Mapping pan-European land cover using Landsat spectral-temporal metrics and the European LUCAS survey
Introduction
Land cover is a key variable influencing the Earth's energy balance, the hydrological and carbon cycle, and the provisioning of natural resources and habitat (Bonan, 2008; Brovkin et al., 2004; Foley et al., 2005). Satellite imagery has long been used for mapping land cover from space (Townshend et al., 1991). The first systematic observations of the Earth land surface became available with the launch of Landsat-1 in 1972, which opened new opportunities for automated land cover mapping (Gordon, 1980; Landgrebe, 1976). In the 1990s and early 2000s, a number of operational land cover programs emerged based on Landsat and Landsat-like data, e.g. CORINE (Coordination of Information on the Environment) land cover in Europe (Büttner, 2014), NLCD (National Land Cover Database) in the USA (Homer et al. 2004, Jin et al., 2013, Vogelmann et al., 2001), EOSD (Earth Observation for Sustainable Development of Forests) in Canada (Wulder et al., 2008), NCAS-LCCP (National Carbon Accounting System-Land Cover Change Project) in Australia (Furby, 2002), and PRODES (Programa Despoluição de Bacias Hidrográficas) in Brazil (INPE, 2002). Over the last decades, tremendous progress has been made in developing up-to-date and accurate land cover information. The availability of high quality, ready-to-analyze medium resolution sensor data (Drusch et al., 2012; Wulder et al., 2012) and advances in IT infrastructures and cloud computing have made it possible to produce regional to global land cover maps in a relatively short period of time (Gong et al., 2013; Xiong et al., 2017).
In Europe, CORINE provides the most comprehensive and detailed maps of land cover and land use change at medium spatial resolution (Büttner, 2014). The CORINE program was established by the European Commission to create harmonized geographical information on the state of the environment in the European Community. CORINE land cover is mapped in 44 classes using a minimum mapping unit of 25 ha for areal phenomena and a minimum width of 100 m for linear phenomena. The first CORINE land cover map was created for the reference year 1990 using satellite data from 1986 to 1998. The project involved 25 countries, and it took ten years to complete. Subsequent land cover updates were produced for the years 2000, 2006, and 2012. Over the years, the product chain has evolved and production times have decreased. The most recent CORINE land cover 2012 involved 39 countries and took two years to complete. CORINE's approach builds on harmonized protocols and guidelines that are executed independently by each country. This way, countries can integrate their national efforts and inventory resources and make the best use of local expert knowledge. The disadvantage is that variable mapping approaches may be employed and that the majority of countries heavily rely on visual interpretation of high-resolution satellite imagery. Only a few countries apply semi-automatic solutions combining national in-situ data and satellite image analysis. Considering the increasing demand for consistent and up-to-date land cover information, there is a strong need to develop and test automated approaches for mapping pan-European land cover.
The increasing and free availability of ready-to-analyze medium resolution imagery has brought new opportunities for the automated mapping of land cover and land cover change over large areas (Hansen and Loveland, 2012). Traditional image-based classification approaches require cloud-free or near-cloud free imagery, and they often go along with heavy user-interaction and visual interpretation methods. Scaling image-based approaches over large areas is technically and logistically challenging, particularly in areas that have a lot of clouds. Mass-processing of Landsat and Landsat-like data has become easier with per-pixel approaches that integrate multiple (potentially all) cloud-free reflectance values for a given pixel and time period, and produce seamless mosaics across image boundaries (Roy et al., 2010).
