Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology

TL;DR

This paper develops deep learning models using satellite data to accurately predict buffelgrass green-ups, aiding wildfire prevention and resource management in the southwestern US.

Contribution

It introduces neural-based models that outperform traditional methods in predicting buffelgrass phenology using multi-modal satellite data.

Findings

Neural models outperform conventional green-up prediction methods.

Deep learning approaches offer significant resource savings.

Multi-modal data enhances prediction accuracy.

Abstract

An invasive species of grass known as "buffelgrass" contributes to severe wildfires and biodiversity loss in the Southwest United States. We tackle the problem of predicting buffelgrass "green-ups" (i.e. readiness for herbicidal treatment). To make our predictions, we explore temporal, visual and multi-modal models that combine satellite sensing and deep learning. We find that all of our neural-based approaches improve over conventional buffelgrass green-up models, and discuss how neural model deployment promises significant resource savings.