International Journal for Multidisciplinary Research (IJFMR) E-ISSN: 2582-2160 ● Website: www.ijfmr.com ● Email: editor@ijfmr.com IJFMR23034169 Volume 5, Issue 3, May-June 2023 1 Prediction Of Leaf Species & Disease Using Ai For Various Plants Ms. Shivani S. Dagwale 1 , Prof. Prashant Adakane 2 1,2 Department Of Computer Science & Engineering, G H Raisoni University, Amravati Abstract This paper presents a method for predicting leaf species and disease in various plants using artificial intelligence. The approach involves training a machine learning model on a dataset of images of plant leaves and corresponding labels of species and disease. The trained model is then evaluated on a test set to determine its accuracy in classifying new images. Our Study show that the model will achieves high accuracy in predicting both leaf species and disease. This method provides a useful tool for identifying plants and detecting disease in agriculture, forestry, and other relevant fields. However, present techniques require laboratory diagnosis which takes time and resources. To help improve plant disease detection, the PlantDoc dataset was created. The original dataset contained 2,598 data images with 13 plant species and 17 classes of diseases. Data was provided as images in JPG, and annotations in both the VOC XML format and CSV format. Keywords: data-set, loss, TensorFlow, convolutional neural network, hypothesis, neural network,plant leaf disease, optimizer I. INTRODUCTION Plant species classification and disease diagnosis are crucial aspects in agriculture and forestry. Early detection of plant diseases can help prevent the spread of infections, increase crop yields, and ultimately improve food security. With the rapid advancement of artificial intelligence, machine learning models have shown great potential in this field. In this study, we aim to develop a reliable method for the prediction of leaf species and disease in 13 different types of plants using the PlantDoc dataset, the IceVision framework, and the YOLOv5 model. The PlantDoc dataset provides a large collection of images of plant leaves and their corresponding labels of species and disease. IceVision is an open-source framework for computer vision tasks, and YOLOv5 is a state-of-the-art object detection model that can handle multiple tasks. We aim to evaluate the performance of the YOLOv5 model in classifying images of plant leaves into their corresponding species and disease categories. The results of this study will provide valuable insights into the potential of AI for the prediction of leaf species and disease and its practical applications in agriculture and forestry..