Comparisons of three recent moderate resolution African land cover datasets: CGLS-LC100, ESA-S2-LC20, and FROM-GLC-Africa30

Xu, Yidi; Yu, Le; Feng, Di; Peng, Dailiang; Li, Congcong; Huang, Xiaomeng; Lu, Hui; Gong, Peng

doi:10.1080/01431161.2019.1587207

Cited by 53 publications

(35 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two classes, Wetland and Shrubland have the highest disagreement. Results obtained here are similar to the ones reported by Xu et al(2019) although different approaches of comparison were used.…”

Section: Discussionsupporting

confidence: 87%

“…A comparison of complete CCI Africa Prototype product with other LC products: Copernicus Global Land Service Land Cover (CGLS-LC100) and Finer Resolution Observation and Monitoring of Global Land Cover for Africa version 2 (FROM-GLC-Africa30) was done before (Xu et al, 2019). CGLS-LC100 has resolution of 100 m, while FROM-GLC-Africa30 has 30 m resolution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inter-Comparison of the Global Land Cover Maps in Africa Supplemented by Spatial Association of Errors

Bratić¹,

Oxoli²,

Brovelli³

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> Recent advances in Earth Observations supported development of high-resolution land cover (LC) maps on a large-scale. This is an important step forward, especially for developing countries, which experienced problems in the past due to absence of reliable LC information. Nevertheless, increasing number of LC products is imposing additional validation workload to confirm their quality. In this paper inter-comparison of two recent LC products (GlobeLand30 and S2 prototype LC 20m map of Africa) for country of Rwanda in Africa was done. It is a way to facilitate validation by identifying the areas with higher probability of error. Specific approach of comparison of single pixel of one map with multiple pixels of another map provided confusion matrix and sub-pixel agreement table. In this work, accuracy indexes based on the confusion matrix were computed as a measure of similarity between the two maps. Furthermore, Moran’s I index was computed for estimation of spatial association of the pixels in disagreement. Also, total disagreement, as well as disagreement of particularly confused classes was visualised to analyse their spatial distribution. The results are showing that similarity of the two maps is about 66%. Disagreements are spatially associated and the most evident in the eastern and north-western part of the area of interest. This coincides also with the distribution of the two most confused classes Wetland and Shrubland. The results delineate areas of inconsistency between the two maps, and therefore areas where careful accuracy analysis are needed.</p>

show abstract

Section: Discussionsupporting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Inter-Comparison of the Global Land Cover Maps in Africa Supplemented by Spatial Association of Errors

Bratić¹,

Oxoli²,

Brovelli³

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Anyhow, this result indicates that the CGLS-LC100 2015 Collection 2 map has a comparable, if not better, quality as previous LC maps. Additional comparison studies verified this indication [20][21][22][23]. Table 4.…”

Section: Quantitative Comparison Of Cgls-lc100 and Existing Global Lcmentioning

confidence: 61%

“…We integrated spectral, temporal and spatial features derived from the PROBA-V time series to improve classification accuracy as recommended by Zhai et al [18] and Eberenz et al [19]. Based on the success of this demonstration product for Africa, showing high quality with an overall accuracy of 74.3% and alignment to other continental LC maps [20][21][22][23], Collection 2 of the CGLS-LC100 product was released in May 2019, extending the map to a global coverage for the reference year 2015 [15]. However, Collection 2 was not just a global up-scaling, but also includes major improvements in the map quality, reaching now around 80% or more of overall accuracy for each continent.…”

Section: Introductionmentioning

confidence: 99%

Copernicus Global Land Cover Layers—Collection 2

et al. 2020

View full text Add to dashboard Cite

In May 2019, Collection 2 of the Copernicus Global Land Cover layers was released. Next to a global discrete land cover map at 100 m resolution, a set of cover fraction layers is provided depicting the percentual cover of the main land cover types in a pixel. This additional continuous classification scheme represents areas of heterogeneous land cover better than the standard discrete classification scheme. Overall, 20 layers are provided which allow customization of land cover maps to specific user needs or applications (e.g., forest monitoring, crop monitoring, biodiversity and conservation, climate modeling, etc.). However, Collection 2 was not just a global up-scaling, but also includes major improvements in the map quality, reaching around 80% or more overall accuracy. The processing system went into operational status allowing annual updates on a global scale with an additional implemented training and validation data collection system. In this paper, we provide an overview of the major changes in the production of the land cover maps, that have led to this increased accuracy, including aligning with the Sentinel 2 satellite system in the grid and coordinate system, improving the metric extraction, adding better auxiliary data, improving the biome delineations, as well as enhancing the expert rules. An independent validation exercise confirmed the improved classification results. In addition to the methodological improvements, this paper also provides an overview of where the different resources can be found, including access channels to the product layer as well as the detailed peer-review product documentation.

show abstract

“…For the study on urban morphology and urbanization, this problem still has to be dealt with. The accuracy of land classification, even when using high-quality, high-spatial-resolution data, such as for the ESA-S2-AFRICA-LC20 map, is still limited by factors such as shadows, mixed pixels, and mapping accuracy, especially for the land-cover type "small settlement" [70]. The original NPP-VIIRS monthly nighttime light data still contain lights related to small settlement areas.…”

Section: Discussionmentioning

confidence: 99%

Filtering the NPP-VIIRS Nighttime Light Data for Improved Detection of Settlements in Africa

Yuan

Menenti

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Observing and understanding changes in Africa is a hotspot in global ecological environmental research since the early 1970s. As possible causes of environmental degradation, frequent droughts and human activities attracted wide attention. Remote sensing of nighttime light provides an effective way to map human activities and assess their intensity. To identify settlements more effectively, this study focused on nighttime light in the northern Equatorial Africa and Sahel settlements to propose a new method, namely, the patches filtering method (PFM) to identify nighttime lights related to settlements from the National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) monthly nighttime light data by separating signal components induced by biomass burning, thereby generating a new annual image in 2016. The results show that PFM is useful for improving the quality of NPP-VIIRS monthly nighttime light data. Settlement lights were effectively separated from biomass burning lights, in addition to capturing the seasonality of biomass burning. We show that the new 2016 nighttime light image can very effectively identify even small settlements, notwithstanding their fragmentation and unstable power supply. We compared the image with earlier NPP-VIIRS annual nighttime light data from the National Oceanic and Atmospheric Administration (NOAA) National Center for Environmental Information (NCEI) for 2016 and the Sentinel-2 prototype Land Cover 20 m 2016 map of Africa released by the European Space Agency (ESA-S2-AFRICA-LC20). We found that the new annual nighttime light data performed best among the three datasets in capturing settlements, with a high recognition rate of 61.8%, and absolute superiority for settlements of 2.5 square kilometers or less. This shows that the method separates biomass burning signals very effectively, while retaining the relatively stable, although dim, lights of small settlements. The new 2016 annual image demonstrates good performance in identifying human settlements in sparsely populated areas toward a better understanding of human activities.

show abstract

Comparisons of three recent moderate resolution African land cover datasets: CGLS-LC100, ESA-S2-LC20, and FROM-GLC-Africa30

Cited by 53 publications

References 26 publications

Inter-Comparison of the Global Land Cover Maps in Africa Supplemented by Spatial Association of Errors

Inter-Comparison of the Global Land Cover Maps in Africa Supplemented by Spatial Association of Errors

Copernicus Global Land Cover Layers—Collection 2

Filtering the NPP-VIIRS Nighttime Light Data for Improved Detection of Settlements in Africa

Contact Info

Product

Resources

About