Institution: Iowa State University
Title: Integration of Survey Data and Big Data to Improve Agricultural Statistics
Date: May 1, 2018
Location: C405 Wells Hall
Time: 10:20 AM - 11:10 AM
Combining information from different sources is an important practical problem in survey sampling. In agricultural statistics, satellite remote sensing data and administrative data are often available and can be used together with survey data to provide more timely estimates or estimates at smaller spatial scales. In this talk we share our experience using machine learning algorithms to derive useful auxiliary information from satellite data, and introduce a hierarchical area-level model framework to integrate auxiliary information to improve small and large area estimation. A case study of planted acreage estimation for various commodity crops using data from NASS June Area Survey, a commodity-specific classification product derived from satellite data, and administrative data from FSA will be presented for illustration.