Land Cover Products Research Articles

Algorithm, Progresses, Datasets and Validation of GLC_FCS30D: the first global 30 m land-cover dynamic product with fine classification system from 1985 to 2022

Abstract. Land cover change information plays an indispensable role in environmental monitoring, climate change research, agricultural planning, urban development, biodiversity conservation, and natural disaster risk assessment. Recently, the free access of Landsat imagery and improvement of computation capacity especially supported by Google Earth Engine platform provides great chance in time-series land-cover change monitoring. We used the stratified land-cover monitoring strategy and time-series Landsat imagery to develop a novel global 30 m land-cover dynamic product with fine classification system from 1985 to 2022 (GLC_FCS30D). Firstly, we used the multitemporal classification to generate the time-series impervious surfaces, wetlands and tidal flat products. Then, we proposed to combine the continuous change detection algorithm and local adaptive updating model to capture the land-cover changes, and to generate a new global 30 m land-cover dynamic product (impervious surfaces, wetlands and tidal flat types were excluded in this step). Next, after overlapping the three multitemporal classification products and the time-series dynamical land-cover dataset, the novel GLC_FCS30D was developed, which contained 35 fine land-cover types. Lastly, using the global 84526 validation points in 2020, the GLC_FCS30D was validated to show the great performance with an overall accuracy of 80.88%, and had obvious advantages over other global land-cover products in diversity of land-cover types and mapping accuracy.

Advanced utilization of satellite and governmental data for determining the coverage and condition of green areas in Poland: An experimental statistics supporting the Statistics Poland

Statistics Poland utilizes Earth Observation and in-situ data to assess green areas, aiming to derive vital information on natural capital statistics and human well-being. This is essential for informed decision-making and sustainable development. Improving regional well-being statistics is a priority due to Poland's low rankings in environmental well-being indicators. To overcome challenges in obtaining comprehensive data at the commune level, the study introduces a new and innovative system for monitoring green areas. This system employs Sentinel-2 satellite data, combined with Copernicus vegetation and phenology products in order to determine extent and condition of green areas. In addition, the applied land cover product (Dynamic World) and national vector database of topographic features (BDOT10k) contributes to the quality and accuracy of the analyses carried out. The system yields two pivotal indicators: one delineating the proportional coverage of green areas within communes boundaries, and the other elucidating the state and health of these delineated areas. A key highlight of the system is its innovative use of local resources and the Google Earth Engine application to observe green areas at a 10-meter resolution at the commune level, particularly in major cities in Poland. These observations are crucial for the Polish Public Services Monitoring System (SMUP), providing comprehensive local-level evaluation services. The research outcome consists of a comparison between the extent of green areas delineated by public administration at the commune level and the extent of green areas determined using a newly proposed method, which relies on satellite imagery from the Copernicus program. The results indicate variability between these two datasets, depending on different forms of land cover within each administrative unit. The most consistent data is derived from large urban agglomerations in Poland.

Mapping Quaking Aspen Using Seasonal Sentinel-1 and Sentinel-2 Composite Imagery across the Southern Rockies, USA

Quaking aspen is an important deciduous tree species across interior western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (<0.09 ha or 30 m2), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. Using observed annual phenology of aspen across the Southern Rockies and leveraging the frequent temporal resolution of S1 and S2, ecologically relevant seasonal imagery composites were developed. We derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best-performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing products in both accuracy (0.93 average F1-score) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America.

SPATIAL ANALYSIS OF LAND COVER CHANGES IN DEPOK CITY USING GEOGRAPHIC INFORMATION SYSTEMS

Depok City is an area undergoing significant changes in land cover due to rapid urban development. Additionally, population growth is contributing to these land cover changes. These factors exert pressure on land use changes, with implications for land cover. Therefore, it is necessary to conduct a spatial analysis of land cover changes in Depok City. This research employs Geographic Information System (GIS) methods and spatial analysis to examine land cover changes in Depok from 2017 to 2022. The objectives of this study are to identify the land cover conditions in Depok from 2017 to 2022 and analyze the changes in land cover during this period. The data source used is Landsat 8 satellite imagery. These satellite images were interpreted to produce land cover maps for the years 2017 and 2022. Subsequently, these two maps were overlaid to assess changes in land use. The research results revealed seven land cover classes in 2017, with the largest in terms of area being Residential/Built-up Areas (12,383.43 hectares), Green Open Spaces (3,479.66 hectares), Dryland Agriculture (2,218.65 hectares), Services/Industry (885.41 hectares), Paddy Fields (414.59 hectares), Open Land (373.66 hectares), and Water Bodies (239.23 hectares). Spatial analysis indicated a decrease in land cover for Green Open Spaces (238.84 hectares), Dryland Agriculture (122.67 hectares), and Paddy Fields (31.89 hectares). Conversely, an increase in land cover was observed for Residential/Built-up Areas (266.01 hectares), Services/Industry (91.84 hectares), and Open Land (35.55 hectares).

