do not exist during this period. In this paper, we made use of reliable impervious surface mapping algorithms that we published before and the Google Earth Engine (GEE) platform to address this data gap. With available data in GEE, we were able to map impervious surfaces over the entire country circa 1978, and during 1985–2017 at an annual frequency. The 1978 data were at 60-m resolution, while the 1985–2017 data were in 30-m resolution. For the 30-m resolution data, we evaluated the accuracies for 1985, 1990, 1995, 2000, 2005, 2010, and 2015. Overall accuracies reached more than 90%. Our results indicate that the growth of impervious surface in China was not only fast but also considerably exceeding the per capita impervious surface area in developed countries like Japan. The 40-year continuous and consistent impervious surface distribution data in China would generate widespread interests in the research and policy-making community. The impervious surface data can be freely downloaded from http://data.ess.tsinghua.edu.cn. [ABSTRACT FROM AUTHOR]

Cellular automata (CA) is a powerful tool for modeling the evolution of macroscopic scale phenomena as it couples time, space, and variables together while remaining in a simplified form. However, such application has remained challenging in forest insect epidemics due to the highly dynamic nature of insect behavior. Recent advances in temporal trajectory-based image analysis offer an alternative way to obtain high-frequency model calibration data. In this study, we propose an insect-CA modeling framework that integrates cellular automata, remote sensing, and Geographic Information System to understand the insect ecological processes, and tested it with measured data of mountain pine beetle (MPB) in the Rocky Mountains. The overall accuracy of the predicted MPB mortality pattern in the test years ranged from 88% to 94%, which illuminates its effectiveness in modeling forest insect dynamics. We further conducted sensitivity analysis to examine responses of model performance to various parameter settings. In our case, the ensemble random forest algorithm outperforms the traditional linear regression in constructing the suitability surface. Small neighborhood size is more effective in simulating the MPB movement behavior, indicating that short-distance is the dominating dispersal mode of MPB. The introduction of a stochastic perturbation component did not improve the model performance after testing a broad range of randomness degree, reflecting a relative compact dispersal pattern rather than isolated outbreaks. We conclude that CA with remote sensing observation is useful for landscape insect movement analyses; however, consideration of several key parameters is critical in the modeling process and should be more thoroughly investigated in future work. [ABSTRACT FROM AUTHOR]

In this paper, we introduced major challenges in mapping croplands, settlements, water and wetlands, and discussed challenges in the use of multi-temporal and multi-sensor data. We then summarized some of the on-going efforts in improving qualities of global land cover maps. Existing technologies provide sufficient data for better map making if extra efforts can be made instead of harmonizing and integrating various global land cover products. Developing and selecting better algorithms, including more input variables (new types of data or features) for classification, having representative training samples are among conventional measures generally believed effective in improving mapping accuracies at local scales. We pointed out that data were more important in improving mapping accuracies than algorithms. Finally, we proposed a new paradigm for global land cover mapping, which included a view of vegetation classes based on their types and form, canopy cover and height. The new paradigm suggests that a universally applicable training sample set is not only possible but also effective in improving land cover classification at the continental and global scales. To ensure an easy transition from traditional land cover mapping to the new paradigm, we recommended that an all-in-one data management and analysis system be constructed. [ABSTRACT FROM AUTHOR]

Since the launch of the first land-observation satellite (Landsat-1) in 1972, land-cover mapping has accumulated a wide range of knowledge in the peer-reviewed literature. However, this knowledge has never been comprehensively analysed for new discoveries. Here, we developed the first spatialized database of scientific literature in English about land-cover mapping. Using this database, we tried to identify the spatial temporal patterns and spatial hotspots of land-cover mapping research around the world. Among other findings, we observed (1) a significant mismatch between hotspot areas of land-cover mapping and areas that are either hard to map or rich in biodiversity; (2) mapping frequency is positively related to economic conditions; (3) there is no obvious temporal trend showing improvement in mapping accuracy; (4) images with more spectral bands or a combination of data types resulted in increased mapping accuracies; (5) accuracy differences due to algorithm differences are not as large as those due to various types of data used; and (6) the complexity of a classification system decreases its mapping accuracy. We recommend that one way to improve our understanding of the challenges, advances, and applications of previous land-cover mapping is for journals to require area-based information at the time of manuscript submission. In addition, building a standard protocol for systematic assessment of land-cover mapping efforts at the global scale through international collaboration is badly needed. [ABSTRACT FROM PUBLISHER]

