Regional Accuracy Assessment of 30-Meter GLC_FCS30, GlobeLand30, and CLCD Products: A Case Study in Xinjiang Area
<p>Study area and the land cover type along with the corresponding examples of their appearance on Google Earth: (source: Google Earth).</p> "> Figure 2
<p>The 30-m global land cover products in harmonized classification systems: (<b>a</b>) remote sensing image of Xinjiang, (<b>b</b>) GLC_FCS30, (<b>c</b>) CLCD, and (<b>d</b>) GlobeLand30.</p> "> Figure 3
<p>The Kӧppen-Geiger climate classification spatial distribution data for the world (<b>a</b>) and Xinjiang (<b>b</b>).</p> "> Figure 4
<p>The quantities and spatial distributions of (<b>a</b>) SRS_Val and (<b>b</b>) GLV_2015, and (<b>c</b>) the number of samples corresponding to each class after LC classification system adjustment. Note: each number following the class represents the sample quantity for that category.</p> "> Figure 5
<p>Flowchart for constructing the HDLV-XJ.</p> "> Figure 6
<p>(<b>a</b>) HDGGS grids and (<b>b</b>) the spatial distribution of validation samples in HDLV-XJ.</p> "> Figure 7
<p>Misclassification errors of (<b>a</b>,<b>b</b>) wetland and (<b>c</b>,<b>d</b>) shrubland.</p> "> Figure 8
<p>Examples of LC types with high consistency.</p> "> Figure 9
<p>(<b>a</b>) The Shannon diversity index (<span class="html-italic">SHDI</span>) and (<b>b</b>) sample proportions of different landscape heterogeneity levels. The calculated <span class="html-italic">SHDI</span> map was classified into different layers at intervals of 0.2.</p> "> Figure 10
<p>(<b>a</b>–<b>c</b>) The relationship between landscape heterogeneity and overall accuracy for LC products and (<b>d</b>–<b>k</b>) the comparison of accuracy among three products in heterogeneous regions.</p> "> Figure 11
<p>The relationship between area ratio and accuracy of LC types.</p> ">
Abstract
:1. Introduction
2. Study Area and Data
2.1. Study Area
2.2. The 30-Meter Global Land Cover Products
2.3. Climate Zone and Population Datasets
2.4. The Existing Land Cover Validation Dataset
3. Methods
3.1. Harmonization of the Land Cover Classification Systems
3.2. Construction of the Land Cover Validation Dataset in Xinjiang
3.2.1. The Equal-Area Stratified Random Sampling Method Based on Multiple Indicator Constraints
3.2.2. Labeling HDLV-XJ Based on Visual Interpretation Method
3.3. Accuracy and Consistency Assessment for Land Cover Products
3.3.1. Accuracy Assessment
3.3.2. Consistency Analysis
4. Results
4.1. The High-Density Land Cover Validation Dataset for Xinjiang
4.2. Accuracy Assessment of GLC_FCS30, GlobeLand30, and CLCD
4.3. Consistency Analysis for Global Land Cover Products
5. Discussion
5.1. The Advantages of the HDLV-XJ Dataset
5.2. Analysis of the Relationship between Different Environment Conditions and the Performance of Land Cover Products
5.3. Limitations
6. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Zhang, X.; Liu, L.; Chen, X.; Gao, Y.; Xie, S.; Mi, J. GLC_FCS30: Global land-cover product with fine classification system at 30 m using time-series Landsat imagery. Earth Syst. Sci. Data 2021, 13, 2753–2776. [Google Scholar] [CrossRef]
- Chen, X.; Liu, L.; Zhang, X.; Li, J.; Wang, S.; Gao, Y.; Mi, J. Long-term water clarity patterns of lakes across China using Landsat series imagery from 1985 to 2020. Hydrol. Earth Syst. Sci. 2022, 26, 3517–3536. [Google Scholar] [CrossRef]
- Chen, J.; Chen, J.; Liao, A.; Cao, X.; Chen, L.; Chen, X.; He, C.; Han, G.; Peng, S.; Lu, M. Global land cover mapping at 30 m resolution: A POK-based operational approach. ISPRS J. Photogramm. Remote Sens. 2015, 103, 7–27. [Google Scholar] [CrossRef]
- Giri, C.; Pengra, B.; Long, J.; Loveland, T.R. Next generation of global land cover characterization, mapping, and monitoring. Int. J. Appl. Earth Obs. Geoinf. 2013, 25, 30–37. [Google Scholar] [CrossRef]
- Yang, J.; Huang, X. The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019. Earth Syst. Sci. Data 2021, 13, 3907–3925. [Google Scholar] [CrossRef]
- Gong, P.; Wang, J.; Yu, L.; Zhao, Y.; Zhao, Y.; Liang, L.; Niu, Z.; Huang, X.; Fu, H.; Liu, S. Finer resolution observation and monitoring of global land cover: First mapping results with Landsat TM and ETM+ data. Int. J. Remote Sens. 2013, 34, 2607–2654. [Google Scholar] [CrossRef]
- Homer, C.; Dewitz, J.; Jin, S.; Xian, G.; Costello, C.; Danielson, P.; Gass, L.; Funk, M.; Wickham, J.; Stehman, S. Conterminous United States land cover change patterns 2001–2016 from the 2016 national land cover database. ISPRS J. Photogramm. Remote Sens. 2020, 162, 184–199. [Google Scholar] [CrossRef]
- Bai, Y.; Feng, M.; Jiang, H.; Wang, J.; Zhu, Y.; Liu, Y. Assessing consistency of five global land cover data sets in China. Remote Sens. 2014, 6, 8739–8759. [Google Scholar] [CrossRef]
- Kang, J.; Wang, Z.; Sui, L.; Yang, X.; Ma, Y.; Wang, J. Consistency analysis of remote sensing land cover products in the tropical rainforest climate region: A case study of Indonesia. Remote Sens. 2020, 12, 1410. [Google Scholar] [CrossRef]
- Tsendbazar, N.-E.; de Bruin, S.; Mora, B.; Schouten, L.; Herold, M. Comparative assessment of thematic accuracy of GLC maps for specific applications using existing reference data. Int. J. Appl. Earth Obs. Geoinf. 2016, 44, 124–135. [Google Scholar] [CrossRef]
- Liu, L.; Zhang, X.; Gao, Y.; Chen, X.; Shuai, X.; Mi, J. Finer-resolution mapping of global land cover: Recent developments, consistency analysis, and prospects. J. Remote Sens. 2021, 2021, 5289697. [Google Scholar] [CrossRef]
- Tsendbazar, N.-E.; De Bruin, S.; Fritz, S.; Herold, M. Spatial accuracy assessment and integration of global land cover datasets. Remote Sens. 2015, 7, 15804–15821. [Google Scholar] [CrossRef]
- Sun, B.; Chen, X.; Zhou, Q. Uncertainty assessment of GlobeLand30 land cover data set over central Asia. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2016, 41, 1313–1317. [Google Scholar] [CrossRef]
