Publications

Wang, Hang; Zhu, Yan; Li, Wenlong; Cao, Weixing; Tian, Yongchao (2014). Integrating remotely sensed leaf area index and leaf nitrogen accumulation with RiceGrow model based on particle swarm optimization algorithm for rice grain yield assessment. JOURNAL OF APPLIED REMOTE SENSING, 8, 83674.

Abstract
A regional rice (Oryza sativa) grain yield prediction technique was proposed by integration of ground-based and spaceborne remote sensing (RS) data with the rice growth model (RiceGrow) through a new particle swarm optimization (PSO) algorithm. Based on an initialization/parameterization strategy (calibration), two agronomic indicators, leaf area index (LAI) and leaf nitrogen accumulation (LNA) remotely sensed by field spectra and satellite images, were combined to serve as an external assimilation parameter and integrated with the RiceGrow model for inversion of three model management parameters, including sowing date, sowing rate, and nitrogen rate. Rice grain yield was then predicted by inputting these optimized parameters into the reinitialized model. PSO was used for the parameterization and regionalization of the integrated model and compared with the shuffled complex evolution-University of Arizona (SCE-UA) optimization algorithm. The test results showed that LAI together with LNA as the integrated parameter performed better than each alone for crop model parameter initialization. PSO also performed better than SCE-UA in terms of running efficiency and assimilation results, indicating that PSO is a reliable optimization method for assimilating RS information and the crop growth model. The integrated model also had improved precision for predicting rice grain yield. (C) The Authors.

DOI:
10.1117/1.JRS.8.083674

ISSN:
1931-3195