• We built a policy-driven regional ecological network in China. • We evaluated the corridors in the network using the space syntax approach. • We identified vulnerable regions from the ecological network. • We applied the ecological network for human footprint and biodiversity analyses. The Three-North Shelterbelt (TNS) program is one of China's major ecological restoration projects over the past few decades. However, evaluation of the ecological network in the TNS region has not been explored yet, in the face of intensified human activities. This study evaluated the ecological network in the TNS region from a policy-driven perspective (i.e., nature reserves). First, we mapped the ecological resistance surface in the TNS region using multiple remotely sensed ecological indicators. Then, using the derived resistance surface, we generated the ecological network and evaluated its connectivity (e.g., corridors) using the space syntax approach. Finally, we investigated the intensity of human activities and the occurrence of species around the derived ecological network. We found the ecological network is denser in humid regions than in arid areas. There are several vulnerable regions in the southern part of the Qilian Mountains and the northern part of Shaanxi. Besides, we observed overall consistent decreasing trends of human activities and species numbers along with the increase of distance to the ecological network, suggesting these corridors of ecological network play a crucial role in maintaining the biodiversity, although they are also under severe stresses of intensified human activities. Our study provides a paradigm of generating the ecological network at a large scale (i.e., the entire TNS region), showing great potential to support the phase III TNS program for sustainable development of ecological resources. [ABSTRACT FROM AUTHOR]

Earth system science has changed rapidly due to global environmental changes and the advent of Earth observation technology. Therefore, new tools are required to monitor, measure, analyze, evaluate, and model Earth observation data. Google Earth (GE) was officially launched by Google in 2005 as a "geobrowser", and Google Earth Engine (GEE) was released in 2010 as a cloud computing platform with substantial computational capabilities. The use of these two tools or platforms in various applications, particularly as used by the remote sensing community, has developed rapidly. In this paper, we reviewed the applications and trends in the use of GE and GEE by analyzing peer-reviewed articles, dating up to January 2021, in the Web of Science (WoS) core collection using scientometric analysis (i.e., by using CiteSpace) and meta-analysis. We found the following: (1) the number of articles describing the use of GE or GEE increased substantially from two in 2006 to 530 in 2020. The number of GEE articles increased much faster than those concerned with the use of GE. (2) Both GE and GEE were extensively used by the remote sensing community as multidisciplinary tools. GE articles covered a broader range of research areas (e.g., biology, education, disease and health, economic, and information science) and appeared in a broader range of journals than those concerned with the use of GEE. (3) GE and GEE shared similar keywords (e.g., "land cover", "water", "model", "vegetation", and "forest"), which indicates that their application is of great importance in certain research areas. The main difference was that articles describing the use of GE emphasized its use as a visual display platform, while those concerned with GEE placed more emphasis on big data and time-series analysis. (4) Most applications of GE and GEE were undertaken in countries, such as the United States, China, and the United Kingdom. (5) GEE is an important tool for analysis, whereas GE is used as an auxiliary tool for visualization. Finally, in this paper, the merits and limitations of GE and GEE, and recommendations for further improvements, are summarized from an Earth system science perspective. [ABSTRACT FROM AUTHOR]

Black soil is one of the most productive soils with high organic matter content. Crop residue covering is important for protecting black soil from alleviating soil erosion and increasing soil organic carbon. Mapping crop residue covered areas accurately using remote sensing images can monitor the protection of black soil in regional areas. Considering the inhomogeneity and randomness, resulting from human management difference, the high spatial resolution Chinese GF-1 B/D image and developed MSCU-net+C deep learning method are used to mapping corn residue covered area (CRCA) in this study. The developed MSCU-net+C is joined by a multiscale convolution group (MSCG), the global loss function, and Convolutional Block Attention Module (CBAM) based on U-net and the full connected conditional random field (FCCRF). The effectiveness of the proposed MSCU-net+C is validated by the ablation experiment and comparison experiment for mapping CRCA in Lishu County, Jilin Province, China. The accuracy assessment results show that the developed MSCU-net+C improve the CRCA classification accuracy from IOUAVG = 0.8604 and KappaAVG = 0.8864 to IOUAVG = 0.9081 and KappaAVG = 0.9258 compared with U-net. Our developed and other deep semantic segmentation networks (MU-net, GU-net, MSCU-net, SegNet, and Dlv3+) improve the classification accuracy of IOUAVG/KappaAVG with 0.0091/0.0058, 0.0133/0.0091, 0.044/0.0345, 0.0104/0.0069, and 0.0107/0.0072 compared with U-net, respectively. The classification accuracies of IOUAVG/KappaAVG of traditional machine learning methods, including support vector machine (SVM) and neural network (NN), are 0.576/0.5526 and 0.6417/0.6482, respectively. These results reveal that the developed MSCU-net+C can be used to map CRCA for monitoring black soil protection. [ABSTRACT FROM AUTHOR]

Garlic and winter wheat are major economic and grain crops in China, and their boundaries have increased substantially in recent decades. Updated and accurate garlic and winter wheat maps are critical for assessing their impacts on society and the environment. Remote sensing imagery can be used to monitor spatial and temporal changes in croplands such as winter wheat and maize. However, to our knowledge, few studies are focusing on garlic area mapping. Here, we proposed a method for coupling active and passive satellite imagery for the identification of both garlic and winter wheat in Northern China. First, we used passive satellite imagery (Sentinel-2 and Landsat-8 images) to extract winter crops (garlic and winter wheat) with high accuracy. Second, we applied active satellite imagery (Sentinel-1 images) to distinguish garlic from winter wheat. Third, we generated a map of the garlic and winter wheat by coupling the above two classification results. For the evaluation of classification, the overall accuracy was 95.97%, with a kappa coefficient of 0.94 by eighteen validation quadrats (3 km by 3 km). The user's and producer's accuracies of garlic are 95.83% and 95.85%, respectively; and for the winter wheat, these two accuracies are 97.20% and 97.45%, respectively. This study provides a practical exploration of targeted crop identification in mixed planting areas using multisource remote sensing data. [ABSTRACT FROM AUTHOR]

The Guangdong–Hong Kong–Macau Greater Bay Area (GBA) of China is one of the largest bay areas in the world. However, the spatiotemporal characteristics and driving mechanisms of urban expansions in this region are poorly understood. Here we used the annual remote sensing images, Geographic Information System (GIS) techniques, and geographical detector method to characterize the spatiotemporal patterns of urban expansion in the GBA and investigate their driving factors during 1986–2017 on regional and city scales. The results showed that: the GBA experienced an unprecedented urban expansion over the past 32 years. The total urban area expanded from 652.74 km2 to 8137.09 km2 from 1986 to 2017 (approximately 13 times). The annual growth rate during 1986–2017 was 8.20% and the annual growth rate from 1986 to 1990 was the highest (16.89%). Guangzhou, Foshan, Dongguan, and Shenzhen experienced the highest urban expansion rate, with the annual increase of urban areas in 51.51, 45.54, 36.76, and 23.26 km2 y−1, respectively, during 1986–2017. Gross Domestic Product (GDP), income, road length, and population were the most important driving factors of the urban expansions in the GBA. We also found the driving factors of the urban expansions varied with spatial and temporal scales, suggesting the general understanding from the regional level may not reveal detailed urban dynamics. Detailed urban management and planning policies should be made considering the spatial and internal heterogeneity. These findings can enhance the comprehensive understanding of this bay area and help policymakers to promote sustainable development in the future. [ABSTRACT FROM AUTHOR]

Vegetation phenology plays a pivotal role in regulating several ecological processes and has profound impacts on global carbon exchange. Large-scale vegetation phenology monitoring mostly relies on Low-Earth-Orbit satellite observations with low temporal resolutions, leaving gaps in data that are important for monitoring seasonal vegetation phenology. High temporal resolution satellite observations have the potential to fill this gap by frequently collecting observations on a global scale, making it easier to study change over time. This study explored the potential of using the Earth Polychromatic Imaging Camera (EPIC) onboard the Deep Space Climate Observatory (DSCOVR) satellite, which captures images of the entire sunlit face of the Earth at a temporal resolution of once every 1–2 h, to observe vegetation phenology cycles in North America. We assessed the strengths and shortcomings of EPIC-based phenology information in comparison with the Moderate-resolution Imaging Spectroradiometer (MODIS), Enhanced Thematic Mapper (ETM+) onboard Landsat 7, and PhenoCam ground-based observations across six different plant functional types. Our results indicated that EPIC could capture and characterize seasonal changes of vegetation across different plant functional types and is particularly consistent in the estimated growing season length. Our results also provided new insights into the complementary features and benefits of the four datasets, which is valuable for improving our understanding of the complex response of vegetation to global climate variability and other disturbances and the impact of phenology changes on ecosystem productivity and global carbon exchange. [ABSTRACT FROM AUTHOR]

