NELDA
Project Summary
The Northern Eurasia Land Dynamics Analysis (NELDA) project was pursued in collaboration with scientists from Oregon State University and Russia. The purpose of the project was to synthesize information on how the Northern Eurasia landmass is changing under a warming climate and to improve climate models based on these findings. My role in the project was to produce a baseline regional land cover map for the year 2005 based on a time series of MODIS spectral data. To do so I used a very similar decision tree classifier approach to the one used to create the C5 MODIS LC product with some improvements. First of all, while I used the same STEP database to create the MODIS LC product, we added many new training sites specific to unique Northern Eurasia ecosystems and re-evaluated many of the existing sites on GoogleEarth. The second source of improvement was a hierarchical classification approach that used a set of climate-based classifications of vegetation types to enhance the quality of the spectral-based classifications. Some of the new approaches tested in this project will be used to create the Collection 6 MODIS LC product.
These pictures were taken during two trips in support of the NELDA project. The first row was from a visit to Syktyvkar, Russia in 2008 and the second row was from a trip to Tartu, Estonia in 2010.
Related Publications
Sulla-Menashe, D, MA Friedl, ON Krankina, A Baccini, CE Woodcock, A Sibley, G Sun, V Kharuk, and V Elsakov. 2011. Hierarchical mapping of northern Eurasia using MODIS data. Remote Sensing of Environment 115: 392-403.
Hierarchical structure of the NELC land cover legend. Dashed lines separate different levels of the hierarchy. The land use, wetland, and tundra layers (not shown) are complementary to the land cover hierarchy.
Abstract:
The Northern Eurasian land mass encompasses a diverse array of land cover types including tundra, boreal forest, wetlands, semi-arid steppe, and agricultural land use. Despite the well-established importance of Northern Eurasia in the global carbon and climate system, the distribution and properties of land cover in this region are not well characterized. To address this knowledge and data gap, a hierarchical mapping approach was developed that encompasses the study area for the Northern Eurasia Earth System Partnership Initiative (NEESPI). The Northern Eurasia Land Cover (NELC) database developed in this study follows the FAO-Land Cover Classification System and provides nested groupings of land cover characteristics, with separate layers for land use, wetlands, and tundra. The database implementation is substantially different from other large scale land cover datasets that provide maps based on a single set of discrete classes. By providing a database consisting of nested maps and complementary layers, the NELC database provides a flexible framework that allows users to tailor maps to suit their needs. The methods used to create the database combine empirically derived climate–vegetation relationships with results from supervised classifications based on Moderate Resolution Imaging Spectroradiometer (MODIS) data. The hierarchical approach provides an effective framework for integrating climate–vegetation relationships with remote sensing-based classifications, and also allows sources of error to be characterized and attributed to specific levels in the hierarchy. The cross-validated accuracy was 73% for the land cover map and 73% and 91% for the agriculture and wetland classifications, respectively. These results support the use of hierarchical classification and climate–vegetation relationships for mapping land cover at continental scales.
Prior probability layers derived from climate–vegetation relationships for selected classes. The range of values for each color refers to the probability of a class' presence at a specific pixel location.
Pflugmacher, D, ON Krankina, WB Cohen, MA Friedl, D Sulla-Menashe, RE Kennedy, P Nelson, TV Loboda, T Kuermmerle, E Dyukarev, V Elsakov, and VI Kharuk. 2011. Comparison and assessment ofcoarse resolution land cover maps for Northern Eurasia. Remote Sensing of Environment 115(12): 3539-3553.
Distribution of dominant life form types for Northern Eurasia based on four global land cover maps: GLC-2000, GLOBCOVER, MODIS C4 and MODIS C5.
Predicted (global map) versus reference land cover area, calculated from (a) all pixels and (b) pure pixels, in percent of total test site area for GLC-2000, GLOBCOVER, MODIS C4, and MODIS C5. Symbol shapes represent individual test sites. Symbol fill patterns and shades of gray represent individual LFT classes (tree: open light gray, shrub: filled light gray, herbaceous: open dark gray, barren: filled dark gray).
Abstract:
Information on land cover at global and continental scales is critical for addressing a range of ecological, socioeconomic and policy questions. Global land cover maps have evolved rapidly in the last decade, but efforts to evaluate map uncertainties have been limited, especially in remote areas like Northern Eurasia. Northern Eurasia comprises a particularly diverse region covering a wide range of climate zones and ecosystems: from arctic deserts, tundra, boreal forest, and wetlands, to semi-arid steppes and the deserts of Central Asia. In this study, we assessed four of the most recent global land cover datasets: GLC-2000, GLOBCOVER, and the MODIS Collection 4 and Collection 5 Land Cover Product using cross-comparison analyses and Landsat-based reference maps distributed throughout the region. A consistent comparison of these maps was challenging because of disparities in class definitions, thematic detail, and spatial resolution. We found that the choice of sampling unit significantly influenced accuracy estimates, which indicates that comparisons of reported global map accuracies might be misleading. To minimize classification ambiguities, we devised a generalized legend based on dominant life form types (LFT) (tree, shrub, and herbaceous vegetation, barren land and water). LFT served as a necessary common denominator in the analyzed map legends, but significantly decreased the thematic detail. We found significant differences in the spatial representation of LFT's between global maps with high spatial agreement (above 0.8) concentrated in the forest belt of Northern Eurasia and low agreement (below 0.5) concentrated in the northern taiga-tundra zone, and the southern dry lands. Total pixel level agreement between global maps and six test sites was moderate to fair (overall agreement:0.67–0.74, Kappa: 0.41–0.52) and increased by 0.09–0.45 when only homogenous land cover types were analyzed. Low map accuracies at our tundra test site confirmed regional disagreements and difficulties of cur-rent global maps in accurately mapping shrub and herbaceous vegetation types at the biome borders of Northern Eurasia. In comparison, tree dominated vegetation classes in the forest belt of the region were accurately mapped, but were slightly overestimated (10%-20%), in all maps. Low agreement of global maps in the northern and southern vegetation transition zones of Northern Eurasia is likely to have important implications for global change research, as those areas are vulnerable to both climate and socio-economic changes.