- Cui, P.; Chen, T.; Li, Y.; Liu, K.; Zhang, D.; Song, C. Comparison and Assessment of Different Land Cover Datasets on the Cropland in Northeast China. Remote Sens. 2023, 15, 5134. [Google Scholar] [CrossRef]
- Zhao, Y.; Gong, P.; Yu, L.; Hu, L.; Li, X.; Li, C.; Zhang, H.; Zheng, Y.; Wang, J.; Zhao, Y. Towards a common validation sample set for global land-cover mapping. Int. J. Remote Sens. 2014, 35, 4795–4814. [Google Scholar] [CrossRef]
- Zhao, T.; Zhang, X.; Gao, Y.; Mi, J.; Liu, W.; Wang, J.; Jiang, M.; Liu, L. Assessing the Accuracy and Consistency of Six Fine-Resolution Global Land Cover Products Using a Novel Stratified Random Sampling Validation Dataset. Remote Sens. 2023, 15, 2285. [Google Scholar] [CrossRef]
- Stehman, S.V.; Foody, G.M. Key issues in rigorous accuracy assessment of land cover products. Remote Sens. Environ. 2019, 231, 111199. [Google Scholar] [CrossRef]
- Tsendbazar, N.; De Bruin, S.; Herold, M. Assessing global land cover reference datasets for different user communities. ISPRS J. Photogramm. Remote Sens. 2015, 103, 93–114. [Google Scholar] [CrossRef]
- Olofsson, P.; Foody, G.M.; Herold, M.; Stehman, S.V.; Woodcock, C.E.; Wulder, M.A. Good practices for estimating area and assessing accuracy of land change. Remote Sens. Environ. 2014, 148, 42–57. [Google Scholar] [CrossRef]
- Wickham, J.D.; Stehman, S.V.; Gass, L.; Dewitz, J.; Fry, J.A.; Wade, T.G. Accuracy assessment of NLCD 2006 land cover and impervious surface. Remote Sens. Environ. 2013, 130, 294–304. [Google Scholar] [CrossRef]
- Sahr, K. Hexagonal discrete global grid systems for geospatial computing. Arch. Fotogram. Kartogr. I Teledetekcji 2011, 22, 363–376. [Google Scholar]
- Liang, S.; Yi, Q.; Liu, J. Vegetation dynamics and responses to recent climate change in Xinjiang using leaf area index as an indicator. Ecol. Indic. 2015, 58, 64–76. [Google Scholar]
- Yu, H.; Bian, Z.; Mu, S.; Yuan, J.; Chen, F. Effects of climate change on land cover change and vegetation dynamics in Xinjiang, China. Int. J. Environ. Res. Public Health 2020, 17, 4865. [Google Scholar] [CrossRef] [PubMed]
- Xu, Y.; Yang, J.; Chen, Y. NDVI-based vegetation responses to climate change in an arid area of China. Theor. Appl. Climatol. 2016, 126, 213–222. [Google Scholar] [CrossRef]
- Rubel, F.; Kottek, M. Observed and projected climate shifts 1901-2100 depicted by world maps of the Köppen-Geiger climate classification. Meteorol. Z. 2010, 19, 135. [Google Scholar] [CrossRef]
- Olofsson, P.; Stehman, S.V.; Woodcock, C.E.; Sulla-Menashe, D.; Sibley, A.M.; Newell, J.D.; Friedl, M.A.; Herold, M. A global land-cover validation data set, part I: Fundamental design principles. Int. J. Remote Sens. 2012, 33, 5768–5788. [Google Scholar] [CrossRef]
