Grape Disease Dataset

The environment plays a crucial role in shaping crop growth and productivity. A IoT will be utilized for monitoring temperature, humidity, and leaf wetness, all of which influence grape quality and lifespan. Furthermore, a far-reaching dataset takes into consideration the investigation of illness designs, natural elements, and potential moderation systems. By leveraging weather-related variables and sensor data, grapevine producers can create an efficient and automated disease detection system. We presents a self-created weather parameter database using sensors. The database consists of 10000 records divided into 5 categories. Here, experiment have been carried out using our dataset to predict grape diseases on various machine learning algorithm.

Data can be collected remotely or in the field. Actual results can be taken from the field at real time after regular interval. Here, experiment have been carried out using our dataset to predict grape diseases on various machine learning algorithm. The dataset is categorized into 8 distinct classes, including 3 disease categories. The disease categories cover a range of common grape diseases, such as powdery mildew, downy mildew, bacterial leaf spot. Temperature and Leaf Wetness Sensor are needed to measure weather parameters and managed by NodeMCU. Data set were analyzed to predict the instances of diseases Downey Mildew, Powdery Mildew and Bacterial Leaf Spot using the algorithm. Additionally, we may need metadata such as the type of grape variety, location, and date of observation. Integrated the collected data means combined the grape disease data with the corresponding environmental data