High-resolution urban land use maps have important applications in urban planning and management, but the availability of these maps is low in countries such as China. To address this issue, we have ...developed a protocol to identify urban land use functions over large areas using satellite images and open social data. We first derived parcels from road networks contained in Open Street Map (OSM) and used the parcels as the basic mapping unit. We then used 10 features derived from Points of Interest (POI) data and two indices obtained from Landsat 8 Operational Land Imager (OLI) images to classify parcels into eight Level I classes and sixteen Level II classes of land use. Similarity measures and threshold methods were used to identify land use types in the classification process. This protocol was tested in Beijing, China. The results showed that the generated land use map had an overall accuracy of 81.04% and 69.89% for Level I and Level II classes, respectively. The map revealed significantly more details of the spatial pattern of land uses in Beijing than the land use map released by the government.
Urban boundaries, an essential property of cities, are widely used in many urban studies. However, extracting urban boundaries from satellite images is still a great challenge, especially at a global ...scale and a fine resolution. In this study, we developed an automatic delineation framework to generate a multi-temporal dataset of global urban boundaries (GUB) using 30 m global artificial impervious area (GAIA) data. First, we delineated an initial urban boundary by filling inner non-urban areas of each city. A kernel density estimation approach and cellular-automata based urban growth modeling were jointly used in this step. Second, we improved the initial urban boundaries around urban fringe areas, using a morphological approach by dilating and eroding the derived urban extent. We implemented this delineation on the Google Earth Engine platform and generated a 30 m resolution global urban boundary dataset in seven representative years (i.e. 1990, 1995, 2000, 2005, 2010, 2015, and 2018). Our extracted urban boundaries show a good agreement with results derived from nighttime light data and human interpretation, and they can well delineate the urban extent of cities when compared with high-resolution Google Earth images. The total area of 65 582 GUBs, each of which exceeds 1 km2, is 809 664 km2 in 2018. The impervious surface areas account for approximately 60% of the total. From 1990 to 2018, the proportion of impervious areas in delineated boundaries increased from 53% to 60%, suggesting a compact urban growth over the past decades. We found that the United States has the highest per capita urban area (i.e. more than 900 m2) among the top 10 most urbanized nations in 2018. This dataset provides a physical boundary of urban areas that can be used to study the impact of urbanization on food security, biodiversity, climate change, and urban health. The GUB dataset can be accessed from http://data.ess.tsinghua.edu.cn.
Taking the “One Million-Mu (666 km
2
)” Plain Afforestation (Phase I) Project (Phase I afforestation) in Beijing city as an example, we monitored the growth status of planted forest using long-term ...remote sensing images, and evaluated the impacts of afforestation on land use change and vegetation growth. We found there is a large space for improvement regarding the ecological benefits of the project. Moreover, we found forest patches with decreasing greenness after the afforestation were mainly converted from farmland with high greenness and low heterogeneity in terms of the normalized difference vegetation index (NDVI). This implies that those farmland patches are inappropriate for afforestation. According to the results from Phase I afforestation and the impact of urbanization on green space, we constructed a series of spatial variables and generated a suitability map for the next “New Round of One Million-Mu (666 km
2
) Afforestation project” (Phase II afforestation). We then modeled the spatial distribution of Phase II afforestation based on the derived suitability map. This study is crucial for the scientific evaluation of afforestation projects for space planning (e.g., urban green space planning). The evaluation and modeling framework built in this study can be used to support the decision making and policy implementation of afforestation projects in China.
Light pollution, a phenomenon in which artificial nighttime light (NTL) changes the form of brightness and darkness in natural areas such as protected areas (PAs), has become a global concern due to ...its threat to global biodiversity. With ongoing global urbanization and climate change, the light pollution status in global PAs deserves attention for mitigation and adaptation. In this study, we developed a framework to evaluate the light pollution status in global PAs, using the global NTL time series data. First, we classified global PAs (30,624) into three pollution categories: non-polluted (5974), continuously polluted (8141), and discontinuously polluted (16,509), according to the time of occurrence of lit pixels in/around PAs from 1992 to 2018. Then, we explored the NTL intensity (e.g., digital numbers) and its trend in those polluted PAs and identified those hotspots of PAs at the global scale with consideration of global urbanization. Our study shows that global light pollution is mainly distributed within the range of 30°N and 60°N, including Europe, north America, and East Asia. Although the temporal trend of NTL intensity in global PAs is increasing, Japan and the United States of America (USA) have opposite trends due to the implementation of well-planned ecological conservation policies and declining population growth. For most polluted PAs, the lit pixels are close to their boundaries (i.e., less than 10 km), and the NTL in/around these lit areas has become stronger over the past decades. The identified hotspots of PAs (e.g., Europe, the USA, and East Asia) help support decisions on global biodiversity conservation, particularly with global urbanization and climate change.