Does settlement land expansion necessarily induce the decrease of cultivated land? Differences in national scale and local counties of China

With the extensive industrialization and urbanization taking place in China during the recent decades, land use throughout the country has experienced profound changes influenced not only by the demand for population growth and living standard improvement but also by the constraints of series of land use policies. However, whether the conflict between the expansion of settlement land (SL) and the loss of cultivated land (CL) have been resolved at the national scale or transferred between the local regions remains unclear. Based on yearly ESA CCI land use and land cover products from 1992 to 2020, the long-term trends of quantity and spatial pattern of SL expansion and CL change in China from national and local views were investigated using trend statistic methods, and finally a comprehensive zoning framework was proposed to recognize the trade-off and synergies relationships between SL expansion and CL change. There are a continuous expansion of SL with global linear trends showing three breakpoints in 2000, 2005, and 2012, and a fluctuation decline of CL presented with four breakpoints in 1997, 2002, 2006, and 2013. Aggregation and dispersion tendencies with linear characteristics of SL expansion and CL change were found with breakpoints in 2001, 2008, 2012, and 2016 and breakpoints in 2001 and 2010, respectively. A spotty spatial pattern of SL was shown spatially coincident with urban agglomerations in China while the planar continuous characteristic was found for CL. Local counties were classified into five tradeoff and synergies zones (TSZs), where general synergies (G-S) and decoupling (D) of SL expansion and CL change were rare cases and the different change in quantity and trend of SL expansion and CL change in local counties was concealed by the national trend. A few scattered counties were belonging to G-S and D TSZs, while most of the counties in the central-east and western China were in General-Tradeoff (G-T) and Superior-Tradeoff (S-T) TSZs. Counties in south and north China with higher percentages of CL were more prevalent in Superior-Synergy (S–S) TSZ. Our findings explicated the complex relationships between SL expansion and CL change of China at the national scale and in local counties, which pointed out the differences of unified land use management activities across scales and could provide insights for future policy-making and management measures of land use to both ensure the national food security and promote regional sustainable development more synchronously.

Forecasting urban futures: Evaluating global land use data sensitivity for regional growth simulation in the Ruhr Metropolitan Area

In recent years, numerous multitemporal global land use and land cover products have been published acting as valuable source for training spatially explicit geosimulation models forecasting urban growth. However, there is a notable gap in research that specifically addresses the sensitivity of models traing with those data sets when it comes to regional modeling purposes. Accordingly, the objectives of this study were to calibrate, validate, and employ global urban input datasets for the regional simulation of urban growth by the year 2030. The SLEUTH urban growth model, focused on the metropolitan area of the Ruhr, Germany, was calibrated using the Global Human Settlement Layer, World Settlement Footprint Evolution, historical OpenStreetMap data, and a Digital Land Cover Model for Germany. The goal was to compare the results in terms of accuracy, certainty, quantity, and allocation, particularly in urban areas susceptible to floods and heat. While all models achieved high accuracy levels concerning quantity and allocation, the extent of new settlements varied from 40.77 km2 to 477.91 km2. The models based on World Settlement Footprint and OpenStreetMap exhibited higher certainty and lower stochasticity. As the simulated urban growth increased, there was a corresponding rise in the likelihood of allocating new settlements in areas affected by natural hazards. While all models presented a similar relative portion of new settlement areas impacted by floods, variations emerged in terms of areas affected by unfavorable thermal conditions. This study underscored the potential use of historical OpenStreetMap data in training cellular automation for geosimulating future settlement growth. Furthermore, it highlighted the applicability of global Earth observation-based urban datasets for regional geosimulation and explored the impacts of diverse input data on the accuracy, certainty, quantity, and allocation performances in simulating future conditions.