- Peel, M.C.; Finlayson, B.L.; McMahon, T.A. Updated world map of the Köppen-Geiger climate classification. Hydrol. Earth Syst. Sci. 2007, 11, 1633–1644. [Google Scholar] [CrossRef]
- Yang, Z.; Lei, J.; Duan, Z.; Dong, J.; Su, C. Spatial distribution of population in Xinjiang. Geogr. Res 2016, 35, 2333–2346. [Google Scholar]
- Dale, V.H. The relationship between land-use change and climate change. Ecol. Appl. 1997, 7, 753–769. [Google Scholar]
- Valjarević, A.; Popovici, C.; Štilić, A.; Radojković, M. Cloudiness and water from cloud seeding in connection with plants distribution in the Republic of Moldova. Appl. Water Sci. 2022, 12, 262. [Google Scholar] [CrossRef]
- Friedl, M.A.; Sulla-Menashe, D.; Tan, B.; Schneider, A.; Ramankutty, N.; Sibley, A.; Huang, X. MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets. Remote Sens. Environ. 2010, 114, 168–182. [Google Scholar] [CrossRef]
- Chen, F.; Chen, J.; Wu, H.; Hou, D.; Zhang, W.; Zhang, J.; Zhou, X.; Chen, L. A landscape shape index-based sampling approach for land cover accuracy assessment. Sci. China Earth Sci. 2016, 59, 2263–2274. [Google Scholar] [CrossRef]
- Morris, E.K.; Caruso, T.; Buscot, F.; Fischer, M.; Hancock, C.; Maier, T.S.; Meiners, T.; Müller, C.; Obermaier, E.; Prati, D. Choosing and using diversity indices: Insights for ecological applications from the German Biodiversity Exploratories. Ecol. Evol. 2014, 4, 3514–3524. [Google Scholar] [CrossRef] [PubMed]
- Spellerberg, I.F.; Fedor, P.J. A tribute to Claude Shannon (1916–2001) and a plea for more rigorous use of species richness, species diversity and the ‘Shannon–Wiener’Index. Glob. Ecol. Biogeogr. 2003, 12, 177–179. [Google Scholar] [CrossRef]
- Karydas, C.; Panagos, P. Towards an assessment of the ephemeral gully erosion potential in Greece using Google Earth. Water 2020, 12, 603. [Google Scholar] [CrossRef]
- Sato, H.; Harp, E. Interpretation of earthquake-induced landslides triggered by the 12 May 2008, M7. 9 Wenchuan earthquake in the Beichuan area, Sichuan Province, China using satellite imagery and Google Earth. Landslides 2009, 6, 153–159. [Google Scholar] [CrossRef]
- Taylor, J.R.; Lovell, S.T. Mapping public and private spaces of urban agriculture in Chicago through the analysis of high-resolution aerial images in Google Earth. Landsc. Urban Plan. 2012, 108, 57–70. [Google Scholar] [CrossRef]
- Potere, D.; Schneider, A.; Angel, S.; Civco, D.L. Mapping urban areas on a global scale: Which of the eight maps now available is more accurate? Int. J. Remote Sens. 2009, 30, 6531–6558. [Google Scholar] [CrossRef]
- Foody, G. Local characterization of thematic classification accuracy through spatially constrained confusion matrices. Int. J. Remote Sens. 2005, 26, 1217–1228. [Google Scholar] [CrossRef]
- Stehman, S.V. Estimating area and map accuracy for stratified random sampling when the strata are different from the map classes. Int. J. Remote Sens. 2014, 35, 4923–4939. [Google Scholar] [CrossRef]
