Crop growth models are essential tools in agricultural system science, addressing complex agricultural challenges such as climate change, resource depletion, and soil degradation. Over the past six decades, many crop growth models have been developed and applied to simulate agricultural production systems and forecast crop yields under various environmental and cropping management conditions. These models can account for how abiotic stress affects crops, helping researchers understand how plants respond to stresses like nutrient, temperature, and water variations. They are often used to optimize cropping management plans for factors such as fertilizer application, irrigation, planting dates, and harvesting schedules. Crop resource use efficiency is influenced by environmental factors, including climate, soil, and farming practices. Therefore, models are suitable tools for evaluating the impacts of abiotic stress on crop growth and resource (e.g., water, fertilizer) use efficiency.

To enhance model accuracy, many scientists have started using a multi-modelling system that integrates machine learning models with crop growth models. Machine learning models can be developed using real-time data from IoT sensors or satellite data. By combining machine learning with crop growth models, researchers can expand the simulation sites from the field scale to a regional scale and improve the parameterization of crop models or detect yield changes under extreme weather conditions. However, this approach is relatively new and not yet fully developed. Integrating machine learning with crop models can enhance the accuracy of model results in estimating how abiotic stress affects crop yields in diverse environmental conditions.

The goal of this research topic is to utilize advanced crop models, such as multi-modelling systems, to estimate the impacts of abiotic stress on crop yields and resource use efficiency. This involves leveraging recent advances in integrating machine learning models with crop growth models to improve the accuracy of predictions and broaden the scale of simulations.

In this Research Topic, we welcome all article types published by Frontiers in Plant Science that focus on:

• Integration of machine learning and crop models for increased accuracy

• Effective cropping management planning through resource use efficiency estimation

• Estimation of environmental changes on soil and water due to abiotic stress

• Simulations of crops, including horticultural crops, in open-field and greenhouse environments

Are you interested in contributing a manuscript to this Research Topic?

Modelling Environmental and Crop Production Systems: Evaluating Impacts of Abiotic Stress on Crop Growth and Resource Use Efficiency