GLC_FCS30:  Global   land-cover product with   fine   classification system at 30 m using time-series Landsat imagery

Zhang, Xiao; Liu, Liangyun; Chen, Xidong; Gao, Yuan; Xie, Shaodong; Murai, Jun

doi:10.5194/essd-2020-182

Cited by 30 publications

(51 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Foody and Arora, 1997;Foody and Mathur, 2004). Usually, the strategies of training sample collection for a large-scale mapping task include: 1) visually-interpreted samples and 2) samples automatically derived from existing LC products (Zhang et al, 2020b). The visual interpretation method can obtain high quality samples but require intensive human labour.…”

Section: Training Sample Generationmentioning

confidence: 99%

30 m annual land cover and its dynamics in China from 1990 to 2019

Yang¹,

Huang²

2021

Preprint

View full text Add to dashboard Cite

Abstract. Land cover (LC) determines the energy exchange, water and carbon cycle between Earth's spheres. Accurate LC information is a fundamental parameter for the environment and climate studies. Considering that the LC in China has been altered dramatically with the economic development in the past few decades, sequential and fine-scale LC monitoring is in urgent need. However, currently, fine-resolution annual LC dataset produced by the observational images is generally unavailable for China due to the lack of sufficient training samples and computational capabilities. To deal with this issue, we produced the first Landsat-derived annual China Land Cover Dataset (CLCD) on the Google Earth Engine (GEE) platform, which contains 30 m annual LC and its dynamics of China from 1990 to 2019. We first collected the training samples by combining stable samples extracted from China’s Land-Use/Cover Datasets (CLUD), and visually-interpreted samples from satellite time-series data, Google Earth and Google Map. Using 335,709 Landsat images on the GEE, several temporal metrics were constructed and fed to the random forest classifier to obtain classification results. We then proposed a post-processing method incorporating spatial-temporal filtering and logical reasoning to further improve the spatial-temporal consistency of CLCD. Finally, the overall accuracy of CLCD reached 79.31 % based on 5,463 visually-interpreted samples. A further assessment based on 5,131 third-party test samples showed that the overall accuracy of CLCD outperforms that of MCD12Q1, ESACCI_LC, FROM_GLC, and GlobaLand30. Besides, we intercompared the CLCD with several Landsat-derived thematic products, which exhibited good consistencies with the Global Forest Change, the Global Surface Water, and three impervious surface products. Based on the CLCD, the trends and patterns of China’s LC changes during 1985 and 2019 were revealed, such as expansion of impervious surface (+148.71 %) and water (+18.39 %), decrease of cropland (−4.85 %) and grassland (−3.29 %), increase of forest (+4.34 %). In general, CLCD reflected the rapid urbanization and a series of ecological projects (e.g., Gain for Green) in China and revealed the anthropogenic implications on LC under the condition of climate change, signifying its potential application in the global change research. The CLCD dataset introduced in this article is freely available at http://doi.org/10.5281/zenodo.4417810 (Yang and Huang, 2021).

show abstract

Section: Training Sample Generationmentioning

confidence: 99%

30 m annual land cover and its dynamics in China from 1990 to 2019

Yang¹,

Huang²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The classification matrix used to produce ODSE-LULC is available from http://doi.org/10.5281/zenodo.4740691. • GLC FCS30-2015 (Zhang et al, 2020);…”

Section: Filteringmentioning

confidence: 99%

“…The GLC FCS30 nomenclature was not suitable for direct translation because some land cover groups (such as forests) are separated in several subcategories. We therefore aggregated their thematic resolution to the higher level of abstraction described in Zhang et al (2020). The complete translation scheme is available via the GitLab repository of the GeoHarmonizer project (https://gitlab.com/ geoharmonizer_inea/spatial-layers).…”

