Skip to content

guhankn1-stack/SIH-25010

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Smart India Hackathon Workshop

Date:30.09.2025

Register Number:25014479

Name:Guhan

Problem Title

SIH 25010: Smart Crop Advisory System for Small and Marginal Farmers

Problem Description

A majority of small and marginal farmers in India rely on traditional knowledge, local shopkeepers, or guesswork for crop selection, pest control, and fertilizer use. They lack access to personalized, real-time advisory services that account for soil type, weather conditions, and crop history. This often leads to poor yield, excessive input costs, and environmental degradation due to overuse of chemicals. Language barriers, low digital literacy, and absence of localized tools further limit their access to modern agri-tech resources.

Impact / Why this problem needs to be solved

Helping small farmers make informed decisions can significantly increase productivity, reduce costs, and improve livelihoods. It also contributes to sustainable farming practices, food security, and environmental conservation. A smart advisory solution can empower farmers with scientific insights in their native language and reduce dependency on unreliable third-party advice.

Expected Outcomes

• A multilingual, AI-based mobile app or chatbot that provides real-time, location-specific crop advisory. • Soil health recommendations and fertilizer guidance. • Weather-based alerts and predictive insights. • Pest/disease detection via image uploads. • Market price tracking. • Voice support for low-literate users. • Feedback and usage data collection for continuous improvement.

Relevant Stakeholders / Beneficiaries

• Small and marginal farmers • Agricultural extension officers • Government agriculture departments • NGOs and cooperatives • Agri-tech startups

Supporting Data

• 86% of Indian farmers are small or marginal (NABARD Report, 2022). • Studies show ICT-based advisories can increase crop yield by 20–30%.

Problem Creater's Organization

Government of Punjab

Theme

Agriculture, FoodTech & Rural Development

Proposed Solution

Agriapp

  • Agriapp is a multilingual, AI-powered mobile application designed to provide small and marginal farmers with personalized, real-time crop advisory. The app leverages advanced machine learning models to analyze soil data, weather conditions, crop history, and market trends. Farmers can input their land details, upload images for pest/disease detection, and receive instant recommendations in their native language. The solution integrates weather APIs, soil health databases, and market price feeds to deliver actionable insights. Voice support and a simple interface ensure accessibility for users with low digital literacy. The app also collects feedback and usage data to continuously improve its advisory services, making it a comprehensive, user-friendly tool for sustainable and profitable farming.
  • Agriapp directly tackles the challenges faced by small and marginal farmers by providing tailored, data-driven recommendations that consider local soil, weather, and crop conditions. The app breaks language and literacy barriers through multilingual support and voice features, ensuring accessibility for all users. * By offering real-time pest and disease detection, weather alerts, and market price updates, Agriapp empowers farmers to make informed decisions, reduce input costs, and improve yields. The platform’s user-friendly design and continuous feedback loop further ensure that advisory services remain relevant, effective, and easy to use for the target audience
  • Innovation and uniqueness of the solution: Agriapp stands out by combining AI-driven, hyper-local advisory with multilingual and voice-enabled support, making advanced agri-tech accessible to even the most underserved farmers. Unlike generic advisory tools, Agriapp integrates real-time data from multiple sources (weather, soil, market) and uses image-based pest/disease detection powered by machine learning. * Its feedback-driven improvement loop, offline functionality, and intuitive design ensure continuous relevance and usability. This holistic, inclusive approach bridges the digital divide and sets Agriapp apart as a truly transformative solution for Indian agriculture.

