Artificial intelligence in agriculture uses technology to improve crop growth and enhance predictions about harvests as well as resource distribution. The research uses multiple regression models to execute artificial intelligence-driven predictions of lettuce plant growth. The analysis of growth patterns used several data-driven approaches which included Linear Regression together with Decision Tree and K-Nearest Neighbors (KNN), Random Forest, and XGBoost methods. The Decision Tree model provided superior performance according to performance evaluation metrics where MSE scored 0.173, RMSE reached 0.417 and MAE amounted to 0.028, and R2-score equaled 0.999. The results indicated that Linear Regression provided the minimum performance with 170.176 MSE and 0.005 R2-score. XGBoost performed almost as well as Random Forest with a R2-score of 0.931 while still showing strong accuracy rates. The study demonstrates that AI models have strong potential in precision agriculture through Decision Tree-based prediction which delivers improved results for predicting lettuce yield to enable advanced farming methods and sustainable food systems.