Utilization of Random Forest to Support Future Corn Harvest Planning
Keywords:
Corn, Machine learning, Plant growth, Precision agriculture, Random forestAbstract
Corn is a strategic food commodity in Indonesia, with national production reaching around 22 million tons. In 2023, Lampung Province will contribute around 9% of the total. However, Lampung faces serious challenges due to climate change. This condition shows the need for further research to increase the productivity and resilience of corn farming to support national food security. Significant climate change has caused a decrease in the quality of corn crops. To overcome this problem, the application of the Random Forest algorithm is expected to increase the yield of the harvest. Random forest is one of the methods that can increase the accuracy in generating attributes for each node that is carried out randomly, with supporting variables such as moisture, temperature, soil moisture in the corn farming environment to predict future crops. By optimizing the hyperparameters, the developed RF model shows a high level of accuracy, with an R-squared (R²) value of 0.894 and a Mean Absolute Error (MAE) of 5.12. Further analysis revealed that air humidity was the most dominant factor in influencing maize growth (67.1%), followed by temperature (25.5%) and soil moisture (7.3%). In addition, the model successfully predicted plant growth with a high degree of accuracy on the new data, resulting in a prediction value of 90.88 for a specific combination of parameters. The conclusions of this study show that RF algorithms can be an effective tool in supporting precision agricultural planning, thereby increasing corn productivity and facing increasingly complex climate change challenges.
References
al., Z. e. (2023). Integrating genetic algorithm with ARIMA and reinforced random forest for yield prediction. Springer Nature, 280–285. doi:10.1007/springerYieldPredict2023
Ardika, S. B. (2023). Prediction of Sumatran food crop yields using machine learning methods. Digital Transformation Technology (Digitech), 389–397.
Dhillon, M. S. (2023). Advances in Crop Modeling with Machine Learning. doi:10.1016/j.eja.2023.06.010
Fitri, E. &. (2023). Optimization of linear regression, random forest regression and multilayer perceptron performance in crop yield prediction. Scientific Journal of Information Technology, 18–28.
Jeong, J. H. (2016). Random forests for global and regional crop yield predictions. PLoS ONE, Article e0156571, 1–15.
Morales, A. &. (2023). Using machine learning for crop yield prediction in the past or the future. Frontiers in Plant Science, Article 1128388. doi:10.3389/fpls.2023.1128388
Muchisha, N. D. (2021). Classification of corn farmland using machine learning based on Landsat-8 image data. IPB Repository, 1–30.
Rethnaraj, J. (2023). Lettuce Crop Yield Prediction Analysis using Random Forest Regression Machine Learning Model in Aeroponics System. IEEE Conference Publication. doi:10.1109/lettucecrop.yield.predict.2023
Suci Amaliah, M. N. (2022). Application of the Random Forest Method for Classification of Coffee Drink Variants at Konijiwa Bantaeng Coffee Shop. VARIANSI: Journal of Statistics and Its Application on Teaching and Research, 121-127.
Suresh, N. (2021). Crop Yield Prediction Using Random Forest Algorithm. IEEE Conference Publication. doi:10.1109/CropYield.RF2021
