No abstract

Stream restoration is widely used to mitigate the degradation of urban stream channels, protect infrastructure, and reduce sediment and nutrient loadings to receiving waterbodies. Stabilizing and revegetating riparian areas can also provide recreational opportunities and amenities, and improve quality of life for nearby residents. In this project, we developed indices of an environmental benefit (potential nitrate load reduction, a priority in the Chesapeake Bay watershed) and economic benefit (household willingness to pay, WTP) of stream restoration for all low order stream reaches in three main watersheds in the Baltimore metro region. We found spatial asynchrony of these benefits such that their spatial patterns were negatively correlated. Stream restoration in denser urban, less wealthy neighborhoods have high WTP, but low potential nitrate load reduction, while suburban and exurban, wealthy neighborhoods have the reverse trend. The spatial asynchrony raises challenges for decision makers to balance economic efficiency, social equity, and specific environmental goals of stream restoration programs.

The accuracy in land-cover classification using remotely sensed imagery can be increased using Bayesian methods that incorporate prior probabilities of classes. However, estimating these prior probabilities can be expensive and data intensive. We propose methods to improve the classification accuracy using Bayesian methods to classify ambiguous (or low-confidence) pixels, using only the remotely sensed imagery or existing land-cover maps to estimate prior probabilities. We propose a spatial method that predicts prior probabilities from the original image, and a temporal method that incorporates land-cover maps from previous years. We illustrate our methods with a neural network (NN) classifier on the U.S. state of Iowa to classify crops into corn/soybean/other using moderate resolution imaging spectroradiometer (MODIS) data. USDA cropland data layers were aggregated to the 250-m resolution of MODIS and used as ground truth, based on a cropland mask from the National Land Cover Database. Results show that the spatial-prior-adjustment method, which predicts prior probabilities for low-confidence pixels based on class percentages of initial NN classification, increased overall accuracy of low-confidence pixels between 2% and 3.3% over the standard NN classification. The temporal-prior-adjustment method, which uses crop classes from the previous six years to estimate prior probabilities for the current year, shows significantly greater accuracy improvement for low-confidence pixels (almost 7%) over the standard NN classification. Increased benefit of the temporal-prior-adjustment method relative to the spatial-prior-adjustment method is likely due to increased information from more ground truth data (from previous years) than the spatial method.