•  
  •  
 

Turkish Journal of Agriculture and Forestry

Abstract

To address the shortcomings of conventional agricultural statistical and monitoring methods on a regional scale, this paper proposes the use of artificial intelligence-driven remote sensing data for analysing crop growth patterns and the economic benefits of grain. Winter wheat data from three stations in a single province from 2011 to 2020 was used, with the leaf area index (LAI) used as the key crop growth indicator value. The simulated annealing algorithm was used to assimilate the LAI and remote sensing leaf area index (MODIS-LAI), simulated by the World Food Study (WOFOST) simulation model, to carry out simulation analysis of winter wheat. The R2 between the simulated and measured values was above 0.70 for 10-year seedling, flowering, and mature stages, and a series of indicators were used to evaluate the effectiveness of the model simulation. The root mean square error (RMSE) suggests a better performance of the simulated seedling stage than the flowering and mature stages, and the difference between the measured and simulated winter wheat yields at the three stations from 2011 to 2020 is relatively small. The simulation results of the model can be further used for the analysis and application of assimilating MODIS-LAI for yield estimation, improving the accuracy of yield prediction of the model.

Author ORCID Identifier

YANG WANG: 0009-0004-8609-7890

DOI

10.55730/1300-011X.3340

Keywords

Crop model, remote sensing, winter wheat, data assimilation, production forecast

First Page

137

Last Page

151

Publisher

The Scientific and Technological Research Council of Türkiye (TÜBİTAK)

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS