Towards a common validation sample set for global land-cover mapping

Zhao, Yuanyuan; Gong, Peng; Yu, Le; Hu, Luanyun; Li, Xueyan; Li, Congcong; Zhang, Haiying; Zheng, Yunpu; Wang, Jie; Zhao, Yongchao; Cheng, Qu; Liu, Caixia; Liu, Shuang; Wang, Xiaoyi

doi:10.1080/01431161.2014.930202

Cited by 166 publications

(139 citation statements)

References 42 publications

Supporting

Mentioning

119

Contrasting

Order By: Relevance

“…More details of the validation data are provided in section 2.4 but the samples from the two competitions (Table 2) were purposely chosen to align with the location of the global validation dataset developed by Zhao et al (2014) in their evaluation of the Chinese 30-m global land cover product.…”

Section: Global Validation Datasetmentioning

confidence: 99%

“…To collect data at the same locations as the validation data assembled for the Chinese 30 m land cover map (Zhao et al, 2014) Combined with the Wilderness dataset to validate both hybrid maps…”

Section: Global Validation Datasetmentioning

confidence: 99%

“…The first was an external dataset that was developed specifically for the validation of the Chinese 30 m global land cover map (Gong et al, 2013;Zhao et al, 2014), which contains 38,664 sample units globally based on Landsat and Google Earth image interpretation. The sample design utilised equal-area stratified random sampling, which partitioned the global land area into approximately 7,000 equal-area hexagons, inside of which 5 random samples were chosen from each one.…”

Section: Map Validationmentioning

confidence: 99%

“…Secondly, we implement a second approach in which the method is only applied to those areas where there is complete disagreement between land cover products, taking agreement between two or more land cover products as the land cover type at all other locations. Finally, we use an independent crowdsourced dataset to validate the products, using the sampling scheme of the global validation dataset created by Zhao et al (2014) as the basis for collecting data via Geo-Wiki.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Building a hybrid land cover map with crowdsourcing and geographically weighted regression

See

Schepaschenko

Lesiv

et al. 2015

ISPRS Journal of Photogrammetry and Remote Sensing

Self Cite

128

103

View full text Add to dashboard Cite

Land cover is of fundamental importance to many environmental applications and serves as critical baseline information for many large scale models e.g. in developing future scenarios of land use and climate change. Although there is an ongoing movement towards the development of higher resolution global land cover maps, medium resolution land cover products (e.g. GLC2000 and MODIS) are still very useful for modelling and assessment purposes. However, the current land cover products are not accurate enough for many applications so we need to develop approaches that can take existing land covers maps and produce a better overall product in a hybrid approach. This paper uses geographically weighted regression (GWR) and crowdsourced validation data from Geo-Wiki to create two hybrid global land cover maps that use medium resolution land cover products as an input.Two different methods were used: a) the GWR was used to determine the best land cover product at each location; b) the GWR was only used to determine the best land cover at those locations where all three land cover maps disagree, using the agreement of the land cover maps to determine land cover at the other cells. The results show that the hybrid land cover map developed using the first method resulted in a lower overall disagreement than the individual global land cover maps. The hybrid map produced by the second method was also better when compared to the GLC2000 and GlobCover but worse or similar in performance to the MODIS land cover product depending upon the metrics considered. The reason for this may be due to the use of the GLC2000 in the development of GlobCover, which may have resulted in areas where both maps agree with one another but not with MODIS, and where MODIS may in fact better represent land cover in those situations. These results serve to demonstrate that spatial analysis methods can be used to improve medium resolution global land cover information with existing products.

show abstract

Section: Global Validation Datasetmentioning

confidence: 99%

Section: Global Validation Datasetmentioning

confidence: 99%

Section: Map Validationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Building a hybrid land cover map with crowdsourcing and geographically weighted regression

See

Schepaschenko

Lesiv

et al. 2015

ISPRS Journal of Photogrammetry and Remote Sensing

Self Cite

128

103

View full text Add to dashboard Cite

show abstract

“…To collect data at the same locations as the validation data assembled for the Chinese 30 m global land cover map (Zhao et al, 2014) 26 participants 1363 points/ participant…”

Section: Global Validation Datasetmentioning

confidence: 99%

Harnessing the power of volunteers, the internet and Google Earth to collect and validate global spatial information using Geo-Wiki

See

Perger

Schill

et al. 2015

Technological Forecasting and Social Change

View full text Add to dashboard Cite

Highlights of the Paper 1. Geo-Wiki is a tool for visualisation, crowdsourcing and validation of information on global land cover.2. Recent enhancements to the tool include a Geo-Wiki for teaching, mobile phone apps and gamfication.3. Crowdsourced data from Geo-Wiki have been used to create new maps of agricultural field size, wilderness, cropland and land cover. AbstractInformation about land cover and land use is needed for a wide range of applications such as nature protection and biodiversity, forest and water management, urban and transport planning, natural hazard prevention and mitigation, monitoring of agricultural policies and economic land use modelling. A number of different remotely-sensed global land cover products are available but studies have shown that there are large spatial discrepancies between these different products when compared. To address this issue of land cover uncertainty, a tool called Geo-Wiki was developed, which integrates online and mobile applications, high resolution satellite imagery available from Google Earth, and data collection through crowdsourcing as a mechanism for validating and improving globally relevant spatial information on land cover and land use. Through its growing network of volunteers and a number of successful data collection campaigns, almost 5 million samples of land cover and land use have been collected at many locations around the globe. This paper provides an overview of the main features of Geo-Wiki, and then using a series of examples, illustrates how the crowdsourced data collected through Geo-Wiki have been used to improve information on land cover and land use.

show abstract

Mapping 30-m Resolution Land Cover of China Based on Full Convolutional Neural Network

Liu

Zhong

2022

Proceedings of the 7th China High Resolution Earth Observation Conference (CHREOC 2020)

View full text Add to dashboard Cite

Towards a common validation sample set for global land-cover mapping

Cited by 166 publications

References 42 publications

Building a hybrid land cover map with crowdsourcing and geographically weighted regression

Building a hybrid land cover map with crowdsourcing and geographically weighted regression

Harnessing the power of volunteers, the internet and Google Earth to collect and validate global spatial information using Geo-Wiki

Mapping 30-m Resolution Land Cover of China Based on Full Convolutional Neural Network

Contact Info

Product

Resources

About