Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Hydrology and Remote Sensing Laboratory » Research » Publications at this Location » Publication #381317

Research Project: Integrating Remote Sensing, Measurements and Modeling for Multi-Scale Assessment of Water Availability, Use, and Quality in Agroecosystems

Location: Hydrology and Remote Sensing Laboratory

Title: Hybrid phenology matching model to retrieve crop phenological stages

item DIAO, C, - University Of Illinois
item YANG, Z. - University Of Illinois
item Gao, Feng

Submitted to: Journal of Photogrammetry and Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 9/10/2021
Publication Date: 9/28/2021
Citation: Diao, C., Yang, Z., Gao, F.N. 2021. Hybrid phenology matching model to retrieve crop phenological stages . Journal of Photogrammetry and Remote Sensing. 181:308-326.

Interpretive Summary: Crop growth stages (or phenology) are essential for crop monitoring, crop modeling, and agricultural management. Remote sensing data have been used to map crop phenology for decades. The shape-based crop phenology approach can detect multiple growth stages using crop growth references and satellite observations. However, the shape-based method has a strong assumption on the shape of the timeseries vegetation index (VI), and the results depend on the reference used. This paper proposes a new hybrid model that reduces the requirements by combining the phenometric extraction and phenology matching models. Crop growth references for corn and soybean under different time-space scenarios were assessed in Illinois from 2002-2017. Results show that the new hybrid model is superior to the conventional shape-based approach and has great potential to quantify spatial variability of crop growth stages required for agricultural statistics.

Technical Abstract: Crop phenology regulates seasonal agroecosystem carbon, water, and energy exchanges, and is a key component in empirical and processbased crop models for simulating biogeochemical cycles of farmlands, assessing gross and net primary production, and forecasting the crop yield. The advances in phenology matching models (e.g., shape model fitting) provide a feasible means to monitor crop phenological progress, with a priori information of reference shapes and reference phenological transition dates. Yet the underlying geometrical scaling assumption of models, together with the challenge in defining phenological references, hinders the applicability of phenology matching in crop phenological studies. The objective of this study is to develop a novel hybrid phenology matching model to retrieve a diverse spectrum of crop phenological stages using satellite time series. The devised hybrid model leverages the complementary strengths of phenometric extraction methods and phenology matching models. It does not require the geometrical scaling assumption and can characterize 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). To systematically evaluate the influence of phenological references on phenology matching, four representative phenological reference scenarios with varying levels of phenological calibrations are further designed with publicly accessible phenological information. The results indicate that the hybrid phenology matching model can achieve high accuracies for estimating corn and soybean phenological growth stages in Illinois, particularly with the year- and region-adjusted phenological reference (R-squared higher than 0.9 and RMSE less than 5 days for most phenological stages). The inter-annual and regional phenological patterns characterized by the hybrid model correspond well with those in the crop progress reports (CPRs). Compared to the benchmark shape model fitting method, the hybrid model is more robust to the decreasing levels of phenological reference calibrations, and is particularly advantageous in retrieving crop early phenological stages (e.g., planted and emerged stages) when the phenological reference information is limited. Together with CPR-enabled phenological reference calibrations, the hybrid model holds large potential to improve the applicability of phenology matching models in revealing spatio-temporal patterns of crop phenology over extended geographical regions.