On Wednesday, March 22, from 12:00–1:00 pm please join us for the next Spatial Technology Lunch in Phelps Hall room 3512. This semi-regular series, hosted by spatial@ucsb, aims to promote discussion and interaction within the university’s spatial technology community. Please RSVP to Kitty Currier (kcurrier@spatial.ucsb.edu) by Tuesday, March 21. Pizza and drinks will be provided.

 

Classifying California plant species throughout the drought using airborne hyperspectral imagery

Susan Meerdink

Classified aerial image

Abstract: Accurate knowledge of plant species seasonal and inter-annual distributions are required for many research and management agendas that track ecosystem health. Airborne imaging spectroscopy data have been successfully used to map species, but often only in a single season due to data availability. During California’s severe drought, NASA’s Hyperspectral Infrared Imager (HyspIRI) preparatory airborne campaign flew a visible near infrared/shortwave infrared (VSWIR) imaging spectrometer and a thermal infrared (TIR) multi-spectral imager providing the opportunity to improve species discrimination over a broader temporal range. Imagery was acquired in the spring, summer, and fall of 2013–2014 spanning from Santa Barbara to Bakersfield, CA. Overall classification was fairly uniform between seasons with accuracies ranging from 84–93%. However, individual species classification varied much more between dates with accuracies ranging from 10–78%. These results show that while overall image classification across seasons is accurate, classification performance may not be sufficient for applications that focus on a specific species of interest. This research contributes to efforts aimed at monitoring ecosystems across large spatial and temporal scales and ultimately supports many research agendas that are tracking ecosystem health and changes.

Susan Meerdink is a Ph.D. Candidate in the UCSB Visualization & Image Processing for Environmental Research (VIPER) lab. She studies the ability to map plant species across seasons in the dynamic and diverse Southern California Mediterranean ecosystem. She uses various technologies to study plant health across environmental gradients and physiology’s effect on optical properties of plant species. Her research leverages a number of tools including novel quantitative methods, land surface temperature, and spectroscopy in the optical and thermal domain.