|
Activity Number:
|
395
- Statistical Models for High-Dimensional Computer Output
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
|
Abstract #329774
|
Presentation
|
|
Title:
|
Fusing Multiple Existing Space-Time Land Cover Products
|
|
Author(s):
|
Amanda Hering* and Nicolás Rodríguez-Jeangros and John McCray and Timothy Kaiser
|
|
Companies:
|
Baylor University and Colorado School of Mines and Colorado School of Mines and Colorado School of Mines
|
|
Keywords:
|
big data;
land cover product;
probabilistic assessment;
spatial-temporal categorical data
|
|
Abstract:
|
Land cover (LC) products are derived primarily from satellite spectral imagery and are essential inputs for environmental studies. However, existing LC products each have different temporal and spatial resolutions and different LC classes that rarely provide enough detail. Here, we review the complexities of LC identification and propose a method for fusing multiple existing LC products to produce a single LC record for a large spatial-temporal grid, referred to as spatiotemporal categorical map fusion (SCaMF). We first reconcile the LC classes across products and then present a probabilistic weighted nearest neighbor estimator of LC class. This estimator depends on three unknown parameters that are estimated using numerical optimization to maximize an agreement criterion that we define. We illustrate the method using six LC products over the Rocky Mountains and show the improvement gained by using data-driven information describing the spatial-temporal behavior of each LC class. Additional flexibility to adapt to local nonstationarities and to produce more detailed classes is incorporated to produce a yearly product from 1983-2012 on 30 and 50 m grids.
|
Authors who are presenting talks have a * after their name.