Section: Filteringmentioning

confidence: 99%

“…Vilar et al (2019) have done extensive evaluation of accuracy of the Coordination of Information on the Environment (CORINE) Land Cover (CLC) products for period 2011-2012 using the LUCAS data and found that agreement with LUCAS was slightly higher for Climate Change Initiative -Land Cover (CCI-LC) (59%; 18 classes) than for CLC (56%; 44 classes). Gao et al (2020) has evaluated accuracy of the global 30 m resolution products GlobeLand30 with 10 classes (Chen et al, 2015), and Global Land Cover with Fine Classification System at 30 m (GLC FCS30) with 18 classes (Zhang et al, 2020) using the LUCAS point data and concluded that the GlobeLand30-2010 product agrees with LUCAS points up to 89%, while GLC FCS30-2015 agrees up to 85%. The large difference in the agreement reported by Vilar et al (2019) and Chen et al (2015) can be attributed to the number of classes in the two studies: the absolute accuracy linearly drops with the number of classes (Herold et al, 2008;Van et al, 2019), and usually the accuracy results for 6-10 classes vs 40 classes can be up to 50% better.…”

mentioning

confidence: 99%

“…The ESA's WorldCover project (https://esa-worldcover.org/) is another global 10 m spatial resolution land cover product that aims at consistent mapping accuracy of at least 75%. Silva et al, 2013) 2006 100-m S2GLC (Malinowski et al, 2020) 2017 10 m 15 classes Pflugmacher et al (2019) 2014-2016 30 m 75% 12 classes N / N GLC FCS30 (Zhang et al, 2020) 2015, 2020 30-m N / N Buchhorn et al (2020Buchhorn et al ( ) 2015Buchhorn et al ( , 2016Buchhorn et al ( , 2017 Based on these works, it can be said that the state-of-the-art land cover mapping projects primarily aim at:…”

mentioning

confidence: 99%

See 2 more Smart Citations

A spatiotemporal ensemble machine learning framework for generating land use / land cover time-series maps for Europe (2000 – 2019) based on LUCAS, CORINE and GLAD Landsat

Witjes¹,

Parente²,

Diemen³

et al. 2021

Preprint

View full text Add to dashboard Cite

A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of land use / land cover (LULC) dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal covariate datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model was fitted by combining random forest, gradient boosted trees, and artificial neural network, with logistic regressor as meta-learner. The results show that the most important covariates for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with 62%, 70%, and 87% accuracy when predicting 33 (level-3), 14 (level-2), and 5 classes (level-1); with artificial surface classes such as 'airports' and 'railroads' showing the lowest match with validation points. The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest gradual deforestation trends in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer.

show abstract

Woody plant functional traits and phylogenetic signals correlate with urbanization in remnant forest patches

Yang,

Wang,

Pan

et al. 2023

Ecology and Evolution

View full text Add to dashboard Cite

Exploring the alterations in functional traits of urban remnant vegetation offers a more comprehensive perspective on plant assembly within the context of urbanization. While plant functional traits are influenced by both environmental gradients and the evolutionary history of plant species, the specific mechanisms by which urbanization mediates the combination of functional traits and the evolutionary history of remnant vegetation remain unclear. To examine the relationship between functional traits and phylogenies of remnant vegetation and urbanization, we classified the woody plant species surveyed in 72 sample plots in nine remnant forest patches in Guiyang, China, into four groups (urban, rural, middle and general groups) according to their location under different levels of urbanization and measured nine functional traits of these species. The phylogenetic signals of each functional trait of the four species groups were then quantified based on Blomberg's K. Furthermore, we analysed the correlations between functional traits and species abundance using phylogenetic generalized least squares. The results showed that significant phylogenetic signals were detected in more functional traits of the urban group than other groups. Thirteen and three significant relationships between functional traits and species abundance were detected for tree and shrub species after removing phylogenies. Tall tree species were more abundant in the urban group, while the general group favoured the species with adaptable traits (low height and high leaf area and C/N). Overall, we demonstrate that urbanization drove shifts in plant functional traits in remnant forests after combining the phylogenetic patterns.

show abstract

GLC_FCS30: Global land-cover product with fine classification system at 30 m using time-series Landsat imagery

Cited by 30 publications

References 54 publications

30 m annual land cover and its dynamics in China from 1990 to 2019

30 m annual land cover and its dynamics in China from 1990 to 2019

A spatiotemporal ensemble machine learning framework for generating land use / land cover time-series maps for Europe (2000 – 2019) based on LUCAS, CORINE and GLAD Landsat

Woody plant functional traits and phylogenetic signals correlate with urbanization in remnant forest patches

Contact Info

Product

Resources

About