National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier

Decision tree classifiers have received much recent attention, particularly with regards to land cover classifications at continental to global scales. Despite their many benefits and general flexibility, the use of decision trees with high spatial resolution data has not yet been fully explored. In support of the National Park Service (NPS) Vegetation Mapping Program (VMP), we have examined the feasibility of using a commercially available decision tree classifier with multitemporal satellite data from the Enhanced Thematic Mapper-Plus (ETM+) instrument to map 11 land cover types at the Delaware Water Gap National Recreation Area near Milford, PA. Ensemble techniques such as boosting and consensus filtering of the training data were used to improve both the quality of the input training data as well as the final products.Using land cover classes as specified by the National Vegetation Classification Standard at the Formation level, the final land cover map has an overall accuracy of 82% (κ=0.80) when tested against a validation data set acquired on the ground (n=195). This same accuracy is 99.5% when considering only forest vs. nonforest classes. Usage of ETM+ scenes acquired at multiple dates improves the accuracy over the use of a single date, particularly for the different forest types. These results demonstrate the potential applicability and usability of such an approach to the entire National Park system, and to high spatial resolution land cover and forest mapping applications in general.     

Mapping vegetation in Yellowstone National Park using spectral feature analysis of AVIRIS data

Knowledge of the distribution of vegetation on the landscape can be used to investigate ecosystem functioning. The sizes and movements of animal populations can be linked to resources provided by different plant species. This paper demonstrates the application of imaging spectroscopy to the study of vegetation in Yellowstone National Park (Yellowstone) using spectral feature analysis of data from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). AVIRIS data, acquired on August 7, 1996, were calibrated to surface reflectance using a radiative transfer model and field reflectance measurements of a ground calibration site. A spectral library of canopy reflectance signatures was created by averaging pixels of the calibrated AVIRIS data over areas of known forest and nonforest vegetation cover types in Yellowstone. Using continuum removal and least squares fitting algorithms in the US Geological Survey's Tetracorder expert system, the distributions of these vegetation types were determined by comparing the absorption features of vegetation in the spectral library with the spectra from the AVIRIS data. The 0.68 μm chlorophyll absorption feature and leaf water absorption features, centered near 0.98 and 1.20 μm, were analyzed. Nonforest cover types of sagebrush, grasslands, willows, sedges, and other wetland vegetation were mapped in the Lamar Valley of Yellowstone. Conifer cover types of lodgepole pine, whitebark pine, Douglas fir, and mixed Engelmann spruce/subalpine fir forests were spectrally discriminated and their distributions mapped in the AVIRIS images. In the Mount Washburn area of Yellowstone, a comparison of the AVIRIS map of forest cover types to a map derived from air photos resulted in an overall agreement of 74.1% (kappa statistic=0.62).     

Integration of Palmer Drought Severity Index and remote sensing data to simulate wetland water surface from 1910 to 2009 in Cottonwood Lake area, North Dakota

Spatiotemporal variations of wetland water in the Prairie Pothole Region are controlled by many factors; two of them are temperature and precipitation that form the basis of the Palmer Drought Severity Index (PDSI). Taking the 196 km² Cottonwood Lake area in North Dakota as our pilot study site, we integrated PDSI, Landsat images, and aerial photography records to simulate monthly water surface. First, we developed a new Wetland Water Area Index (WWAI) from PDSI to predict water surface area. Second, we developed a water allocation model to simulate the spatial distribution of water bodies at a resolution of 30 m. Third, we used an additional procedure to model the small wetlands (less than 0.8 ha) that could not be detected by Landsat. Our results showed that i) WWAI was highly correlated with water area with an R² of 0.90, resulting in a simple regression prediction of monthly water area to capture the intra- and inter-annual water change from 1910 to 2009; ii) the spatial distribution of water bodies modeled from our approach agreed well with the water locations visually identified from the aerial photography records; and iii) the R² between our modeled water bodies (including both large and small wetlands) and those from aerial photography records could be up to 0.83 with a mean average error of 0.64 km² within the study area where the modeled wetland water areas ranged from about 2 to 14 km². These results indicate that our approach holds great potential to simulate major changes in wetland water surface for ecosystem service; however, our products could capture neither the short-term water change caused by intensive rainstorm events nor the wetland change caused by human activities.