Integrating Locally-Weighted Meta-Regression and Machine Learning to Capture Spatial Complexity in Multi-Scale Benefit Transfers

The USDA spends more than $5 billion per year on conservation to enhance environmental quality, ecosystem services and agricultural sustainability. The biophysical impacts of these programs (e.g., on soil retention and water quality) are relatively well understood and can be estimated using standard modeling approaches. Yet the economic benefits of these programs remain unknown, and credible information on non-market benefits is particularly lacking. Despite “a rich literature on valuation of non-market goods, the methods are often difficult or impractical to use. Large-scale, applied valuation of this type almost universally requires benefit transfer (BT); yet BT methods to support reliable large-scale valuation are inadequately developed, particularly for applications such as resource conservation and water quality improvements with widespread, diffuse impacts. USDA and its partners hence struggle to produce credible estimates of non-market conservation benefits. Addressing this major gap, this project will develop standardized BT procedures designed to support valid and reliable BTs for spatially heterogeneous, large-scale environmental changes due to resource conservation.