Detection of Land Use Changes in Forests Using Satellite Image Classification Based on Deep Learning: A Case Study of Sardasht Forests

Awareness of changes in forest areas has always been one of the most crucial environmental considerations globally. Sardasht forests is located in the northern Zagros region and with an area of around 91,117 hectares constitute for 24% of Iran total forests. They play an important role in water supply, soil preservation, climate regulation and overall economic and social balance in the country. Nevertheless, these forests are currently perceived as degraded due to the primary reason of tree cutting for fuel and livestock feed. In this study, remote sensing data of the study area including Landsat 5 TM satellite images from 2002, Landsat 7 ETM images from 2012, Landsat 8 OLI images 2020 and classification algorithms, maximum likelihood and artificial neural network were utilized. To examine the accuracy of each classification, ground truth points were randomly collected using GPS devices and by implementing control points, statistical parameters of error accuracy including Kappa coefficient and overall accuracy were calculated. The results show that the map generated using the artificial neural network algorithm has an overall accuracy of 98.32% with a Kappa coefficient of 0.9781 while the map produced by the maximum likelihood algorithm has an overall accuracy of 92.45% with a Kappa coefficient of 0.901. As a result, the artificial neural network algorithm demonstrates to be a more suitable method for producing land cover maps compared to the maximum likelihood algorithm.

Comparison and Evaluation of Five Global Land Cover Products on the Tibetan Plateau

The Tibetan Plateau (TP) region contains maximal alpine grassland ecology at the mid-latitudes. This region is also recognized as an ecologically fragile and sensitive area under the effects of global warming. Regional climate modeling and ecosystem research depend on accurate land cover (LC) information. In order to obtain accurate LC information over the TP, the reliability and precision of five moderate/high-resolution LC products (MCD12Q1, C3S-LC, GlobeLand30, GLC_FCS30, and ESA2020 in 2020) were analyzed and evaluated in this study. The different LC products were compared with each other in terms of areal/spatial consistency and assessed with four reference sample datasets (Geo-Wiki, GLCVSS, GOFC-GOLD, and USGS) using the confusion matrix method for accuracy evaluation over the TP. Based on the paired comparison of these five LC datasets, all five LC products show that grass is the major land cover type on the TP, but the range of grass coverage identified by the different products varies noticeably, from 43.35% to 65.49%. The fully consistent spatial regions account for 43.72% of the entire region of the TP, while, in the transition area between grass and bare soil, there is still a large area of medium-to-low consistency. In addition, a comparison of LC datasets using integrated reference datasets shows that the overall accuracies of MCD12Q1, C3S-LC, GlobeLand30, GLC_FCS30, and ESA2020 are 54.29%, 49.32%, 53.03%, 53.73%, and 60.11%, respectively. The producer accuracy of the five products is highest for grass, while glaciers have the most reliable and accurate characteristics among all LC products for users. These findings provide valuable insights for the selection of rational and appropriate LC datasets for studying land-atmosphere interactions and promoting ecological preservation in the TP.

A non‐grain production on cropland spatiotemporal change detection method based on Landsat time‐series data

AbstractGlobal food security is being threatened by the reduction of high‐quality cropland, extreme weather events, and the uncertainty of food supply chains. The globalization of agricultural trade has elevated the diversification of non‐grain production (NGP) on cultivated land to a prominent strategy for poverty alleviation in numerous developing nations. Its rapid expansion has engendered a multitude of deleterious consequences on both food security and ecological stability. NGP in China is becoming very common in the process of rapid urbanization, threatening national food security. To better understand the causal mechanisms and enable governments to balance food security and rural development, it is crucial to have a clear understanding of the spatiotemporal dynamics of NGP using remote sensing. Yet knowledge gaps remain concerning how to use remote sensing to track human‐dominated or ‐induced long‐term cultivated land changes. Our study proposed a method for detecting the spatiotemporal evolution of NGP based on Landsat time‐series data under the Google Earth Engine platform. This approach was proposed by (1) obtaining the union of cultivated lands from multiple landcover products to minimize the cultivated land omission, (2) constructing multi‐index dynamic trend rules for 3 representative types of NGP and obtaining results at the pixel level, while adopting the continuous change detection and classification algorithm to Landsat time series (1986–2022) to determine when the most recent change occurred, (3) minimizing the noise by object‐oriented land use–land cover classification and mode filter approaches, and (4) mapping the spatiotemporal distribution of NGP. The proposed methodology was tested in Jiashan, located in Zhejiang Province (eastern China), where NGP is widespread. We achieved a high overall accuracy of 95.67% for NGP type detection and an overall accuracy of 85.26% for change detection of time. The results indicated a continued increasing pattern of NGP in Jiashan from 1986 to 2022, with the cumulative percentage of NGP increasing from 0.02% to 20.69%. This study highlights the utilization of time‐series data to document essential NGP information for evaluating food security in China and the method is well‐suited for large‐scale mapping due to its automatic manner.

