KISAN-MITRA
खेती की समस्याओं का समाधान, समृद्धि की ओर
Created on 13th June 2023
•
KISAN-MITRA
खेती की समस्याओं का समाधान, समृद्धि की ओर
The problem KISAN-MITRA solves
Crop Disease Detection: The platform uses machine learning algorithms to evaluate crop photos and properly identify illnesses. When users contribute photographs of infected crops, the system may deliver disease detection results by training the model on a library of annotated images representing various crop diseases. Furthermore, the platform provides treatment recommendations for the diagnosed illnesses, supporting farmers in efficiently controlling crop health.
Crop Recommendation: The platform builds algorithms to examine data on soil qualities, climatic conditions, and other pertinent elements and recommend acceptable crops for specific locations or soil types. Users may get tailored crop suggestions based on their location and soil qualities, which can help them make more educated decisions about what to cultivate on their farms.
Soil and Other Property Analysis: The platform allows users to enter soil test results and other farm-related property information. The system analyzes the input and produces important insights and recommendations for soil improvement or nutrient management using this data. Users may also view the data in the form of visualizations or reports, allowing them to better understand and handle their soil-related issues.
Kisaan Samachar (News Portal): The portal compiles agricultural news, farming practices, government regulations, market trends, and more. It categorizes and presents the platform's news stories, giving users a consolidated location for staying up to current on pertinent agricultural information. Users may use search features and filters
Overall, the web app improves farming by offering quick disease diagnosis, individualized crop suggestions, soil analysis, access to agricultural news, a handy marketplace, and a friendly farming community. Its goal is to provide farmers with the tools and knowledge they need to make educated decisions, increase production, and implement sustainable farming methods.
Challenges we ran into
Data collection and quality: It might be difficult to get a broad and complete dataset of leaf pictures and soil nutrient information. It is critical to ensure the quality and correctness of the data while building dependable machine learning models.
Model training and optimization: Training machine learning models using TensorFlow and scikit-learn necessitates skill in method selection, data preparation, and hyperparameter tuning. It might take time and iteration to get the necessary precision and efficiency.
Front-end and back-end integration: It might be difficult to integrate the React front-end with the Node.js back-end and ensure good communication between the two. Managing API endpoints, coordinating data transfers, and synchronizing UI changes with server answers all need meticulous planning.
Deployment and scalability: Moving the program to a production environment and assuring its scalability and performance in the face of high traffic might be difficult. Optimizing the app's design, introducing caching methods, and making optimal use of server resources are all critical concerns.
User interface and user experience design: It might be difficult to design an intuitive and user-friendly interface that allows farmers to simply collect leaf photos, enter soil nutrient data, and understand the app's suggestions. Conducting user testing and implementing feedback are critical steps in improving the overall user experience.