International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 03 | Mar 2024
p-ISSN: 2395-0072
www.irjet.net
Crop Prediction for Indian Agriculture using Machine Learning and Deep Learning Classifiers K.Tharani, R.Karthiga, S.K.Srinisa, Ms.A.Aruna,M.E., Student, Dept of AI&DS Muthayammal Engineering College Rasipuram, Tamil Nadu, India. Student, Dept of AI&DS Muthayammal Engineering College Rasipuram, Tamil Nadu, India. Student, Dept of AI&DS Muthayammal Engineering College Rasipuram, Tamil Nadu, India. Assistant Professor, Dept of AI&DS Muthayammal Engineering College Rasipuram, Tamil Nadu, India. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Crop prediction is a process that uses deep learning to predict crop yields and other metrics based on a variety of factors such as weather, soil data, and crop history data. The goal of this mission is to provide farmers and other stakeholders with accurate and reliable information about desired crops that can help them make more informed decisions on planting, harvesting and other agricultural management. Crop forecasting problems present many challenges, including the need for accurate and timely data, the selection of features and characteristics for analysis, and the development of machine learning models suitable for forecasting. Additionally, forecast accuracy may be affected by factors such as regional differences in climate and soil, the presence of pests, and other environmental factors. To solve these problems, researchers and developers in the field of crop forecasting have developed different types of studies, including the generation of preliminary data, selection of features, selection of deep learning models, and performance evaluation. These techniques will involve the use of different types of data, such as weather data, soil data, and crop data, as well as various deep learning methods such as multilayer perceptron algorithms and convolutional neural networks algorithms. Ultimately, the success of crop forecasting depends on the system's ability to accurately and reliably analyze data from multiple sources and then predict crop yields and other metrics with accuracy. By solving these problems, crop forecasting has the potential to increase agricultural productivity and sustainability and support the development of more efficient and effective agriculture.
analyze different types of agricultural data using deep learning for accurate crop prediction. Our method aims to capture relationships and patterns in agricultural ecosystems by integrating data from different sources, thus predicting crop yield more easily and in a timely manner. We explore the potential of deep learning, including convolutional neural networks (CNN), Multi layer perceptron (MLP), neural networks (RNN), and their variants, to process data in different letters. The introduction highlights the challenges associated with the integration of traditional crop forecasting techniques and highlights the opportunities offered by the combination of deep learning and multivariate data analysis. We discuss the importance of each data change in preserving different aspects of crop growth and underscore the need for capable and interpretable models that can unravel the complexities of agriculture. We also present a draft of the paper that includes the methodology, experimental setup, results, and discussion to provide readers with a method. Through this research, we aim to contribute to the advancement of agricultural technology by publishing a general crop prediction method that uses the power of deep learning and multiple data fusion. Our method has the potential to improve the decision-making processes of farmers, agricultural policy makers and other stakeholders by increasing the accuracy and efficiency of crop forecasting, ultimately contributing to agricultural sustainability and food security around the world.
2. PROBLEM STATEMENT
Key Words: Machine Learning, Deep Learning, Crop prediction.
Crop prediction is a complex task influenced by many factors such as environment, soil quality and agricultural practices. Modern methods often rely on statistical models or simple machine learning methods that are difficult to capture relationships in multimodal data. Crop forecasting involves many challenges that are influenced by factors such as environment, soil properties, crop diversity and agricultural practices. Traditional machine learning models often struggle to capture complex relationships in complex agricultural systems, resulting in low accuracy. The main purpose of this research is to create an accurate and powerful crop prediction system that uses the power of deep learning to use different data sets.
1.INTRODUCTION In recent years, the integration of technologies such as deep learning and large-scale data analysis has changed many things, including agriculture. Accurate prediction of crop yield is important for optimizing agriculture, ensuring food security and reducing financial risk for farmers. Modern methods often rely on historical data and simple models and lack the ability to use rich data from a variety of sources such as satellite images, weather data, soil composition and health indicators of crops. This article presents a new way to
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 348