A variety of per-pixel approaches exist that may be categorized as follows: composites based on the best pixel observation within a given time period (Griffiths et al., 2012; Hermosilla et al., 2015; Roy et al., 2010), spectral-temporal metrics based on statistical moments (Azzari and Lobell, 2017; Potapov et al., 2015), and phenological metrics derived from fitting time series functions (Schwieder et al., 2016; Zhu and Woodcock, 2014a). All these methods have advantages and disadvantages; sometimes they are used in combination. Composites select the best pixel observations for a given time period using a set of rules and optimization functions. The goal is to reduce atmospheric effects while retaining original reflectance observations. Spectral-temporal metrics do not (necessarily) yield observed reflectance. Rather they describe the spectral distribution and variance of a pixel over a year or season. Spectral-temporal metrics are a simple means to express seasonal land cover dynamics related to vegetation growth and land use, and they have been used to map land cover (Azzari and Lobell, 2017; Hansen et al., 2011), tree species (Thompson et al., 2015), and forest disturbances (Potapov et al., 2015). Time series approaches yield a detailed model of land surface phenology because they directly estimate parameters that describe the timing, shape, and periodicity of the land surface changes. In this respect, time series methods are superior to spectral-temporal composites, but they also have higher requirements regarding data density and computing power. Research is ongoing to evaluate how to scale time series methods effectively across very large areas. In this study, we build on spectral-temporal metrics to automate land cover classification across Europe.
Collecting reference data for training and validation is an essential component in land cover mapping. Ideally, a combination of photo-interpretation and field work is employed that covers the expected range of land cover and environmental conditions (Strahler et al., 2006). If reference data are used for validation, then a probability sampling design is required to ensure statistical estimates of map accuracy (Stehman, 1997). Since reference data collection takes a major effort, there is a paucity of reference datasets at the regional (country to continental) and global scale. For global scale validation, tremendous progress has been made through crowdsourcing activities (Fritz et al., 2017) and probability-based samples of high-resolution imagery (Pengra et al., 2015). These approaches fill a crucial gap, but they also have trade-offs concerning interpretation uncertainty (Foody and Boyd, 2013) and sample size (Banaszkiewicz et al., 2014). Countries that support national land cover programs often rely on photo-interpretation and field survey data (Vogelmann et al., 2001; Homer et al., 2004; Wickham et al., 2010), which are usually not publicly available.
The European Land Use/Cover Area frame Survey (LUCAS) provides a unique source of publicly available land cover survey data. LUCAS is coordinated by Eurostat, the statistical office of the European Commission, with the aim to inform decision makers and the general public about changes in management and coverage of the European territory (Martino and Fritz, 2008). LUCAS collects information on land cover and land use, agro-environmental, and soil data every three years in the European Union since 2006. The survey is conducted in two phases. In the first phase, land cover is recorded via photo-interpretation at a systematic sampling grid with points spaced 2 km apart. In the second phase, a stratified sample is visited in the field. This sample represents the largest harmonized in-situ land cover record in Europe. In 2012, the in-situ measurements involved 750 field surveyors. The main purpose of LUCAS is statistical estimation. The survey was not designed for mapping. However, the potential benefits are high, if LUCAS data can be successfully used to train modern machine learning classification algorithms. Past remote sensing studies that incorporated LUCAS data have been limited to statistical estimates (Gallego and Bamps, 2008), map validation (EEA, 2006), and semi-automated training of classification models over smaller regions (Mack et al., 2017). No study has utilized LUCAS for automated, pan-European land cover mapping.
The objective of this study was to develop a method for mapping pan-European land cover by automated classification of Landsat spectral-temporal metrics using the largest European-wide land cover survey LUCAS. We evaluate the mapping approach at the continental and regional scales and specifically address the following research questions:
- •
How does data density impact classification accuracy?
- •
How do environmental predictors improve classification accuracy?
- •
How does the automated land cover map compare to the existing CORINE product?
