Integration of IoT Sensors and Satellite Vegetation Indices for Real-Time Crop Monitoring and Yield Prediction

The integration of IoT, remote sensing and artificial  intelligence has emerged as an efficient approach for improving crop yield for precision agriculture. The existing crop monitoring systems bacically consider IoT sensor data or satellite imagery, thereby limiting their ability to assess crop condition and predict the yield.Our paper proposes an IoT-Satellite-Weather integrated framework. This framework combins sensor data, sentinel-2 vegetatation indices and weather information, which leads to a multimodal approach. The dataset represents a fusion of multimodal data, THis data is analysed using Random forest and LSTM models for yield prediction and also crop monitoring.

This framework provides a comprehensive representation of the crop condition by combining temporal, spatial and environmental data. The results are  predicted through a decision support dashboard whichsupports farming activities like irrigation scheduling, fertilizer management and crop planning. The proposed framework provides a scalable and smart solution, establishing a foundation for AI-enabled smart farming systems.