Synergizing google earth engine and earth observations for potential impact of land use/ land cover on air quality

Changes in land use and land cover are imperative drivers of climate change in urbanization. The conversion of land use modifies the physical and thermal characteristics of the land surface and also has an impact on the air quality. This study aims to assess the potential impact of land use and land cover (LULC) on the air quality in Gujarat state, India for 6 years, 2018, 2020, and 2023. Six land-use types, water bodies, forest, agricultural land, built-up, barren land, and scrubland obtained from the Landsat 8 land cover product processed in Google Earth Engine (GEE), where LULC of each category was estimated. The analysis findings indicated that variations in pollution response to LULC change exhibit distinct differences across different regions, influenced by natural factors or human activities like deforestation and urbanization. Over the years 2018–2023, agricultural land seems to consistently decrease in area, but urban areas saw exponential growth. The combined percentage of agricultural land and forest area slightly decreased from 61.08% to 60.7%, while the water spread area increased from 4.07% to 5.13%. The category of bare land decreased from 29.59% to 27.56%, mainly due to urbanization converting bare soil into built-up areas. The Sentinel-5P satellite data was used to estimate atmospheric pollution i.e., carbon mono-oxide (CO), Nitrogen dioxide (NO2), Methane (CH4), Sulfur Dioxide (SO2), and formaldehyde (HCHO). Over the past decade, a significant portion of land use land cover has transitioned from forest to vegetation areas in the western region, while urbanization has rapidly expanded in the eastern and central-western parts.

Comparison and Validation of Multiple Medium- and High-Resolution Land Cover Products in Southwest China

The rapid advancement of remote sensing technology has given rise to numerous global- and regional-scale medium- to high-resolution land cover (LC) datasets, making significant contributions to the exploration of worldwide environmental shifts and the sustainable governance of natural resources. Nonetheless, owing to the inherent uncertainties embedded within remote sensing imagery, LC datasets inevitably exhibit inaccuracies. In this study, a local accuracy assessment of LC datasets in Southwest China was conducted. The datasets utilized in our analysis include ESA WorldCover, CLCD, Esri Land Cover, CRLC, FROM-GLC10, GLC_FCS30, GlobeLand30, and SinoLC-1. This study employed a sampling approach that combines proportional allocation and stratified random sampling (SRS) to gather sample points and compute confusion matrices to validate eight LC products. The local accuracy of the eight LC maps differs significantly from the overall accuracy provided by the original authors in Southwest China. ESA WorldCover and CLCD demonstrate higher local accuracy than other products in Southwest China, with their overall accuracy (OA) values being 87.1% and 85.48%, respectively. Simultaneously, we computed the area for each LC map based on categories, quantifying uncertainty through the reporting of confidence intervals for both accuracy and area parameters. This study aims to validate and compare eight LC datasets and assess precision and area of diverse spatial resolution datasets for mapping and monitoring across Southwest China.

Assessing the impact of anthropogenic activities on land use and land cover changes in the semi-arid and arid regions of Algeria.

Land use and land cover are critical factors that influence the environment and human societies. The dynamics of LULC have been constantly changing over the years, and these changes can be analyzed at different spatial and temporal scales to evaluate their impact on the natural environment. This study employs multitemporal satellite data to investigate the spatial and temporal transformations that occurred in Sidi Bel Abbes province, situated in the northwestern region of Algeria, spanning from the early 1990s to 2020. Notably, this province is marked by semi-arid and arid climates and hosts a wide range of areas susceptible to gravitational hazards, especially concerning alterations in land use and forest fires. The interactive supervised classification tool utilized multiple machine learning algorithms including Random Forest, Support Vector Machine, Classification and Regression Tree, and Naïve Bayes to produce land cover maps with six main classes: forest, shrub, agricultural, pasture, water, and built-up. The findings showed that the LULC in the research area is undergoing continuous change, particularly in the forest and agricultural lands. The forest area has decreased significantly from 10.80% in 1990 to 5.25% in 2020, mainly due to repeated fires. Agricultural land has also undergone fluctuations, with a decrease between 1990 and 2000, followed by a fast increase and near stabilization in 2020. At the same time, pasture lands and built-up areas grew steadily, increasing by 11% and 13% respectively. This research highlights the significant impact of anthropogenic activities on LULC changes in the study area and can provide valuable insights for promoting sustainable land use policies.