Section snippets
Study area
The study area covers Europe from approximately 10°W to 30°E longitude and 35°N to 71°N latitude (Fig. 1). The area is similar to the CORINE land cover dataset (2012) excluding Iceland, Turkey, Malta, and Cyprus. On the eastern boundary, we included the Kaliningrad region and the western part of Ukraine to complete the Carpathian region. Europe's climate ranges from dry-warm Mediterranean climate of the south to subarctic and tundra climates in the northeast. Western and Northwestern Europe has
Landsat data and data availability
We downloaded all orthorectified (L1T) Operational Land Imager (OLI) images acquired between January 1st 2014 and December 31st 2016 with an estimated cloud cover of <75% from the United States Geological Service (USGS). In total, we used 18,675 images across 476 WRS-2 footprints. On average, this yielded 40 images per footprint over the three-year period. The number of available images varied regionally being lowest in the northern Scandinavian peninsula (minimum = 16) and highest in the
Classification accuracy and class confusions
In this section, we present the thematic class confusion of the Full3 model (Table 5), which is based on seasonal medians and annual variance metrics calculated over three years, and auxiliary predictors. We start with the six dominant land cover classes that account together for 94% of the study area: seasonal croplands, broadleaved forests, coniferous forest, mixed forest, shrublands, and grasslands. Then, we focus on the small land cover classes: water, barren, artificial, perennial
Conclusions
This study demonstrated the potential for automated mapping of pan-European land cover by integrating machine learning, Landsat spectral-temporal metrics, and the European land cover survey LUCAS. The acquisition of ground-truth data plays a major part in the development and validation of land cover maps (Fritz et al., 2017; Olofsson et al., 2012), which highlights the unique value of the internationally coordinated, Europe-wide LUCAS survey. Although the thematic resolution of our map (12
Acknowledgements
This work was supported by the German Federal Ministry of Education and Research through the GeoMultiSens project (grant no. 01IS14010B). We used an extended version of the open source analytics engine Apache Flink to conduct our experiments. We thank the open source community of Apache Flink for supporting us in extending the system to fit our needs. We also acknowledge the helpful suggestions of the anonymous reviewers. This research contributes to the Landsat Science Team 2018-2023 (//landsat.usgs.gov/2018-2023-science-team
References (96)
- et al.
Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring
Remote Sens. Environ.
(2017) - et al.
Mapping continuous fields of tree and shrub cover across the Gran Chaco using Landsat 8 and Sentinel-1 data
Remote Sens. Environ.
(2018) - et al.
Analysis of the conflict between omission and commission in low spatial resolution dichotomic thematic products: the Pareto Boundary
Remote Sens. Environ.
(2004) - et al.
Global land cover mapping at 30m resolution: a POK-based operational approach
ISPRS J. Photogramm. Remote Sens.
(2015) A TM Tasseled Cap equivalent transformation for reflectance factor data
Remote Sens. Environ.
(1985)- et al.
Sentinel-2: ESA's optical high-resolution mission for GMES operational services
Remote Sens. Environ.
(2012) - et al.
Key issues in making and using satellite-based maps in ecology: a primer
For. Ecol. Manag.
(2006) - et al.
Global land cover mapping from MODIS: algorithms and early results
Remote Sens. Environ.
(2002) - et al.
MODIS collection 5 global land cover: algorithm refinements and characterization of new datasets
Remote Sens. Environ.
(2010) - et al.
Using CORINE land cover and the point survey LUCAS for area estimation
Int. J. Appl. Earth Obs. Geoinf.
(2008)
Utilizing LANDSAT imagery to monitor land-use change: a case study in Ohio
Remote Sens. Environ.
Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping
Remote Sens. Environ.
A review of large area monitoring of land cover change using Landsat data
Remote Sens. Environ.
An integrated Landsat time series protocol for change detection and generation of annual gap-free surface reflectance composites
Remote Sens. Environ.
A comprehensive change detection method for updating the National Land Cover Database to circa 2011
Remote Sens. Environ.
Computer-based remote sensing technology - a look to the future
Remote Sens. Environ.
A comparison of resampling methods for remote sensing classification and accuracy assessment
Remote Sens. Environ.
Predicting palustrine wetland probability using random forest machine learning and digital elevation data-derived terrain variables
Photogramm. Eng. Remote Sens.
Using prior probabilities in decision-tree classification of remotely sensed data
Remote Sens. Environ.