Nighttime light observations from remote sensing provide us with a timely and spatially explicit measure of human activities, and therefore enable a host of applications such as tracking urbanization and socioeconomic dynamics, evaluating armed conflicts and disasters, investigating fisheries, assessing greenhouse gas emissions and energy use, and analyzing light pollution and health effects. The new and improved sensors, algorithms, and products for nighttime lights, in association with other Earth observations and ancillary data (e.g., geo-located big data), together offer great potential for a deep understanding of human activities and related environmental consequences in a changing world. This paper reviews the advances of nighttime light sensors and products and examines the contributions of nighttime light remote sensing to perceiving the changing world from two aspects (i.e., human activities and environmental changes). Based on the historical review of the advances in nighttime light remote sensing, we summarize the challenges in current nighttime light remote sensing research and propose four strategic directions, including: Improving nighttime light data; developing a long time series of consistent nighttime light data; integrating nighttime light observations with other data and knowledge; and promoting multidisciplinary and interdisciplinary analyses of nighttime light observations. [ABSTRACT FROM AUTHOR]

Ongoing climate variability and change is impacting pollen exposure dynamics among sensitive populations. However, pollen data that can provide beneficial information to allergy experts and patients alike remains elusive. The lack of high spatial resolution pollen data has resulted in a growing interest in using phenology information that is derived using satellite observations to infer key pollen events including start of pollen season (SPS), timing of peak pollen season (PPS), and length of pollen season (LPS). However, it remains unclear if the agreement between satellite-based phenology information (e.g. start of season: SOS) and the in-situ pollen dynamics vary based on the type of satellite product itself or the processing methods used. To address this, we investigated the relationship between vegetation phenology indicator (SOS) derived from two separate sensor/satellite observations (MODIS, Landsat), and two different processing methods (d ouble l ogistic r egression (DLM) vs h ybrid p iecewise l ogistic r egression (HPLM)) with in-situ pollen season dynamics (SPS, PPS, LPS) for three dominant allergenic tree pollen species (birch, oak, and poplar) that dominate the springtime allergy season in North America. Our results showed that irrespective of the data processing method (i.e. DLM vs HPLM), the MODIS-based SOS to be more closely aligned with the in-situ SPS, and PPS while upscaled Landsat based SOS had a better precision. The data products obtained using DLM processing methods tended to perform better than the HPLM based methods. We further showed that MODIS based phenology information along with temperature and latitude can be used to infer in-situ pollen dynamic for tree pollen during spring time. Our findings suggest that satellite-based phenology information may be useful in the development of early warning systems for allergic diseases. • Ongoing climate change is altering pollen season dynamics. • Lack of pollen monitoring data makes it difficult to manage allergic symptoms. • Satellite data can be leveraged to inform pollen dynamics at high spatial resolution. [ABSTRACT FROM AUTHOR]

• Developing a two-step inference algorithm to solve the joint posterior distribution of model parameters and state variables in assimilating remote sensing into crop model. • The effectiveness of the proposed DA algorithm has been verified experimentally. • Introducing the uncertainties of model parameters quantified by MCMC and LAI observations quantified by GPR into the ensemble data assimilation method. Data assimilation techniques integrating crop growth models and remote sensing technologies offer a feasible approach for large-scale crop yield estimation. Previous research has primarily focused on either recalibrate the uncertain model parameters or updating model state variables independently using remotely sensed observations. In this study, we developed a two-step inference algorithm that couples the parameter inference and the state update, to solve the joint posterior distribution of uncertain parameters and state variables given the remote sensing observations. An Observing Simulation System (OSS) experiment was first performed based on the WOFOST crop model to validate the effectiveness of the parameter inference method. The results indicate that, the parameter inference method successfully improved the estimation of different types of model parameters and enhanced yield estimation. Furthermore, leaf area index (LAI) retrieved from Sentinel-2 was assimilated into the WOFOST model to simulate winter wheat yield at the plot scale in the northeastern part of Henan Province. The results demonstrated that the proposed two-step inference algorithm can more effectively correct model simulation biases and improve winter wheat yield estimation accuracy (R²=0.58, MAPE=12.75 %, and RMSE=1112 kg·ha⁻¹), outperforming the standard EnKF algorithm (R²=0.51, MAPE=14.62 %, RMSE=1328 kg·ha⁻¹). Overall, attributed to its unified approach to estimating both model parameters and state variables, the proposed two-step inference algorithm shows promising application prospects for data assimilation-based crop yield estimation. [ABSTRACT FROM AUTHOR]

