<![CDATA[The main objective of this research is to implement the Linear Regression computational algorithm to predict crop yields more accurately. The research method includes collecting and analyzing historical data from 10 agricultural samples that include these variables. This data is then used to train a prediction model. The model evaluation used the Mean Squared Error (MSE) and R² score metrics to assess prediction accuracy. The research results show that the Linear Regression model can provide accurate predictions, with prediction results on new data reaching 479.5 kg/ha. Data visualization revealed a significant relationship between environmental variables and crop yields, which supports the validity of the model constructed. The conclusions of this research confirm that implementing computational algorithms can be an effective tool to help farmers make more informed decisions regarding planting times and land management strategies. This not only increases agricultural efficiency and productivity but also helps in reducing uncertainty in crop yields. The implementation of technology using the linear regression algorithm is expected to make a significant contribution to more sustainable and efficient agricultural practices, as well as support increased crop yields in the future.]]>
Copyrights © 2024
