Investigation of the Wheat Production Dynamics Under Climate Change via Machine Learning Models

This study employs two distinct machine learning (ML) methodologies to investigate the impact of 12 different key climatic variables on wheat production efficiency, a crucial component of the global and Turkish agricultural economy. Neural network (NN) and eXtreme Gradient Boosting (XGBoost) algorithms are utilised to model wheat production performance using climate variable data, including greenhouse gases, from 1990 to 2024. The models incorporate a total of 21 different independent variables, comprising 9 climatic variables (daytime and nighttime total 18 variables) and 3 distinct greenhouse gas variables, considering day and night values separately. Wheat production efficiency analyses indicate that between 2005 and 2024, Turkey’s wheat cultivation area decreased, while production efficiency increased. ML analyses reveal that greenhouse gases are the most influential variables in wheat production. XGBoost identified four different variables associated with wheat production, whereas the neural network determined that five different variables affect wheat production. While the influence of greenhouse gases was observed in both ML models, it was concluded that nighttime humidity, daytime 10 m v-wind, and daytime 2 m temperature may be additional climatic factors that will impact wheat production in the future. This study elucidates the complex relationship between climate change and wheat production in Turkey. The findings emphasise the importance of the potential for predicting wheat yields with the dual influence of climatic factors and informing agricultural producers about such next-generation practices.