Enhancing Pear Tree Yield Estimation Accuracy by Assimilating LAI and SM into the WOFOST Model Based on Satellite Remote Sensing Data

Agriculture, Journal Year: 2025, Volume and Issue: 15(5), P. 464 - 464

Published: Feb. 21, 2025

In modern agriculture, timely and accurate crop yield information is crucial for optimising agricultural production management resource allocation. This study focused on improving the prediction accuracy of pear yields. Taking Alar City, Xinjiang, China as research area, a variety data including leaf area index (LAI), soil moisture (SM) remote sensing were collected, covering four key periods growth. Three advanced algorithms, Partial Least Squares Regression (PLSR), Support Vector (SVR) Random Forest (RF), used to construct regression models LAI vegetation in using Sentinel-2 satellite data. The results showed that RF algorithm provided best when inverting LAI. coefficients determination (R2) 0.73, 0.72, 0.76, 0.77 periods, respectively, root-mean-square errors (RMSE) 0.21 m2/m2, 0.24 0.18 0.16 respectively. Therefore, was selected preferred method inversion this study. Subsequently, further explored potential assimilation techniques enhancing simulation. SM incorporated into World Food Studies (WOFOST) growth model by namely, Four-Dimensional Variational Approach (4D-Var), Particle Swarm Optimisation (PSO) algorithm, Ensemble Kalman Filter (EnKF), (PF) separate joint assimilation, experimental assimilated significantly improved compared unassimilated model. particular, EnKF highest estimation with R2 0.82, 0.79 RMSE 1056 kg/ha 1385 alone assimilated, whereas 4D-Var performed jointly high 0.88, reduced 923 kg/ha. addition, it found assimilating outperformed one variable, enhanced predictive performance beyond variable alone. summary, present demonstrated great provide strong support effectively integrating through assimilation.

Language: Английский

Development of an ecohydrological model for coupled simulation of water and carbon fluxes, crop growth, and canopy spectra over croplands

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 235, P. 110336 - 110336

Published: April 6, 2025

Language: Английский