Skip to main content Skip to secondary navigation
Lauren Gillespie
Main content start
Ph.D. Student

Lauren Gillespie

Ph.D. Student in Computer Science, admitted Autumn 2019

TomKat Graduate Fellow for Translational Research

Research Lab: Moises Exposito-Alonso

Year Awarded: 2021

Lauren is co-advised by Prof. Moisés Expósito-Alonso, a Principal Investigator in the Department of Plant Biology at the Carnegie Institution for Science and co-affiliated with Stanford's Department of Biology, and Prof. Noah Goodman from Stanford CS and Psychology. Lauren enjoys splitting her time between MoiLab and CoCoLab, and can also be occasionally found hanging around Stanford's NLP Group as well.

All her life, Lauren has been fascinated by the natural world and the plethora of amazing species and ecosystems that have evolved here. She has personally witnessed the devastating effects of anthropogenic climate change. From massive in scale, like Hurricane Harvey which decimated her home state of Texas in 2017, to the minuscule, such as watching tree after tree in her neighborhood succumb to the invasive fungus oak wilt, the dizzyingly fast rate of anthropogenic climate change is a clear and present danger.

The aim of her work is to increase understanding of global change ecology using state-of-the-art machine learning. Broadly speaking, her research touches on research topics spanning machine learning, global ecology, genomics, population genetics, and remote sensing.

Specifically, she aims to:

  1. Better quantify biodiversity loss and ecosystem change at a variety of spatial and temporal scales
  2. Start to understand the specific causal mechanisms behind loss of biodiversity across the tree of life
  3. Ultimately develop informed, precision strategies for mitigating this loss and adapting our ecosystems to a warmer and drier climate future.

Website 

Google Scholar Page

Monitoring the Sustainability and Resilience of California’s Ecosystems From Space

Lauren’s research focuses on fine-scaled quantification of Earth’s most ancient, widespread, and sustainable energy source: its natural ecosystems. The objective of her project is to map the photosynthetic resilience of California’s terrestrial ecosystems at meter-level resolution directly from satellite imagery utilizing deep neural networks. Such maps will enable fine-grained quantification of the photosynthetic ecosystem services  California’s ecosystems provide, while also detecting ecosystems vulnerable to climate change and the causal factors underlying ecosystem decline in California over the past decade. Long-term, her proposed pipeline has the capability to be rapidly scaled to a continental, and potentially global scale through its use of cheap, publicly available satellite imagery and open source citizen science observation data. The resulting maps will enable decision makers, policy analysts, and conservationists to make precision decisions on what areas to prioritize for conservation and how to harden ecosystems to future climate shifts in order to protect our most sustainable yet threatened energy source from the effects of global climate change.