A Machine Learning Approach for Predictive Analysis of Jasmine Flower Yield and Plant Health Monitoring

Plant diseases and unpredictable yields are two issues that jasmine flower production must deal with, necessitating cutting-edge solutions for effective crop management. It provides a hybrid approach for plant health monitoring and jasmine yield prediction based on machine learning. For yield prediction, a Random Forest algorithm is used, and for illness identification via picture analysis, a Convolutional Neural Network (CNN) is deployed. For realtime monitoring, leaf photos and data from IoT sensors such as temperature, humidity, and soil moisture are analyzed. The suggested model outperforms conventional models in terms of accuracy, with a Mean Absolute Error (MAE) of 7.3 and an accuracy of 89% for yield prediction. CNN's F1-score for identifying plant diseases was 90.5%. With the help of TensorFlow and MATLAB Simulink, the system is implemented and offers farmers useful information. This all-inclusive solution improves crop management efficiency in jasmine production by optimizing yield projections and early disease detection.