- Bie, Q.; Shi, Y.; Li, X.; Wang, Y. Contrastive Analysis and Accuracy Assessment of Three Global 30 m Land Cover Maps Circa 2020 in Arid Land. Sustainability 2023, 15, 741. [Google Scholar] [CrossRef]
- Fritz, S.; See, L. Identifying and quantifying uncertainty and spatial disagreement in the comparison of Global Land Cover for different applications. Glob. Change Biol. 2008, 14, 1057–1075. [Google Scholar] [CrossRef]
- See, L.M.; Fritz, S. A method to compare and improve land cover datasets: Application to the GLC-2000 and MODIS land cover products. IEEE Trans. Geosci. Remote Sens. 2006, 44, 1740–1746. [Google Scholar] [CrossRef]
- Wang, J.; Yang, X.; Wang, Z.; Cheng, H.; Kang, J.; Tang, H.; Li, Y.; Bian, Z.; Bai, Z. Consistency Analysis and Accuracy Assessment of Three Global Ten-Meter Land Cover Products in Rocky Desertification Region—A Case Study of Southwest China. ISPRS Int. J. Geo Inf. 2022, 11, 202. [Google Scholar] [CrossRef]
- Pérez-Hoyos, A.; García-Haro, F.; San-Miguel-Ayanz, J. Conventional and fuzzy comparisons of large scale land cover products: Application to CORINE, GLC2000, MODIS and GlobCover in Europe. ISPRS J. Photogramm. Remote Sens. 2012, 74, 185–201. [Google Scholar] [CrossRef]
- Ludwig, C.; Walli, A.; Schleicher, C.; Weichselbaum, J.; Riffler, M. A highly automated algorithm for wetland detection using multi-temporal optical satellite data. Remote Sens. Environ. 2019, 224, 333–351. [Google Scholar] [CrossRef]
- Tsendbazar, N.; Herold, M.; De Bruin, S.; Lesiv, M.; Fritz, S.; Van De Kerchove, R.; Buchhorn, M.; Duerauer, M.; Szantoi, Z.; Pekel, J.-F. Developing and applying a multi-purpose land cover validation dataset for Africa. Remote Sens. Environ. 2018, 219, 298–309. [Google Scholar] [CrossRef]
- Herold, M.; Mayaux, P.; Woodcock, C.; Baccini, A.; Schmullius, C. Some challenges in global land cover mapping: An assessment of agreement and accuracy in existing 1 km datasets. Remote Sens. Environ. 2008, 112, 2538–2556. [Google Scholar] [CrossRef]
- Fitzpatrick-Lins, K. Comparison of sampling procedures and data analysis for a land-use and land-cover map. Photogramm. Eng. Remote Sens. 1981, 47, 343–351. [Google Scholar]
- Lv, Z.; Wang, P.; Yan, C.; Nie, M.; Xiong, X.; Ding, M. Spectral characteristic of the waters with different sizes of particles: Impact of water quality and land-use type. Environ. Sci. Pollut. Res. 2023, 30, 9543–9557. [Google Scholar] [CrossRef]
- Kang, J.; Yang, X.; Wang, Z.; Cheng, H.; Wang, J.; Tang, H.; Li, Y.; Bian, Z.; Bai, Z. Comparison of three ten meter land cover products in a Drought region: A case study in Northwestern China. Land 2022, 11, 427. [Google Scholar] [CrossRef]
- Zhu, L.; Jin, G.; Gao, D. Integrating Land-Cover Products Based on Ontologies and Local Accuracy. Information 2021, 12, 236. [Google Scholar] [CrossRef]
Validated LC Products | Validation Area | Sample Quantity | Literature |
---|---|---|---|
