Regional Mapping of Essential Urban Land Use Categories in China: A Segmentation-Based Approach

Tu, Ying; Чэн, Бин; Zhang, Tao; Xu, Bing

doi:10.3390/rs12071058

Cited by 35 publications

(43 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, it can be found that the POI features had the greatest contributions in the EULUC-Nanjing mapping (Table 7 and Figure 9). However, Tu et al [26] pointed out that compared with POI data, the features obtained from Sentinel-2 imagery were the main factors affecting the classification performance. This may be because this study used the regenerated POI data by overcoming the problem of unbalanced distribution and extracted the POI spatial features.…”

Section: Contribution Of Different Featuresmentioning

confidence: 99%

“…The classification accuracy for 27 validation cities ranges from 40.4% to 82.9% for Level I, and from 34% to 80% for Level II. However, the relatively lower accuracy of EULUC-China may not sufficiently meet the growing demands for urban planning, environmental monitoring, and other aspects at local to regional scopes [26], which can be attributed to the following aspects. Firstly, the buffer thresholds of roads for generating urban parcels were simply divided into major and minor categories without details assigned.…”

Section: Introductionmentioning

confidence: 99%

“…The figure in brackets is the number of features. Mean and standard deviation of blue, green, red, near-infrared, short-wave-infrared bands (band11,12), NDVI, NDBI, and NDWI.Textural features(26): Entropy, contrast and correlation of blue, green, red, and near-infrared bands. Entropy of NDVI.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Mapping Essential Urban Land Use Categories in Nanjing by Integrating Multi-Source Big Data

et al. 2020

View full text Add to dashboard Cite

High-spatial-resolution (HSR) urban land use maps are very important for urban planning, traffic management, and environmental monitoring. The rapid urbanization in China has led to dramatic urban land use changes, however, so far, there are no such HSR urban land use maps based on unified classification frameworks. To fill this gap, the mapping of 2018 essential urban land use categories in China (EULUC-China) was jointly accomplished by a group of universities and research institutes. However, the relatively lower classification accuracy may not sufficiently meet the application demands for specific cities. Addressing these challenges, this study took Nanjing city as the case study to further improve the mapping practice of essential urban land use categories, by refining the generation of urban parcels, resolving the problem of unbalanced distribution of point of interest (POI) data, integrating the spatial dependency of POI data, and evaluating the size of training samples on the classification accuracy. The results revealed that (1) the POI features played the most important roles in classification performance, especially in identifying administrative, medical, sport, and cultural land use categories, (2) compared with the EULUC-China, the overall accuracy for Level I and Level II in EULUC-Nanjing has increased by 11.1% and 5%, to 86.1% and 80% respectively, and (3) the classification accuracy of Level I and Level II would be stable when the number of training samples was up to 350. The methods and findings in this study are expected to better inform the regional to continental mappings of urban land uses.

show abstract

Section: Contribution Of Different Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mapping Essential Urban Land Use Categories in Nanjing by Integrating Multi-Source Big Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…With the development of big data, many new data sources were introduced into the land-use classification field. Mobile phone record data, floating car data, social media data, and other big data have shown their importance in land-use classification [3,[12][13][14][15][16][17][18]. Although the inclusion of socioeconomic data can improve the accuracy of land-use classification, studies combining image data and multiple-source Internet open data to classify urban land use are relatively rare, and few studies have been conducted in large cities.…”

Section: Introductionmentioning

confidence: 99%

Mapping Essential Urban Land Use Categories in Beijing with a Fast Area of Interest (AOI)-Based Method

Hu²,

Gong

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Due to the spatially mixed vegetation structures, seasonal variations of vegetation, and the temporal inconsistency between Landsat and Sentinel data, the classification accuracy for these vegetation types is relatively low [28]; (2) Usage of limited features. The predictors are mainly depending on Sentinel-2 based features such as spectral and derived remote sensing indices, without considering other information that is highly correlated with land covers such as nighttime light (NTL) and incident microwave radiation [29,30]; (3) Uncertainty of models. A unified model is used to classify global land cover, which may lead to biased performance for localized experiments.…”

Section: Introductionmentioning

confidence: 99%

Improved Mapping Results of 10 m Resolution Land Cover Classification in Guangdong, China Using Multisource Remote Sensing Data With Google Earth Engine

Lang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Land cover information depicting the complex interactions between human activities and surface change is critically essential for nature conservation, social management, and sustainable development. Recent advances have shown great potentials of remote sensing data in generating high-resolution land cover maps, but it remains unclear how different models, data sources, and inclusive features affect the classification results, which hinders its applications in regional studies requiring more accurate land cover data. Informing these issues, here we developed a robust framework to improve the mapping results of 10 m resolution land cover classification in Guangdong Province, China using thousands of manually collected samples, multisource remote sensing data (Sentinel-1, Sentinel-2, and Luojia-1), machine learning algorithms, and a free cloud-based platform of Google Earth Engine. Results showed that an overall accuracy of 86.12% and a Kappa coefficient of 0.84 could be achieved for land cover classification in Guangdong for 2019. We found that Random Forest (RF) models achieved better performance than classification and regression trees (CART), minimum distance (MD), and support vector machine (SVM) models. We also found that features derived from Sentinel-1 data and Sentinel-2 spectral indices greatly contributed to the classification process, while the feature of Luojia-1 data was not as much important as other configurations. A comparison between our results and several existing land cover products in terms of classification accuracy and visual interpretation further validated the effectiveness and robustness of the proposed framework. Our experiments and findings not only systematically elucidate the role of classification methods and data sources in deriving more accurate and reliable land cover maps, but also provide certain guidelines for future land cover mapping from regional to global scales.

show abstract

Regional Mapping of Essential Urban Land Use Categories in China: A Segmentation-Based Approach

Cited by 35 publications

References 22 publications

Mapping Essential Urban Land Use Categories in Nanjing by Integrating Multi-Source Big Data

Mapping Essential Urban Land Use Categories in Nanjing by Integrating Multi-Source Big Data

Mapping Essential Urban Land Use Categories in Beijing with a Fast Area of Interest (AOI)-Based Method

Improved Mapping Results of 10 m Resolution Land Cover Classification in Guangdong, China Using Multisource Remote Sensing Data With Google Earth Engine

Contact Info

Product

Resources

About