Prediction of Tomato Plant Disease with Meteorological Condition and Artificial Intelligence

Predicting disease in advance plays a vital role in taking preventive measures towards plant protection. The work proposes predicting tomato plant disease with meteorological conditions and artificial intelligence. Support Vector Regression (SVR) and Random Forest Regression (RFR) models are employed for the time-series forecasting of temperature and relative humidity. The models are optimized with GridSearchCV to fine-tune the hyperparameters to better forecast weather parameters. The RMSE for temperature is 0.0369; relative humidity is 1.8442 for the SVR model, 0.0246 for temperature, and 0.5918 for relative humidity with the RFR model. The R 2 values show a good prediction performance. The correlation between actual and predicted test values is positive.