Making better use of accuracy data in land change studies: estimating accuracy and area and quantifying uncertainty using stratified estimation
Remote Sens. Environ.
A global reference database from very high resolution commercial satellite data and methodology for application to Landsat derived 30 m continuous field tree cover data
Remote Sens. Environ.
Comparison and assessment of coarse resolution land cover maps for Northern Eurasia
Remote Sens. Environ.
Eastern Europe's forest cover dynamics from 1985 to 2012 quantified from the full Landsat archive
Remote Sens. Environ.
Quantification of live aboveground forest biomass dynamics with Landsat time-series and field inventory data: a comparison of empirical modeling approaches
Remote Sens. Environ.
A modified soil adjusted vegetation index
Remote Sens. Environ.
Improving near-real time deforestation monitoring in tropical dry forests by combining dense Sentinel-1 time series with Landsat and ALOS-2 PALSAR-2
Remote Sens. Environ.
Web-enabled Landsat Data (WELD): Landsat ETM plus composited mosaics of the conterminous United States
Remote Sens. Environ.
Land use intensity trajectories on Amazonian pastures derived from Landsat time series
Int. J. Appl. Earth Obs. Geoinf.
Mapping Brazilian savanna vegetation gradients with Landsat time series
Int. J. Appl. Earth Obs. Geoinf.
Mapping land cover in complex Mediterranean landscapes using Landsat: improved classification accuracies from integrating multi-seasonal and synthetic imagery
Remote Sens. Environ.
Selecting and interpreting measures of thematic classification accuracy
Remote Sens. Environ.
Practical implications of design-based sampling inference for thematic map accuracy assessment
Remote Sens. Environ.
Model-assisted estimation as a unifying framework for estimating the area of land cover and land-cover change from remote sensing
Remote Sens. Environ.
Global land cover classification by remote-sensing - present capabilities and future possibilities
Remote Sens. Environ.
Red and photographic infrared linear combinations for monitoring vegetation
Remote Sens. Environ.
Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product
Remote Sens. Environ.
Thematic accuracy of the NLCD 2001 land cover for the conterminous United States
Remote Sens. Environ.
Thematic accuracy assessment of the 2011 National Land Cover Database (NLCD)
Monitoring large areas for forest change using Landsat: generalization across space, time and Landsat sensors
Remote Sens. Environ.
Opening the archive: How free data has enabled the science and monitoring promise of Landsat
Remote Sens. Environ.
Virtual constellations for global terrestrial monitoring
Remote Sens. Environ.
Automated cropland mapping of continental Africa using Google Earth Engine cloud computing
ISPRS J. Photogramm. Remote Sens.
Using the 500 m MODIS land cover product to derive a consistent continental scale 30 m Landsat land cover classification
Remote Sens. Environ.
Continuous change detection and classification of land cover using all available Landsat data
Remote Sens. Environ.
Automated cloud, cloud shadow, and snow detection in multitemporal Landsat data: An algorithm designed specifically for monitoring land cover change
Remote Sens. Environ.
Forest biomass estimation over regional scales using multisource data
Geophys. Res. Lett.
European area frame sampling based on very high resolution images
Applied Spatial Data Analysis With R
Cited by (149)
Classifying raw irregular time series (CRIT) for large area land cover mapping by adapting transformer model
2024, Science of Remote SensingConservation policy and forest transition in Zagros forests: Statistical analysis of human welfare, biophysical, and climate drivers
2024, Forest Policy and EconomicsAutomatic classification of land cover from LUCAS in-situ landscape photos using semantic segmentation and a Random Forest model
2024, Environmental Modelling and SoftwareHow do conservation policies, climate and socioeconomic changes impact Hyrcanian forests of northern Iran?
2023, Ecological InformaticsUnderstanding the robustness of spectral-temporal metrics across the global Landsat archive from 1984 to 2019 – a quantitative evaluation
2023, Remote Sensing of Environment
- 1
Currently at Senacor Technologies AG, Germany.