Development of large-scale crop phenological characterization framework with satellite time series

Keywords: Remote Sensing, Time series, Optical imaging, Phenology, Agriculture
Abstract Type: Virtual Paper Abstract

Abstract

Large-scale remote monitoring of crop phenological development is vital for scheduling farm management activities and estimating crop yields. Tracking crop phenological progress is also crucial to understand agricultural responses to environmental stress and climate change. During the past decade, time series of remotely sensed imagery has been increasingly employed to monitor the seasonal growing dynamics of crops. Yet our ability in characterizing the critical crop phenological stages from planting to harvest using remotely sensed imagery is still limited. In this presentation, I will introduce our efforts towards developing large-scale crop phenological characterization framework for retrieving a diverse range of crop phenological stages. Specifically, the framework includes a collection of curve fitting-based phenological models, a hybrid phenology matching model, and a newly developed CropSow model. With corn and soybean in Illinois as a case study, the framework can estimate key phenological stages of crop cycles, ranging from farming practice-relevant stages (e.g., planted and harvested) to crop development stages (e.g., emerged and mature). It shows marked potential to advance phenological monitoring as well as subsequent crop mapping and yield estimation at large scales for more sustainable agricultural development.