Evaluating Traditional and Advanced Forecasting Models for Economic Impact Prediction in Agriculture A Machine Learning Approach

Agricultural forecasting has become increasingly critical in understanding and mitigating the economic impacts of climate change on crop production. This research investigates the effectiveness of various machine learning, deep learning, and traditional time series models in predicting economic outcomes for agriculture using a comprehensive dataset that includes attributes such as country, region, crop type, average temperature, CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emissions, soil health index, and adaptation strategies. By employing a diverse array of models-namely, Linear Regression, Support Vector Regression, Decision Trees, Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbors, ARIMA, SARIMA, LSTM, and GRU-this work compares performance based on key metrics including accuracy, mean absolute error, mean squared error, root mean squared error, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, and mean absolute percentage error. Results reveal that deep learning models, particularly GRU and LSTM, demonstrate superior accuracy and error minimization capabilities, significantly outperforming traditional models like ARIMA and SARIMA. Machine learning algorithms, including Support Vector Regression and Gradient Boosting, also performed moderately well, though with varied accuracy across different crop types and regions. The analysis highlights the importance of advanced techniques in handling the non-linear and complex patterns inherent in climate and agricultural data, offering enhanced predictive power for stakeholders aiming to optimize resource allocation and adapt to climate impacts. This research underscores the value of integrating advanced machine learning and deep learning models into agricultural forecasting, providing a robust foundation for informed decision-making and resilience planning in climate-sensitive sectors.