Feature Optimization-Based Machine Learning Approach for Czech Land Cover Classification Using Sentinel-2 Images

The Czech Republic is one of the countries along the Belt and Road Initiative, and classifying land cover in the Czech Republic helps to understand the distribution of its forest resources, laying the foundation for forestry cooperation between China and the Czech Republic. This study aims to develop a practical approach for land cover classification in the Czech Republic, with the goal of efficiently acquiring spatial distribution information regarding its forest resources. This approach is based on multi-level feature extraction and selection, integrated with advanced machine learning or deep learning models. To accomplish this goal, the study concentrated on two typical experimental regions in the Czech Republic and conducted a series of classification experiments, using Sentinel-2 and DEM data in 2018 as the main data sources. Initially, this study extracted various features, including spectral, vegetation, and terrain features, from the study area, then assessed and selected key features based on their importance. Additionally, this study also explored multi-level spatial contextual features to improve classification performance. The extracted features include texture and morphological features, as well as deep semantic information learned by utilizing a deep learning model, 3D CNN. Finally, an AdaBoost ensemble learning model with the random forest as the base classifier is designed to produce land cover classification maps, thus obtaining the spatial distribution of forest resources. The experimental results demonstrate that feature optimization significantly enhances the extraction of high-quality features of surface objects, thereby improving classification performance. Specifically, morphological and texture features can effectively enhance the discriminability between different features of surface objects, thereby improving classification accuracy. Utilizing deep learning networks enables more efficient extraction of deep feature information, further enhancing classification accuracy. Moreover, employing an ensemble learning model effectively boosts the accuracy of the original classification results from different individual classifiers. Ultimately, the classification accuracy of the two experimental areas reaches 92.84% and 93.83%, respectively. The user accuracies for forests are 92.24% and 93.14%, while the producer accuracies are 97.71% and 97.02%. This study applies the proposed approach for nationwide classification in the Czech Republic, resulting in an overall classification accuracy of 90.98%, with forest user accuracy at 91.97% and producer accuracy at 96.2%. The results in this study demonstrate the feasibility of combining feature optimization with the 3D Convolutional Neural Network (3DCNN) model for land cover classification. This study can serve as a reference for research methods in deep learning for land cover classification, utilizing optimized features.

Mapping the Spatiotemporal Dynamics of Cropland Abandonment and Recultivation across the Yangtze River Basin

Whether China can achieve the United Nations’ Sustainable Development Goals (SDGs) largely depends on the ability of main food-producing areas to cope with multiple land use change challenges. Despite the fact that the Yangtze River basin is one of the key regions for China’s food security, the spatiotemporal dynamics of cropland abandonment and recultivation remain largely unexplored in this region. The present study assesses the evolution of the agricultural system within the Yangtze River basin between 2000 and 2020 by mapping cropland abandonment and recultivation using MODIS time series and multiple land cover products. The results highlight a widespread cropland abandonment process (i.e., 10.5% of the total study area between 2000 and 2020), predominantly in Western Sichuan, Eastern Yunnan, and Central Jiangxi. Although 70% of abandoned cropland is situated in areas with slopes less than 5°, the highest rates of abandonment are in mountainous regions. However, by 2020, 74% of this abandoned cropland had been recultivated at least once, whereas half of the abandoned croplands got recultivated within three years of their initial abandonment. Hence, as this is one of the first studies that unravels the complex interaction between cropland abandonment and recultivation in a spatiotemporal explicit context, it offers (i) scientists a novel methodological framework to assess agricultural land use issues across large geographical entities, and (ii) policy-makers new insights to support the sustainable transition of the agricultural sector.

