Sugarcane Disease Prediction and Integration IOT Sensors using Deep Learning

In today’s environments, A number of diseases brought on by pathogenic bacteria, viruses, and fungi reduce the yield of sugarcane, an economically important crop. The farmers are suffering from different problems like over raining, diseases on crops etc. Some of the new farmers don’t understand the management of crops and how to save crops from disease. By identifying disease indicators using datasets of photos of sugarcane leaves. We employed a Convolutional Neural Network (CNN) in this project. To categorize the various illnesses, including rust, mosaic, red rot, smut, and yellow. To classify the different diseases such as smut, red rot, mosaic, yellow and rust. A clever, Internet of Things-integrated deep learning system for predicting sugarcane disease is proposed in this paper.and the system utilizes the data like temperature, soil moisture, humidity and leaf wetness by using and integrating with IOT sensor. To reduce output loss and guarantee sustainable cultivation, these illnesses must be detected early and accurately predicted. This study suggests an integrated approach that uses deep learning models and Internet of Things-based sensor technology to forecast sugarcane diseases. While image sensors take high-resolution pictures of sugarcane leaves, IoT sensors are placed in the field to gather real-time environmental data like temperature, humidity, soil moisture, and leaf wetness. To recognize and classify the collected multimodal data, a hybrid model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) looks at both visual and environmental features.