Urban land use mapping is critical to understanding human activities in space. The first national mapping result of essential urban land use categories of China (EULUC-China) was released in 2019. ...However, the overall accuracies in some of the plain cities such as Beijing, Chengdu, and Zhengzhou were lower than 50% because many parcel-based mapping units are large with mixed land uses. To address this shortcoming, we proposed an area of interest (AOI)-based mapping approach, choosing Beijing as our study area. The mapping process includes two major steps. First, grids with different sizes (i.e., 300 m, 200 m, and 100 m) were derived from original land parcels to obtain classification units with a suitable size. Then, features within these grids were extracted from Sentinel-2 spectral data, point of interest (POI), and Tencent Easygo crowdedness data. These features were classified using a random forest (RF) classifier with AOI data, resulting in a 10-category map of EULUC. Second, we superimposed the AOIs layer on classified units to do some rectification and offer more details at the building scale. The overall accuracy of the AOI layer reached 98%, and the overall accuracy of the mapping results reached 77%. This study provides a fast method for accurate geographic sample collection, which substantially reduces the amount of fieldwork for sample collection and improves the classification accuracy compared to previous EULUC mapping. The detailed urban land use map could offer more support for urban planning and environmental policymaking.
We report the world's first all-season training and validation sample sets for global land cover classification with Landsat-8 data. Prior to this, such samples were only available at a single date ...primarily from the growing season. It is unknown how much limitation such a single-date sample has to mapping global land cover in other seasons of the year. To answer this question, we selected available Landsat-8 images from four seasons and collected training and validation samples from them. We compared the performances of training samples in different seasons using Random Forest algorithm. We found that the use of training samples from any individual season would result in the best overall classification accuracy when validated by samples in the same season. The global overall accuracy from combined best seasonal results was 67.2% when classifying the 11 Level-1 classes in the Finer Resolution Observation and Monitoring of Global Land Cover (FROM-GLC) classification system. The use of training samples from all seasons (named all-season training sample set hereafter) produced an overall accuracy of 67.0%. We also tested classification within 10° latitude 60° longitude zones using all-season training subsample within each zone and obtained an overall accuracy of 70.2%. This indicates that properly grouped subsamples in space can help improve classification accuracies. All the results in this study seem to suggest that it is possible to use an all-season training sample set to reach global optimality with universal applicability in classifying images acquired at any time of a year for global land cover mapping.
Timely and accurate wetland information is necessary for wetland resource management. Recent advances in machine learning and remote sensing have facilitated cost-effective monitoring of wetlands. ...However, reliable methods for fine-grained and rapid wetland mapping are still lacking. To address the issue, a wetland sample set with 20 categories for China was collected based on a sampling strategy that combines automatic sample generation and visual interpretation. Simultaneously, a novel multi-stage method for fine-grained wetland classification was proposed, which integrates pixel-based and object-based strategies using ensemble learning algorithms and multi-source remote sensing data. First, a pixel-based ensemble learning algorithm was implemented to classify five rough wetland categories and six non-wetland categories. Second, an object-based ensemble learning approach was designed to separate the water cover in the pixel-based classification results into eight detailed categories. Third, the merged pixel-based and object-based classification results were refined with knowledge-based post-processing procedures to identify 14 fine-grained wetland categories. Results using the Pixel Information Expert Engine (PIE-Engine) cloud platform proved the effectiveness of the proposed wetland classification method. The overall accuracy, kappa, and weighted F1 reached 87.39%, 82.80%, and 86.02%, respectively. The adopted ensemble learning algorithm yielded better performance than classifiers such as CatBoost, random forest, and XGBoost. The incorporation of spectral, texture, shape, topographic, and geographic features from multi-source data contributed to differentiating wetland categories. According to the relative contribution, spectral indexes (NDVI and NDWI), texture features (sum average and contrast), and topographic features (slope and elevation) were identified as important leading predictors for the first-stage pixel-based classification. Shape features (shape index and compactness) and auxiliary features (geographic location) were crucial predictors for the second-stage object-based classification. Compared with other products, our 10-m wetland mapping results for national wetland reserves were rich in detail and fine in categories. Overall, the constructed sample set and developed classification method show promise in laying a foundation for large-scale wetland mapping. The derived wetland maps can provide support for wetland protection and restoration.