Time-first approach for land cover mapping using big Earth observation data time-series in a data cube – a case study from the Lake Geneva region (Switzerland)

ABSTRACT Accurate, consistent, and high-resolution Land Use & Cover (LUC) information is fundamental for effectively monitoring landscape dynamics and better apprehending drivers, pressures, state, and impacts on land systems. Nevertheless, the availability of such national products with high thematic accuracy is still limited and consequently researchers and policymakers are constrained to work with data that do not necessarily reflect on-the-ground realities impending to correctly capture details of landscape features as well as limiting the identification and quantification of drivers and rate of change. Hereafter, we took advantage of the Switzerland’s official LUC statistical sampling survey and dense time-series of Sentinel-2 data, combining them with Machine and Deep Learning methods to produce an accurate and high spatial resolution land cover map over the Lake Geneva region. Findings suggest that time-first approach is a valuable alternative to space-first approaches, accounting for the intra-annual variability of classes, hence improving classification performances. Results demonstrate that Deep Learning methods outperform more traditional Machine Learning ones such as Random Forest, providing more accurate predictions with lower uncertainty. The produced land cover map has a high accuracy, an improved spatial resolution, while at the same time preserving the statistical significance (i.e. class proportion) of the official national dataset. This work paves the way towards the objective to produce a yearly high resolution land cover map of Switzerland and potentially implement a continuous land change monitoring capability. However further work is required to properly address challenges such as the need for increased temporal resolution for LUC information or the quality of training samples.

Decline in Planting Areas of Double-Season Rice by Half in Southern China over the Last Two Decades

Accurately tracking the changes in rice cropping intensity is a critical requirement for policymakers to formulate reasonable land-use policies. Southern China is a traditional region for rice multi-cropping, yet less is known about its spatial–temporal changes under the background of rapid urbanization in recent decades. Based on images from Landsat and MODIS and multiple land cover products, the gap-filling and Savitzky–Golay filter method (GF-SG), the enhanced pixel-based phenological features composite approach (Eppf-CM), random forest (RF), and the difference in NDVI approach (DNDVI) were combined to map the rice cropping pattern with a spatial resolution of 30 × 30 m over Southern China in 2000 and 2020 through Google Earth Engine (GEE). Subsequently, the spatial–temporal changes in rice cropping intensity and their driving factors were examined by Getis-Ord Gi* and geographical detector. The results showed that the produced rice cropping pattern maps exhibited high accuracy, with kappa coefficients and overall accuracies exceeding 0.81 and 90%, respectively. Over the past two decades, the planting areas of double-season rice in Southern China decreased by 54.49%, and a reduction was observed across eight provinces, while only half of the provinces exhibited an increase in the planting areas of single-season rice. Compared to the year 2000, the planting area of the conversion from double- to single-season rice cropping systems in 2020 was 2.71 times larger than that of the conversion from single- to double-season rice cropping systems. The hotspots of the change in rice cropping intensity were mainly located in the central part of Southern China (excluding the Poyang Lake Plain). The decline in the rural labor force, coupled with ≥10 °C accumulated temperature and topographical factors, plays a crucial role in the decreased intensity of rice cropping. Our findings can be beneficial for realizing regional agricultural sustainability and food security.

A Framework for Fine-Grained Land-Cover Classification Using 10 m Sentinel-2 Images

Land-cover mapping plays a crucial role in resource detection, ecological environmental protection, and sustainable development planning. The existing large-scale land-cover products with coarse spatial resolution have a wide range of categories, but they suffer from low mapping accuracy. Conversely, land-cover products with fine spatial resolution tend to lack diversity in the types of land cover they encompass. Currently, there is a lack of large-scale land-cover products simultaneously possessing fine-grained classifications and high accuracy. Therefore, we propose a mapping framework for fine-grained land-cover classification. Firstly, we propose an iterative method for developing fine-grained classification systems, establishing a classification system suitable for Sentinel-2 data based on the target area. This system comprises 23 fine-grained land-cover types and achieves the most stable mapping results. Secondly, to address the challenges in large-scale scenes, such as varying scales of target features, imbalanced sample quantities, and the weak connectivity of slender features, we propose an improved network based on Swin-UNet. This network incorporates a pyramid pooling module and a weighted combination loss function based on class balance. Additionally, we independently trained models for roads and water. Guided by the natural spatial relationships, we used a voting algorithm to integrate predictions from these independent models with the full classification model. Based on this framework, we created the 2017 Beijing–Tianjin–Hebei regional fine-grained land-cover product JJJLC-10. Through validation using 4254 sample datasets, the results indicate that JJJLC-10 achieves an overall accuracy of 80.3% in the I-level validation system (covering seven land-cover types) and 72.2% in the II-level validation system (covering 23 land-cover types), with kappa coefficients of 0.7602 and 0.706, respectively. In comparison with widely used land-cover products, JJJLC-10 excels in accurately depicting the spatial distribution of various land-cover types and exhibits significant advantages in terms of classification quantity and accuracy.

Deciphering the evolving trajectories of China's megaregions from 1992 to 2020: A novel morphological approach based on global land cover products

The monitoring of megaregion boundaries (MBs) is of vital importance for optimizing land use decision-making. However, the morphological structure of megaregions is currently insufficiently identified due to the nontransparent proprietary or inherent deficiency data sources. Thus, this study utilized land cover products integrated with morphological approaches to delineate the evolving trajectories of China's megaregions from 1992 to 2020. Firstly, core areas of megaregions and periphery affected areas were extracted from urban land density maps based on the gravity model and landscape metrics. Secondly, contiguous urban-rural fringes were improved based on the morphological operations and the rank-size distribution. Thirdly, urban land was automatically allocated to megaregions, considering planning policies. Furthermore, three indicators (gross domestic product, population, and land use density) are considered to validate our results, and our extracted MBs show a better understanding than the administrative divisions. The dynamic expansion patterns of twenty identified MBs were captured. As urbanization continues, the boundaries between megaregions become increasingly blurred and eventually merged into large-scale continuous megaregions that extend far beyond administrative divisions. Our study provides valuable insights for megaregion planning, including the effective urban management policies, the role of core cities in each megaregion in terms of radiation and capability.

Extracting Shrubland in Deserts from Medium-Resolution Remote-Sensing Data at Large Scale

Shrubs are important ecological barriers in desert regions and an important component of global carbon estimation. However, the shrubland in deserts has been hardly presented, although many high-quality land cover datasets with a 10 m scale based on remote-sensing data have been publicly released products. Therefore, the underestimation of carbon storage is inevitable with the absence of desert shrublands. The existing land-cover datasets have been analyzed and compared, and it has been found that the reason for missing the shrubland in deserts is mainly indued by the absence of shrubland samples, which are easy to neglect and difficult to retrieve. In this study, we developed a semi-automatic method to extract shrubland samples in deserts as the updated input for the machine-learning method. Firstly, the initial samples of desert shrublands were identified from the very high spatial-resolution (0.3~0.5 m) imagery on GEE, and the maximum NDVI from Sentinel-2 was used for double-checking. Secondly, a feature-based method was used to learn the feature from the initial samples and a similarity-based searching method was employed to automatically expand the samples. Finally, the expanded samples and their corresponding time-series satellite images were inputted into different machine-learning methods at a large region (1.63 × 106 km2) for extracting the shrubland in the desert. It was found that different combinations of feature variables and time-series combinations have different impacts on the overall accuracy (OA) of the classification results, as well as the performance of identifying and classifying the different land-cover types. Compared to the existing global-scale land-cover products, the proposed method can better identify the shrubland in deserts and show better overall accuracy.

Fine-resolution mapping and assessment of artificial surfaces in the northern hemisphere permafrost environments

ABSTRACT Permafrost degradation has strong and long-lasting effects on anthropogenic land-use activities, contradicting the goal of sustainable development in polar and high-elevation regions. The artificial surface (AS) plays a central role in determining human-environment relationships in permafrost environments. Despite recent progress in monitoring land surfaces, attempts to map permafrost AS with satellite remote sensing have been limited. In this study, we propose an operational framework for fine-resolution mapping and assessment of permafrost AS across the entire Northern Hemisphere landmass. The proposed framework was designed to take advantage of prior knowledge obtained from existing global-scale land-cover products. As a result, a 10 m resolution permafrost AS map for 2016–2017 was created using a locally adaptive classification strategy. We found that the created map exhibited an overall accuracy of 91.7 ± 2.1% with minimum accuracies > 70%. We estimated that the total area of permafrost AS in the Northern Hemisphere was approximately 9,000 km2, most notably in the Russian Arctic. Future projections indicate that there will be over one-seventh of the permafrost AS area at high geohazard risk by the end of the twenty-first century. Our study provides new perspectives on the ‘permafrost-human-climate’ nexus, which can advance our understanding of the terrestrial system.