Mapping vegetated wetlands of Alaska using L-band radar satellite imagery

Whitcomb, J.; Moghaddam, Mahta; McDonald, K. C.; Kellndorfer, Josef; Podest, E.

doi:10.5589/m08-080

Cited by 106 publications

(94 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the original [26] classification in Alaska and subsequent work demonstrated that the technique was capable of providing highly accurate (∼90%) maps of wetland type and represented a significant improvement over existing mapping in the area, the approach had a number of limitations that needed to be addressed. One major problem was that the method necessitated breaking the mosaic into sixteen tiles.…”

Section: Introductionmentioning

confidence: 99%

“…A particular advantage of random forests over other machine learning algorithms, such as support vector machines (SVM), is that it only requires a small number of tuning parameters [25] and is computationally efficient. Random forests was applied by Whitcomb et al [26] to data from the Japanese Earth Resources Satellite (JERS-1) and ancillary layers to derive a map of wetlands in Alaska and was found to produce maps with a higher accuracy than applying unsupervised (ISODATA) and supervised (maximum likelihood) algorithms. Following from the successful application of random forests to map wetlands from JERS-1 data and ancillary data [26], subsequent studies focused on applying the same method to data from the Phased-Array L-band SAR (PALSAR) carried onboard the Advanced Land Orbiting Satellite (ALOS) [27] and expanding the technique to also include wetlands in Canada [28].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of ALOS PALSAR Data for High-Resolution Mapping of Vegetated Wetlands in Alaska

et al. 2015

Self Cite

View full text Add to dashboard Cite

As the largest natural source of methane, wetlands play an important role in the carbon cycle. High-resolution maps of wetland type and extent are required to quantify wetland responses to climate change. Mapping northern wetlands is particularly important because of a disproportionate increase in temperatures at higher latitudes. Synthetic aperture radar data from a spaceborne platform can be used to map wetland types and dynamics over large areas. Following from earlier work by using Japanese Earth Resources Satellite (JERS-1) data, we applied the "random forests" classification algorithm to variables from L-band ALOS PALSAR data for 2007, topographic data (e.g., slope, elevation) and locational information (latitude, longitude) to derive a map of vegetated wetlands in Alaska, with a spatial resolution of 50 m. We used the National Wetlands Inventory and National Land Cover Database (for upland areas) to select training and validation data and further validated classification results with an independent dataset that we created. A number of improvements were made to the method of Whitcomb et al. (2009): (1) more consistent training data in upland areas; (2) better distribution of training data across Remote Sens. 2015, 7 7273 all classes by taking a stratified random sample of all available training pixels; and (3) a more efficient implementation, which allowed classification of the entire state as a single entity (rather than in separate tiles), which eliminated discontinuities at tile boundaries. The overall accuracy for discriminating wetland from upland was 95%, and the accuracy at the level of wetland classes was 85%. The total area of wetlands mapped was 0.59 million km 2 , or 36% of the total land area of the state of Alaska. The map will be made available to download from NASA's wetland monitoring website.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of ALOS PALSAR Data for High-Resolution Mapping of Vegetated Wetlands in Alaska

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wetland types (1-km resolution) were listed by Whitcomb et al [19] as combinations of estuarine (tidal inlet), lacustrine (lakes), or palustrine (bogs and fens) with scrub/shrub, emergent, or moss/lichen vegetation cover. Permafrost types for Alaska were mapped originally by Ferrians [23] and regridded to 8-km spatial resolution for this analysis.…”

Section: Methods and Data Sets Usedmentioning

confidence: 99%

“…Vegetation cover classes from 2009 MODIS imagery (1-km resolution; Friedl et al 2002 [22]) and the wetland map developed from satellite radar by Whitcomb et al [19] were added to the EVI trend analysis (Figure 2). Wetland types (1-km resolution) were listed by Whitcomb et al [19] as combinations of estuarine (tidal inlet), lacustrine (lakes), or palustrine (bogs and fens) with scrub/shrub, emergent, or moss/lichen vegetation cover.…”

Section: Methods and Data Sets Usedmentioning

confidence: 99%

“…According to MODIS 1-km land cover mapping (Figure 2), this Alaskan arctic region is predominantly (99%) open tundra cover, 0.1% evergreen (coniferous) forest cover, and 0.7% barren land cover. Wetlands, as identified by Whitcomb et al [19], covered 28% (89,180 km 2 ) of the region, located mainly on the coastal plain, with 82% of these ecosystems classified as herbaceous and 18% as shrub covered wetlands across the region (Figure 2). About 85% of the region was located on continuous permafrost.…”

