AI-DRIVEN MULTICROP DISEASE DETECTION AND PRECISION PESTICIDE RECOMMENDATION SYSTEM USING DEEP LEARNING

Abstract

A nation's ability to innovate depends on its agriculture industry. All nations are built on agriculture, which provides food and raw materials. For humans, agriculture is essential as a source of food. Plant disease detection has thus grown to be a serious problem. Technology has always been used in agriculture, but with the introduction of powerful computer systems and massive datasets in the early 21st century, the use of deep learning in crop disease diagnosis gained significance. To diagnose agricultural illnesses in the old system, farmers mostly depended on physical observation and knowledge passed down through the generations. Specialists in agriculture would examine the crops in person, identify illnesses based on outward signs, and provide treatments. Although this approach had advantages, it was laborious, reliant on the observer's skill, and occasionally resulted in incorrect diagnoses. As a result, the expanding global population and rising food demand need the use of sophisticated methods for agricultural disease identification, such as deep learning. To avoid large output losses, crop diseases must be promptly and accurately identified. Farmers can respond quickly to stop the spread of illnesses by automating the detection process, which will increase agricultural production. Furthermore, by reducing the needless use of pesticides, offering specific pesticide recommendations lessens the negative environmental effects of farming. Convolutional neural networks (CNNs), in instance, are deep learning algorithms that have shown to be quite successful in image identification tasks, which makes them perfect for seeing patterns in photos of sick crops. The way farmers manage their crops has changed dramatically with the introduction of deep learning in agriculture, particularly in the areas of crop disease detection and categorization. Farmers are now able to more effectively and precisely identify agricultural illnesses by utilizing cutting-edge technology. This has important ramifications for food security since it makes prompt intervention possible and recommends sensible actions, like using pesticides, to stop the spread of illness.