Cellular automata (CA)-based models have been extensively used in urban expansion modeling because of their simplicity, flexibility and intuitiveness. Previous studies on CA-based urban growth ...modeling have mainly focused on the process of spatial allocation of increased urban lands; however, the temporal contexts during the simulation have not been properly explored. In this study, we examined the influence of temporal contexts of initial seeds (i.e. urban extent maps), transition rules, and urban demands (i.e. urban areas) on the CA-based urban growth modeling in Beijing, China, over a long period of 1984-2013. Comparison of the annual model outputs with the time series data of annual urban extent maps from satellite observations revealed that the overall accuracy of urban growth modeling decreased by approximately 12%, with an increase in iterations from 1984-2013. By contrast, the value of the figure of merit (FoM) increased to 26.57%. The continuous change of FoM during the modeling suggests a "spin-up" effect, a rapid increase in FoM at the beginning of modeling, of CA-based urban growth models, and this effect is primarily attributed to the neighborhood component in CA. The effect of temporal contexts reflected by components of initial seeds and urban demands in CA-based urban growth models have considerable impacts on the model performance, i.e. the FoM increased by 7% when using actual urban demands during each iteration instead of the commonly used linear growth during the modeling period. Hence, we suggest that more efforts regarding the temporal contexts in CA-based modeling are required, to better understand error propagation and uncertainty assessment.
Timely cropland information is crucial for ensuring food security and promoting sustainable development. Traditional field survey methods are time-consuming and costly, making it difficult to support ...rapid monitoring of large-scale cropland changes. Furthermore, most existing studies focus on cropland evaluation from a single aspect such as quantity or quality, and thus cannot comprehensively reveal spatiotemporal characteristics of cropland. In this study, a method for evaluating the quantity and quality of cropland using multi-source remote sensing-derived data was proposed and effectively applied in the black soil region in Northeast China. Evaluation results showed that the area of cropland increased significantly in the study area between 2010 and 2018, and the proportion of cropland increased by 1.17%. Simultaneously, cropland patches became larger and landscape connectivity improved. Most of the gained cropland was concentrated in the northeast and west, resulting in a shift in the gravity center of cropland to the northeast direction. Among land converted into cropland, unused land, grassland, and forest were the main sources, accounting for 36.38%, 31.47%, and 16.94% respectively. The quality of cropland in the study area generally improved. The proportion of low-quality cropland decreased by 7.17%, while the proportions of high-quality and medium-quality cropland increased by 5.65% and 5.17%, respectively. Specifically, the quality of cropland improved strongly in the east, improved slightly in the southwest, and declined in the north. Production capacity and soil fertility were key factors impacting cropland quality with obstacle degrees of 36.22% and 15.64%, respectively. Overall, the obtained results were helpful for a comprehensive understanding of spatiotemporal changes in cropland and driving factors and can provide guidance for cropland protection and management. The proposed method demonstrated promising reliability and application potential, which can provide a reference for other cropland evaluation studies.
Artificial impervious areas are predominant indicators of human settlements. Timely, accurate, and frequent information on artificial impervious areas is critical to understanding the process of ...urbanization and land use/cover change, as well as of their impacts on the environment and biodiversity. Despite their importance, there still lack annual maps of high-resolution Global Artificial Impervious Areas (GAIA) with longer than 30-year records, due to the high demand of high performance computation and the lack of effective mapping algorithms. In this paper, we mapped annual GAIA from 1985 to 2018 using the full archive of 30-m resolution Landsat images on the Google Earth Engine platform. With ancillary datasets, including the nighttime light data and the Sentinel-1 Synthetic Aperture Radar data, we improved the performance of our previously developed algorithm in arid areas. We evaluated the GAIA data for 1985, 1990, 1995, 2000, 2005, 2010, and 2015, and the mean overall accuracy is higher than 90%. A cross-product comparison indicates the GAIA data are the only dataset spanning over 30 years. The temporal trend in GAIA agrees well with other datasets at the local, regional, and global scales. Our results indicate that the GAIA reached 797,076 km2 in 2018, which is 1.5 times more than that in 1990. China and the United States (US) rank among the top two in artificial impervious area, accounting for approximately 50% of the world's total in 2018. The artificial impervious area of China surpassed that of the US in 2015. By 2018, the remaining eight among the top ten countries are India, Russia, Brazil, France, Italy, Germany, Japan, and Canada. The GAIA dataset can be freely downloaded from http://data.ess.tsinghua.edu.cn.
•We improved the performance of “Exclusion/Inclusion” approach in arid regions.•We mapped global artificial impervious areas (GAIA) with Google Earth Engine.•The mean overall accuracy over multiple years is higher than 90%.•GAIA reached 797,076 km2 by 2018, more than 2.5 times that of 1990.•The top five countries are China, US, India, Russia, and Brazil.