TimeSpec4LULC: a global multispectral time series database for training LULC mapping models with machine learning
-
Published:2022-03-30
Issue:3
Volume:14
Page:1377-1411
-
ISSN:1866-3516
-
Container-title:Earth System Science Data
-
language:en
-
Short-container-title:Earth Syst. Sci. Data
Author:
Khaldi Rohaifa,Alcaraz-Segura Domingo,Guirado Emilio,Benhammou Yassir,El Afia Abdellatif,Herrera Francisco,Tabik Siham
Abstract
Abstract. Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet.
This paper presents TimeSpec4LULC (https://doi.org/10.5281/zenodo.5913554; Khaldi et al., 2022), a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500 m resolution, from 2000 to 2021, and was annotated using spatial–temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE).
The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial–temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8 d temporal granularity into monthly composites; (3) merging Terra + Aqua data into a combined time series; and (4) extracting, at the pixel level, 6 076 531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial–temporal consistency across LULC products, temporal data availability, and the global human modification index.
A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe.
To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery.
This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping.
Funder
Universidad de Granada LifeWatch – Niclas Öberg Foundation Ministerio de Ciencia e Innovación Consejería de Economía, Conocimiento, Empresas y Universidad, Junta de Andalucía European Commission European Social Fund European Research Council
Publisher
Copernicus GmbH
Subject
General Earth and Planetary Sciences
Reference93 articles.
1. Alexakis, D. D., Grillakis, M. G., Koutroulis, A. G., Agapiou, A., Themistocleous, K., Tsanis, I. K., Michaelides, S., Pashiardis, S., Demetriou, C., Aristeidou, K., Retalis, A., Tymvios, F., and Hadjimitsis, D. G.: GIS and remote sensing techniques for the assessment of land use change impact on flood hydrology: the case study of Yialias basin in Cyprus, Nat. Hazards Earth Syst. Sci., 14, 413–426, https://doi.org/10.5194/nhess-14-413-2014, 2014. a 2. Aqu: MYD09A1,
https://developers.google.com/earth-engine/datasets/catalog/MODIS_006_MYD09A1?hl=en,
last access: 10 January 2022. a 3. Arino, O., Bicheron, P., Achard, F., Latham, J., Witt, R., and Weber, J.-L.:
The most detailed portrait of Earth, Eur. Space Agency, 136, 25–31, 2008. a 4. Bartholome, E. and Belward, A. S.: GLC2000: a new approach to global land cover
mapping from Earth observation data, Int. J. Remote Sens.,
26, 1959–1977, 2005. a 5. Bojinski, S., Verstraete, M., Peterson, T. C., Richter, C., Simmons, A., and
Zemp, M.: The concept of essential climate variables in support of climate
research, applications, and policy, B. Am. Meteorol.
Soc., 95, 1431–1443, 2014. a
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|