− In agriculture, rice plays an important role in the Indonesian economy. Rice produces rice, one of the most widely consumed staple food sources in Indonesia. Many factors can cause rice production failure, one of which is leaf pests and diseases. Therefore, early identification and management of plant diseases is an important step in an effort to increase crop yields and ensure food safety. One way to detect rice leaf images early is to perform an image classification process and create a web-based application. The method that has the ability in image processing is deep learning technique with convolutional neural network (CNN) method. The Convolutional Neural Network (CNN) method works to perform and predict diseases in plants by using image categorization or object images. This research aims to apply the web application of image classification of rice plant diseases to the Amazon Web Service (AWS) by identifying and classifying various types of rice leaf diseases using the CNN algorithm, so that farmers can detect rice plant diseases quickly and accurately through image analysis. This application was created using Convolutional Neural Network (CNN) methodology and Software Development Life Cycle (SDLC). The result of this study is that researchers created a web application for the classification of rice plant diseases through leaf images which are divided into 4 categories, namely Healthy, Leaf Blight, Brown Leaf Blight and Hispa, which is made a classification model using CNN with an accuracy value of 0. 8608, then using the streamlit framework to build a website, and utilizing AWS services in the form of Amazon Elastic Compute Cloud (Amazon EC2) as a hosting service, Amazon Simple Storage Service (Amazon S3) as a service for storing rice plant disease classification models and for storing web files, and Amazon Identity and Access Management Role (Amazon IAM) as a service to create a role that gives permission to connect between AWS S3 and AWS EC2. Testing the disease classification model in rice plants implemented on the web in EC2 shows quite good results with an accuracy of 78.5%. This can affect the model's ability to recognize specific disease patterns