GLC_FCS30 | Globe | 44,043 | Zhang et al. (2021) [1] |
CLCD | China | 5463 | Yang et al. (2021) [5] |
GlobeLand30 | Globe | 38,644 | Chen et al. (2015) [3] |
FROM-GLC30 | Globe | 38,664 | Zhao et al. (2014) [15] |
GlobeLand30, FROM-GLC30, and GLC_FCS30 | Globe | 79,112 | Zhao et al. (2023) [16] |
CLCD | Id | GlobeLand30 | Id | GLC_FCS30 | Id |
---|---|---|---|---|---|
Cropland | 1 | Cultivated land | 10 | Rain-fed cropland | 10 |
Herbaceous cover | 11 | ||||
Tree or shrub cover (orchard) | 12 | ||||
Irrigated cropland | 20 | ||||
Forest | 2 | Forest | 20 | Evergreen broadleaved forest | 50 |
Deciduous broadleaved forest | 60 | ||||
Closed deciduous broadleaved forest | 61 | ||||
Open deciduous broadleaved forest | 62 | ||||
Evergreen needleleaved forest | 70 | ||||
Closed evergreen needleleaved forest | 71 | ||||
Open evergreen needleleaved forest | 72 | ||||
Deciduous needleleaved forest | 80 | ||||
Closed deciduous needleleaved forest | 81 | ||||
Open deciduous needleleaved forest | 82 | ||||
Mixed-leaf forest | 90 | ||||
Shrub | 3 | Shrubland | 40 | Shrubland | 120 |
Evergreen shrubland | 121 | ||||
Deciduous shrubland | 122 | ||||
Grassland | 4 | Grassland | 30 | Grassland | 130 |
Wetland | 9 | Wetland | 50 | Wetlands | 180 |
Impervious | 8 | Artificial surfaces | 80 | Impervious surfaces | 190 |
Bare land | 7 | Bare land | 90 | Lichens and mosses | 140 |
Sparse vegetation | 150 | ||||
Sparse shrubland | 152 | ||||
Sparse herbaceous cover | 153 | ||||
Bare areas | 200 | ||||
Consolidated bare areas | 201 | ||||
Unconsolidated bare areas | 202 | ||||
Water | 5 | Water bodies | 60 | Water body | 210 |
Snow/Ice | 6 | Permanent snow and ice | 100 | Permanent ice and snow | 220 |
Tundra | 70 |
New Code | Climate | Climate Code |
---|---|---|
1 | Desert | BWk |
2 | Grassland | BSk + Dsa + Dsb |
3 | Continental forest | Dfa + Dfb |
4 | Boreal forest | Dsc + Dwc + Dfc |
5 | Frost | EF |
LC Type | Typical Imagery on Google Earth |
---|---|
Cropland | |
Forest | |
Shrubland | |
Grassland | |
Water | |
Snow/Ice | |
Bare land | |
Impervious | |
Wetland |
SRS_Val vs. HDLV-XJ | GLV_2015 vs. HDLV-XJ | |||
---|---|---|---|---|
Classes | P.A. | U.A. | P.A. | U.A. |
Cropland | 100.00% | 77.78% | 0.00% | 0.00% |
Forest | 75.00% | 100.00% | 0.00% | 0.00% |
Shrubland | 75.00% | 75.00% | 0.00% | 0.00% |
Grassland | 90.63% | 82.86% | 0.00% | 0.00% |
Water | 0.00% | 0.00% | 0.00% | 0.00% |
Snow/Ice | 75.00% | 50.00% | 94.44% | 77.27% |
Bare land | 89.09% | 100.00% | 89.80% | 100.00% |
Impervious | 0.00% | 0.00% | 0.00% | 0.00% |
Wetland | 0.00% | 0.00% | 0.00% | 0.00% |
O.A. | 88.68% | 82.43% |
Classified | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
CRP | FST | SHR | GRS | Wat | SI | BaL | IMP | WET | Total | ||
Reference | CRP | 1369 | 4 | 59 | 13 | 0 | 0 | 61 | 7 | 2 | 1515 |
FST | 1 | 570 | 4 | 6 | 0 | 0 | 14 | 0 | 0 | 595 | |
SHR | 1 | 1 | 294 | 7 | 0 | 0 | 15 | 0 | 0 | 318 | |
