A data-driven crop model for biomass sorghum growth process simulation.

Area of Science:

• Agricultural Science
• Plant Physiology
• Computational Biology

Background:

• Accurate crop yield prediction is vital for resource management, especially in variable climates.
• Biomass sorghum growth simulation requires models that account for complex genotype-environment-management interactions.

Purpose of the Study:

• To develop a novel data-driven crop model for simulating phenotypic changes in biomass sorghum.
• To improve the accuracy of biomass sorghum growth and yield predictions.
• To disentangle the effects of environmental and management factors on crop development.

Main Methods:

• Integration of a detailed physiological sorghum development framework.
• Application of data-driven techniques for genotypic parameter calibration using experimental data.
• Simulation of phenotypic changes influenced by genotype, environment, and management.

Main Results:

• The model accurately predicts biomass production in sorghum.
• The model successfully differentiates the impacts of environmental and management factors on phenotype.
• Effective model calibration was achieved even with limited experimental data.

Conclusions:

• The developed model enhances the accuracy and applicability of biomass sorghum prediction.
• The model provides valuable insights for optimizing precision agriculture strategies.
• This approach offers a robust method for simulating crop growth under varying conditions.