• A new Regional Geo-Statistics (RGS) Method is proposed to better extract remote sensing features for yield estimation. • Adding the surface reflectance bands to the vegetation index as features can improve the accuracy of yield estimation. • The multi-source data can realize the best yield estimation results. • LightGBM is capable of yield prediction on remote sensing data. • Quantitative analysis of the contribution of multi-source data. Timely and accurate estimation of maize yield is crucial for ensuring food security. This study integrated multi-source data (satellite, meteorological, and soil data) on Google Earth Engine (GEE) and used machine learning techniques to estimate summer maize yield across 469 counties in the Huang-Huai-Hai Plain of China from 2010 to 2020. A novel method for extracting features from remote sensing images was proposed called the Regional Geo-Statistics (RGS) Method. We compared its performance with the traditional county-level averages method and explained the impact and contributions of incorporating multi-source data on yield estimation models. Firstly, Enhanced Vegetation Index (EVI) and Near-Infrared Vegetation Reflectance (NIRv) were transformed into regional geostatistical vectors and county-level averages using GEE. Then, yield was estimated using LightGBM, RF and LASSO. The results highlighted the superiority of the RGS method, with LightGBM yielding the best model (R2 = 0.55, RMSE = 852.92 kg/ha, NRMSE = 13.66 %). Further improvements were achieved by gradually adding meteorological and soil variables, with R2 improvements of 0.03 and 0.20, respectively. The Comprehensive Factor Model (CFM), utilizing all data as features, achieved the best results (R2 = 0.76, RMSE = 629.33 kg/ha, NRMSE = 10.08 %). The interpretability analysis based on CFM model underscored the significance of soil-related variables, which contributed significantly (45.38 %) alongside remote sensing variables, emphasizing the crucial role of soil variables in maize yield estimation. This study presents a versatile and reliable method for integrating multi-source data for maize yield estimation, supporting agricultural management and food security. [ABSTRACT FROM AUTHOR]

China has launched a series of ambitious poverty alleviation strategies to end extreme poverty, officially announcing the achievement of this goal in 2020. Currently, these counties persist in their efforts to achieve the goal of rural revitalization. Many studies often showcase the spatial patterns of China's remarkable success in counties out of poverty, but often disregard the relative poverty-returning risk (PRR), specifically within China's 832 extreme poverty counties. Nighttime light datasets (NTL) have been extensively employed as a surrogate measure for socioeconomic performance in underserved regions. In this work, we constructed an NTL-based relative PRR index to detect the spatial patterns of PRR among 832 counties. Then, we identified the main influencing factors concerning the PRR mitigation of 14 poverty-stricken clusters based on three dimensions: geophysical, economic, and social. Our results showed that counties in central China are far from returning to extreme poverty with low PRR. However 14 counties (2.41% of the 832) show high PRR, and those counties are mainly clustered in southwest China. This implies that those regions require more poverty-related policy support, financial inflows, and assistance. Regional differences were found in the factors that influence the mitigation of PRR. This is crucial for developing targeted strategies to consolidate poverty eradication. Our findings are essential for China's poverty-related SDGs, ensuring that no one is left behind. [Display omitted] • We investigated the 832 county-level relative PRRs. • China's relative PRRs are spatially imbalanced at the county level. • High PRR counties (2.41%) clusters gathering in southwestern China were observed. • There are geographic discrepancies in the factors that alleviate PRR. [ABSTRACT FROM AUTHOR]