GRS | 130 | 204 | 51 | 3679 | 0 | 20 | 788 | 1 | 5 | 4878 | |
Wat | 1 | 0 | 3 | 1 | 128 | 2 | 6 | 1 | 1 | 143 | |
SI | 0 | 1 | 2 | 89 | 2 | 781 | 18 | 0 | 0 | 893 | |
BaL | 6 | 4 | 181 | 542 | 2 | 108 | 11,513 | 1 | 16 | 12,373 | |
IMP | 18 | 0 | 16 | 3 | 0 | 0 | 17 | 86 | 0 | 140 | |
WET | 12 | 3 | 9 | 14 | 1 | 1 | 16 | 0 | 21 | 77 | |
Total | 1538 | 787 | 619 | 4354 | 133 | 912 | 12,448 | 96 | 45 | 20,932 | |
P.A. | 90.36% | 95.80% | 92.45% | 75.42% | 89.51% | 87.46% | 93.05% | 61.43% | 27.27% | ||
U.A. | 89.01% | 72.43% | 47.50% | 84.50% | 96.24% | 85.64% | 92.49% | 89.58% | 46.67% | ||
O.A. | 88.10% | ||||||||||
Kappa | 0.798716 |
Classified | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
CRP | FST | SHR | GRS | Wat | SI | BaL | IMP | WET | Total | ||
Reference | CRP | 1211 | 7 | 0 | 261 | 0 | 0 | 24 | 11 | 1 | 1515 |
FST | 3 | 289 | 0 | 295 | 0 | 1 | 4 | 3 | 0 | 595 | |
SHR | 8 | 0 | 0 | 203 | 0 | 0 | 101 | 6 | 0 | 318 | |
GRS | 26 | 29 | 0 | 3620 | 1 | 14 | 1173 | 14 | 1 | 4878 | |
Wat | 0 | 1 | 0 | 11 | 115 | 1 | 11 | 4 | 0 | 143 | |
SI | 0 | 0 | 0 | 52 | 11 | 551 | 279 | 0 | 0 | 893 | |
BaL | 17 | 0 | 0 | 1040 | 10 | 26 | 11,261 | 19 | 0 | 12,373 | |
IMP | 22 | 1 | 0 | 77 | 0 | 0 | 18 | 22 | 0 | 140 | |
WET | 8 | 2 | 0 | 34 | 4 | 1 | 18 | 5 | 5 | 77 | |
Total | 1295 | 329 | 0 | 5593 | 141 | 594 | 12,889 | 84 | 7 | 20,932 | |
P.A. | 79.93% | 48.57% | 0.00% | 74.21% | 80.42% | 61.70% | 91.01% | 15.71% | 6.49% | ||
U.A. | 93.51% | 87.84% | 0.00% | 64.72% | 81.56% | 92.76% | 87.37% | 26.19% | 71.43% | ||
O.A. | 81.57% | ||||||||||
Kappa | 0.675249 |
Classified | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
CRP | FST | SHR | GRS | Wat | SI | BaL | IMP | WET | Total | ||
Reference | CRP | 1360 | 2 | 1 | 109 | 1 | 0 | 15 | 21 | 6 | 1515 |
FST | 5 | 274 | 6 | 297 | 1 | 1 | 9 | 2 | 0 | 595 | |
SHR | 18 | 5 | 58 | 120 | 2 | 0 | 105 | 3 | 7 | 318 | |
GRS | 48 | 58 | 46 | 3800 | 7 | 40 | 854 | 4 | 21 | 4878 | |
Wat | 1 | 1 | 0 | 3 | 126 | 1 | 2 | 1 | 8 | 143 | |
SI | 0 | 5 | 3 | 37 | 2 | 543 | 302 | 0 | 1 | 893 | |
BaL | 59 | 9 | 61 | 988 | 25 | 33 | 11,170 | 8 | 20 | 12,373 | |
IMP | 18 | 0 | 1 | 11 | 0 | 0 | 6 | 104 | 0 | 140 | |
WET | 0 | 1 | 1 | 3 | 8 | 0 | 3 | 0 | 61 | 77 | |
Total | 1509 | 355 | 177 | 5368 | 172 | 618 | 12,466 | 143 | 124 | 20,932 | |
P.A. | 89.77% | 46.05% | 18.24% | 77.90% | 88.11% | 60.81% | 90.28% | 74.29% | 79.22% | ||
U.A. | 90.13% | 77.18% | 32.77% | 70.79% | 73.26% | 87.86% | 89.60% | 72.73% | 49.19% | ||
O.A. | 83.58% | ||||||||||
Kappa | 0.717466 |
Similarity Coefficient | Three Maps | GLC_FCS30 vs. CLCD | CLCD vs. GlobeLamd30 | GLC_FCS30 vs. GlobeLand30 |
---|---|---|---|---|
Cropland | 66.01% | 69.76% | 80.60% | 64.47% |
Forest | 30.95% | 42.48% | 55.20% | 35.27% |
Shrubland | 0.00% | 0.00% | 0.00% | 2.10% |
Grassland | 37.76% | 48.53% | 67.80% | 43.26% |
Water | 66.13% | 71.81% | 74.80% | 61.89% |
