Modeling Phenology Combining Data Assimilation Techniques and Bioclimatic Indices in a Cabernet Sauvignon Vineyard (<i>Vitis vinifera</i> L.) in Central Chile

Abstract

Phenology is a science that is fundamental to crop productivity and is especially sensitive to environmental changes. In Mediterranean and semi-arid climates, vineyard phenology is directly affected by changes in temperature and rainfall distribution, being highly vulnerable to climate change. Due to the significant heterogeneity in soil, climate, and crop variables, we need fast and reliable ways to assess vineyard phenology in large areas. This research aims to evaluate the performance of the phenological data assimilation model (DA-PhenM) and compare it with phenological models based on meteorological data (W-PhenM) and models based on Sentinel-2 NDVI (RS-PhenM). Two W-PhenM approaches were evaluated, one assessing eco- and endo-dormancy, as proposed by Caffarra and Eccel (CaEc) and the widely used BRIN model, and another approach based on the accumulation of heat units proposed by Parker called the Grapevine Flowering Veraison model (GFV). The DA-PhenM evaluated corresponds to the integration between RS-PhenM and CaEc (EKF-CaEC) and between RS-PhenM and GFV (EKF-GFV). Results show that EKF-CaEc and EKF-GFV have lower root mean square error (RMSE) values than CaEc and GFV models. However, based on the number of parameters that models require, EKF-GFV performs better than EKF-CaEc because the latter has a higher Bayesian Index Criterion (BIC) than EKF-GFV. Thus, DA-PhenM improves the performance of both W-PhenM and RS-PhenM, which provides a novel contribution to the phenological modeling of Vitis vinifera L. cv Cabernet Sauvignon.

Keywords

• vegetation indices
• extended Kalman filter
• earth observation
• state forcing units
• dormancy