A common theme in agriculture is to reduce human participation i.e. to reduce human participation and to increase farmer purchase. Due to this no farmers can not produce a good output which decrease their income. This is due to many significant factors such as a lack of minerals, moisture of the soil, temperature changes, etc. Furthermore, due to the high incidence of crop diseases, both the quantity and quality of the harvest are affected. IoT sensors can easily be monitored and this gives information about agricultural areas and so smart agriculture is a new concept. Part of the methodology involves taking real-time pictures of crops with high-resolution cameras and deploying Internet of Things sensors to record vital environmental and soil variables. The diseases that are present and their type are then identified by running these photos through improved machine learning algorithms that were created using huge data sets. The thyroid resilience system allows early medical intervention based on accurate identification of early symptoms of sickness, with prompt action reducing the losses from infection. Each of the sensors paired with the analysis of our images allows for a much more detailed and accurate assessment than our previously standardised methods to detect disease. In addition to the aforementioned Internet of Things sensor network that actively collects environmental data (temperature, humidity, and soil moisture), the proposed system also includes a live picture capture module for visual crop monitoring capture (Vanitha et al. 2023). Seedlings are grown with impenetrable disks under the pictures taken of the plant leaves, which are then filed using a machine learning model trained to identify common diseases. Data is preprocessed at edge with a system to ensure sustainability and remote availability for the farmers, thus giving them useful insights on a cloud based platform.