Section: Study Regionmentioning

confidence: 99%

See 1 more Smart Citation

Regional Analysis of NASA Satellite Greenness Trends for Ecosystems of Arctic Alaska

Potter¹

2014

IJG

View full text Add to dashboard Cite

Trends in the growing season MODerate resolution Imaging Spectroradiometer (MODIS) Enhanced Vegetation Index (EVI) time-series were analyzed for the period from 2000 to 2010 to understand landscape-level patterns of vegetation change in ecosystems of arctic Alaska. We compared datasets for vegetation cover types, wetland cover classes, wildfire boundaries since the 1940s, permafrost type, and elevation to identify the most likely combination of factors driving regional changes in habitat quality and ecosystem productivity. Approximately 57% of all arctic ecosystem areas in Alaska were detected with significant (p < 0.05) positive or negative MODIS growing season EVI trends from 2000 to 2010. Nearly all (99%) of these ecosystem areas (covering 178,050 km 2 ) were detected with significant positive growing season EVI trends. The vast majority of the arctic Alaska region detected with significant positive growing season EVI trends was classified as upland tundra cover, although non-forested wetlands (marshes, bogs, fens, and floodplains) were co-located on 8% of that area. Herbaceous wetlands were co-located on 55% of the total area detected with significant negative growing season EVI trends, mostly on the arctic coastal plain and foothills. This evidence supports the hypothesis that temperature (warming) has markedly enhanced the rates of upland tundra vegetation growth across most of arctic Alaska over recent years.

show abstract

Historical and projected trends in landscape drivers affecting carbon dynamics in Alaska

Pastick

Duffy²,

Genet

et al. 2017

Ecological Applications

View full text Add to dashboard Cite

Modern climate change in Alaska has resulted in widespread thawing of permafrost, increased fire activity, and extensive changes in vegetation characteristics that have significant consequences for socioecological systems. Despite observations of the heightened sensitivity of these systems to change, there has not been a comprehensive assessment of factors that drive ecosystem changes throughout Alaska. Here we present research that improves our understanding of the main drivers of the spatiotemporal patterns of carbon dynamics using in situ observations, remote sensing data, and an array of modeling techniques. In the last 60 yr, Alaska has seen a large increase in mean annual air temperature (1.7°C), with the greatest warming occurring over winter and spring. Warming trends are projected to continue throughout the 21st century and will likely result in landscape-level changes to ecosystem structure and function. Wetlands, mainly bogs and fens, which are currently estimated to cover 12.5% of the landscape, strongly influence exchange of methane between Alaska's ecosystems and the atmosphere and are expected to be affected by thawing permafrost and shifts in hydrology. Simulations suggest the current proportion of near-surface (within 1 m) and deep (within 5 m) permafrost extent will be reduced by 9-74% and 33-55% by the end of the 21st century, respectively. Since 2000, an average of 678 595 ha/yr was burned, more than twice the annual average during 1950-1999. The largest increase in fire activity is projected for the boreal forest, which could result in a reduction in late-successional spruce forest (8-44%) and an increase in early-successional deciduous forest (25-113%) that would mediate future fire activity and weaken permafrost stability in the region. Climate warming will also affect vegetation communities across arctic regions, where the coverage of deciduous forest could increase (223-620%), shrub tundra may increase (4-21%), and graminoid tundra might decrease (10-24%). This study sheds light on the sensitivity of Alaska's ecosystems to change that has the potential to significantly affect local and regional carbon balance, but more research is needed to improve estimates of land-surface and subsurface properties, and to better account for ecosystem dynamics affected by a myriad of biophysical factors and interactions.

show abstract

Mapping vegetated wetlands of Alaska using L-band radar satellite imagery

Cited by 106 publications

References 48 publications

Evaluation of ALOS PALSAR Data for High-Resolution Mapping of Vegetated Wetlands in Alaska

Evaluation of ALOS PALSAR Data for High-Resolution Mapping of Vegetated Wetlands in Alaska

Regional Analysis of NASA Satellite Greenness Trends for Ecosystems of Arctic Alaska

Historical and projected trends in landscape drivers affecting carbon dynamics in Alaska

Contact Info

Product

Resources

About