Estimation of Climate Change Parameters for Agricultural Economy Efficiency with Machine Learning Methods

Climate change threatens economies worldwide by disrupting food and water supplies, necessitating complex statistical models to forecast crop yields. Turkey, heavily reliant on agriculture, requires economic analyses of the intricate links between climate variability and resource availability to mitigate climate change impacts through effective policies. Recent predictive modeling incorporating meteorological data demonstrates the feasibility of anticipating monthly precipitation in Türkiye. The study demonstrates the effectiveness of using monthly relative humidity and average temperature data from 1970 to 2021 for precise precipitation predictions by applying artificial neural networks. The study's conclusions have important ramifications for raising agricultural output. Accurate monthly precipitation estimates enable stakeholders to make well-informed decisions on the development of grain crops, improving agricultural practices and raising sector productivity overall.