Snow/Ice | 51.84% | 55.52% | 72.42% | 47.02% |
Bare land | 74.14% | 73.46% | 90.41% | 69.55% |
Impervious | 12.14% | 17.64% | 15.44% | 40.84% |
Wetland | 0.78% | 2.34% | 8.96% | 8.12% |
OS | 69.96% | 78.46% | 83.32% | 75.16% |
LC Type | Mean Area | Percentage Mean |
---|---|---|
Cropland | 98,989.83 | 5.95% |
Forest | 29,424.22 | 1.77% |
Shrubland | 18,850.94 | 1.13% |
Grassland | 350,050.94 | 21.03% |
Water | 11,369.57 | 0.68% |
Snow/Ice | 42,092.11 | 2.53% |
Bare land | 1,102,577.54 | 66.22% |
Impervious | 7339.36 | 0.44% |
Wetland | 4202.49 | 0.25% |
LC Type | GLC_FCS30 | Percentage in GLC_FCS30 | CLCD | Percentage in CLCD | GlobeLand30 | Percentage in GlobeLand30 |
---|---|---|---|---|---|---|
Cropland | 104,931.34 | 6.30% | 87,744.63 | 5.27% | 104,293.52 | 6.26% |
Forest | 48,311.59 | 2.90% | 18,576.16 | 1.12% | 21,384.91 | 1.28% |
Shrubland | 44,592.01 | 2.68% | 1.27 | 0.00% | 11,959.54 | 0.72% |
Grassland | 307,358.94 | 18.46% | 383,017.16 | 23.01% | 359,776.72 | 21.61% |
Water | 10,028.85 | 0.60% | 10,792.64 | 0.65% | 13,287.22 | 0.80% |
Snow/Ice | 55,086.92 | 3.31% | 35,631.59 | 2.14% | 35,557.83 | 2.14% |
Bare land | 1,084,205.57 | 65.12% | 1,123,584.54 | 67.49% | 1,099,942.51 | 66.07% |
Impervious | 7472.84 | 0.45% | 5048.18 | 0.30% | 9497.05 | 0.57% |
Wetland | 2908.94 | 0.17% | 500.84 | 0.03% | 9197.70 | 0.55% |
LC Type | CRP | FST | SHR | GRS | Wat | SI | BaL | IMP | WET | Total |
---|---|---|---|---|---|---|---|---|---|---|
HDLV-XJ | 1515 | 595 | 318 | 4878 | 143 | 893 | 12,373 | 140 | 77 | 20,932 |
SRS_Val | 55 | 23 | 19 | 143 | 3 | 28 | 381 | 5 | 2 | 659 |
GLV_2015 | 0 | 0 | 32 | 0 | 1 | 96 | 283 | 2 | 0 | 403 |
LC Product | Method | Literature |
---|---|---|
GLC_FCS30 | Local adaptive random forest models were trained for each 5° × 5′ geographical grid element to generate the land-cover maps. | Zhang et al. (2021) [1] |
CLCD | A global random forest classifier was trained to classify the whole of China. | Yang et al. (2021) [5] |
GlobeLand30 | A global pixel- and object-based classification model was applied to classify global land covers, and a knowledge-based interactive post-process was applied to improve the mapping accuracy. | Chen et al. (2015) [3] |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, J.; Ren, Y.; Chen, X. Regional Accuracy Assessment of 30-Meter GLC_FCS30, GlobeLand30, and CLCD Products: A Case Study in Xinjiang Area. Remote Sens. 2024, 16, 82. https://doi.org/10.3390/rs16010082
Liu J, Ren Y, Chen X. Regional Accuracy Assessment of 30-Meter GLC_FCS30, GlobeLand30, and CLCD Products: A Case Study in Xinjiang Area. Remote Sensing. 2024; 16(1):82. https://doi.org/10.3390/rs16010082
Chicago/Turabian StyleLiu, Jingpeng, Yu Ren, and Xidong Chen. 2024. "Regional Accuracy Assessment of 30-Meter GLC_FCS30, GlobeLand30, and CLCD Products: A Case Study in Xinjiang Area" Remote Sensing 16, no. 1: 82. https://doi.org/10.3390/rs16010082