International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 12 | Dec 2025
p-ISSN: 2395-0072
www.irjet.net
ML-Agri Care: Enhancing Crop Yield through Machine Learning -Based Crop Predictor, Fertilizer Recommender, and Plant Disease Detector Chaitra K C1 ,Rohit2, Shreyas H B3, Sinchana N G4,Spoorthi M R5 1Asst.Prof. Information Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere,
affiliated to VTU Belagavi, Karnataka, India.
2 3 4 5Bachelor of Engineering, Information Science and Engineering, Bapuji Institute of Engineering and
Technology, Davangere, affiliated to VTU Belagavi, Karnataka, India. -------------------------------------------------------------------------***------------------------------------------------------------------------
Abstract - Agriculture is the backbone of the global
practices, thereby transforming traditional farming methods into more productive and environmentally friendly systems.
economy, yet farmers face significant challenges in optimizing crop yield due to unpredictable weather patterns, soil degradation, pest infestations, and inadequate knowledge of best farming practices. This paper presents ML Agri Care, an integrated machine learning-based agricultural decision support system designed to address these challenges through three core modules: crop yield prediction, fertilizer recommendation, and plant disease detection. The system leverages supervised learning algorithms including Random Forest, Support Vector Machines, Convolutional Neural Networks, and ensemble methods to provide accurate, datadriven recommendations to farmers. By analyzing historical agricultural data, soil parameters, weather conditions, and plant images, ML-Agri Care empowers farmers with actionable insights to enhance productivity, reduce input costs, and promote sustainable farming practices. Experimental results demonstrate high accuracy across all modules, with the crop predictor achieving 92% accuracy, fertilizer recommender reaching 89% accuracy, and disease detector attaining 94% accuracy on validation datasets. The system is implemented as a user-friendly web application accessible to farmers with minimal technical expertise, bridging the gap between advanced machine learning technology and practical agricultural applications.
2. OBJECTIVES To develop a machine learning-based crop prediction system that recommends the most suitable crops based on soil type, climate conditions, and environmental factors. To design a fertilizer recommendation module that suggests the right type and number of fertilizers by analyzing soil nutrients, crop needs, and sustainable farming practices. To implement a plant disease detection system using computer vision and deep learning techniques that identifies crop diseases early from leaf or plant images, enabling timely interventions. To enhance crop yield and farmer productivity through datadriven decision-making, reducing reliance on manual guesswork and traditional trial-and-error methods. To promote sustainability in agriculture by reducing excessive use of fertilizers, minimizing crop losses, and optimizing resource utilization. To create a user-friendly platform that makes advanced technology accessible to farmers, helping them adopt modern farming practices with ease.
Key Words: machine learning, crop prediction, fertilizer recommendation, plant disease detection, soil data analysis, precision agriculture, and sustainable farming.
3. LITERATURE SURVEY
1. INTRODUCTION
This section summarizes the conclusions of multiple articles that have been studied and reviewed. This section contains records that were reviewed prior to and during project development. The documents provided an improved understanding of existing solutions, how methods can be optimized, and how algorithms could be selected based on their performance to get a better result while developing the Project.
ML-Agri Care is an innovative agricultural support system designed to enhance crop yield and farming efficiency through the application of machine learning techniques. By integrating a crop prediction model, a fertilizer recommendation engine, and a plant disease detection tool, this platform offers comprehensive assistance to farmers. It analyzes critical factors such as soil data, environmental parameters, and crop images to provide tailored guidance on optimal crop selection, precise fertilizer usage, and early identification of plant diseases. This data-driven approach not only improves resource utilization and sustainability but also empowers farmers to adopt precision agriculture
© 2025, IRJET
|
Impact Factor value: 8.315
The reviewed studies collectively highlight the growing importance of machine learning in modern agriculture, particularly in crop yield prediction, crop selection, disease monitoring, and fertilizer recommendation. Researchers have used diverse datasets including soil parameters, weather factors, satellite imagery, crop type, and historical
|
ISO 9001:2008 Certified Journal
|
Page 127