• The developed ACNN model outperforms RF and 1DCNN models in identifying spatial heterogeneity of wheat yields. • Coupling of 1D CNNs and multi-channel attention mechanism to improve feature learning. • Investigated the importance of key phenological stages and spectral bands for yield estimation. Accurately expressing the spatial pattern of crop yield at a sizeable regional field scale is paramount for precision agriculture. However, the current methodologies consistently face numerous challenges, comprising inadequate yield samples and algorithmic tendencies to underestimate higher yield values and overestimate lower ones. Data-driven deep learning algorithms effectively transform remotely sensed data into high-dimensional feature representations. Developing a cost-efficient model that minimizes the impact of insufficient field samples while maximizing the representation of crop yield differences on plots is worthwhile. The study developed an ACNN (Attention-based One-dimensional Convolutional Neural Network) model to efficiently extract and optimize the spatiotemporal features of winter wheat yield from Sentinel-2 MSI Level-2A data while relatively reducing the model's reliance on training samples. Winter wheat yield at both county and field scales in Henan Province was estimated utilizing Random Forest (RF), Convolutional Neural Network (CNN), and the ACNN models. The proposed ACNN model effectively identified key phenological stages and discerned noteworthy spectral bands essential for field-scale winter wheat yield estimation. It underscores the heading stage as a pivotal period influencing yield formation, emphasizing the indispensable contributions of the B8 (835.1 nm) and B12 (2202.4 nm) spectral bands in yield estimation. Moreover, this model adeptly overcame the challenge of underestimating higher values and overestimating lower values in crop yield estimation while showcasing robust generalization ability. The study presents a practical method for field-scale crop yield estimation over a large area with insufficient yield samples. [ABSTRACT FROM AUTHOR]

Allometric urban scaling law quantifies disproportional relationships between urban indicators and city size, which has been reported across developed countries and parts of the global south, but its applicability in Africa is neglected. Here, taking built-up areas derived from remote sensing in more than 7000 African agglomerations in 2015 as examples, we systematically investigate this settlement scaling law from continental, regional, and country levels. Results show that the built-up area linearly scales with population across the African continent and within northern and western Africa, while it sub-linearly scales with population in southern (β = 0.85, 95% CI: 0.808–0.891) and central (β = 0.93, 95% CI: 0.906–0.957) Africa, but super-linearly (β = 1.10, 95% CI:1.068–1.121) in eastern Africa. National settlement scaling exponents (β) vary from 0.65 to 1.25 with an average of 0.96, whose 63.6% variance can be explained by their share of built-up area, share of metropolitan population, GDP per capita, and proportion of slum dwellers. Residuals of scaling fitting reflect local population-land tensions. Western and eastern Africa are relatively rich in buildable land resources, while northern Africa is relatively poor. This study expanded the settlement scaling theory in Africa and multiple indicators are needed to further understand the rapidly evolving African urban systems. • We verify the applicability of scaling law in the African urban system. • Built-up areas sub-linearly scale with city size in southern and central Africa, but super-linearly in eastern Africa. • Settlement scaling law uncovers disparities in the population-land tension. • Socioeconomic and urban development factors account for the variance of settlement scaling exponents. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • Change patterns of global mining spots were presented. • North America have more surface mining spots categorized as shrink type (rehabilitated). • South America and Asia had the highest proportions of expand type of mining spots. • The potential of remote sensing to monitoring changes of surface mining region were investigated. Abstract Quantifying the spatiotemporal change of land cover and understanding their ecological, environmental, and socioeconomic impacts are important for sustainable development. Surface mining by the minerals industry is one driver of the changes in land cover, leading to loss of natural vegetation and top soils, and interruption of ecosystem service flows. This study investigates the effectiveness of remote sensing datasets to identify and map land cover changes, with the specific goal of understanding the impact of surface mining activities on land cover globally from 1980s to 2013. Diverse remote sensing datasets with long term observations are analyzed, including high-resolution images in Google Earth, Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI), the Moderate Resolution Imaging Spectroradiometer (MODIS) Vegetation Index (VI) product and Defense Meteorological Satellites Program (DMSP)/Operational Linescan System (OLS) stable night-time light. The results indicated that after entering 21st century, North America (e.g., the United States and Canada) was the only continent to have more surface mining spots categorized as Shrink type (rehabilitated) rather than Expand type. South America (e.g., Chile and Brazil) and Asia (e.g., India and China) had the highest proportions of Expand Type of surface mining spots. Detailed demonstrations on how those remote sensing datasets could help in mining spot monitoring are presented. [ABSTRACT FROM AUTHOR]