Technical Approach

TECHNICAL APPORACH

  • Technologies to be used:Mobile App Development: Flutter (Dart) for cross-platform Android/iOS support • Backend/API: Node.js with Express or Python (FastAPI/Django REST) for scalable APIs • AI/ML: Python (TensorFlow, PyTorch, scikit-learn) for crop advisory, pest/disease detection, and recommendation models • Database: PostgreSQL or MongoDB for user data, soil/market/weather records • Cloud & Hosting: AWS, Google Cloud, or Azure for backend, storage, and ML model deployment • APIs: Integration with weather APIs, government agri-data, and market price feeds • Voice & Language: Google Cloud Speech-to-Text, Text-to-Speech, and translation APIs for multilingual and voice support • Image Processing: OpenCV, TensorFlow Lite for on-device pest/disease detection • Security: OAuth2, JWT for authentication and data privacy • Other: Firebase for push notifications and analytics
  • Methodology and process for implementation: 1. Requirement Analysis: Gather detailed requirements from stakeholders (farmers, agri-experts, government bodies). 2. System Design: Design system architecture, data flow, and user interface (UI/UX) wireframes. Prepare flow charts for advisory logic and user journeys. 3. Data Collection & Integration: Aggregate soil, weather, crop, and market data from public APIs and government sources. Prepare datasets for AI/ML model training. 4. AI/ML Model Development: Build and train models for crop recommendation, pest/disease detection (using image data), and yield prediction. 5. Backend & API Development: Develop secure, scalable REST APIs for data processing, user management, and advisory delivery. 6. Mobile App Development: Implement the cross-platform app using Flutter, integrating APIs, voice, and multilingual support. 7. Testing & Validation: Conduct unit, integration, and user acceptance testing. Validate AI/ML outputs with agri-experts. 8. Pilot Deployment: Launch a pilot with a small group of farmers, collect feedback, and refine features. 9. Full-Scale Deployment: Roll out the app to a wider audience, monitor usage, and provide support. 10. Continuous Improvement: Use analytics and user feedback to update models, add features, and enhance usability.
    c:\Users\acer\Pictures\Screenshots\Screenshot 2025-09-30 174445.png
  • Feasibility and Viability

    FEASIBILITY AND VIADILITY

    • Analysis of the feasibility of the idea: The Agriapp solution is highly feasible due to the increasing penetration of smartphones and mobile internet in rural India. The required technologies—AI/ML, cloud computing, and mobile development—are mature and accessible. *Publicly available datasets and APIs for weather, soil, and market prices support rapid development. Collaboration with agricultural experts and local organizations can ensure data accuracy and user adoption. The modular architecture allows for phased implementation and scaling. Initial pilot programs can validate the approach before full-scale rollout. With government and NGO support, the solution can be deployed cost-effectively and maintained sustainably.
    • Potential challenges and risks:Data Quality & Availability: Incomplete or inaccurate soil, weather, or market data may affect advisory accuracy.
      Digital Literacy: Some farmers may struggle to use mobile apps despite voice and language support.
      Connectivity: Limited internet access in remote areas could hinder real-time updates and cloud-based features.
      User Adoption: Resistance to new technology or reliance on traditional practices may slow adoption.
      Model Accuracy: AI/ML models may produce errors, especially in pest/disease detection from images.
      Privacy & Security: Protecting user data and ensuring secure authentication is critical.
      Scalability: Handling large user bases and high data volumes as the app grows.
      Maintenance: Continuous updates and support are needed to keep the app relevant and effective.

    Impact and Benefits

    IMPACT AND BENIFTS

    • Potential impact on the target audience: Agriapp has the potential to transform the lives of small and marginal farmers by providing them with timely, scientific, and personalized crop advisory. This can lead to increased crop yields, reduced input costs, and improved income stability. The app’s multilingual and voice-enabled features ensure inclusivity, empowering even low-literate and non-tech-savvy users. By promoting sustainable farming practices and reducing dependency on unreliable sources, Agriapp can enhance food security, improve livelihoods, and contribute to the overall socio-economic development of rural communities.
    • Benefits of the solution (social, economic, environmental, etc.):
      Social: Empowers farmers with knowledge, bridges the digital divide, and fosters community resilience.
      Economic: Increases productivity and profitability, reduces unnecessary input costs, and provides access to better market prices.
      Environmental: Promotes sustainable farming practices, reduces chemical overuse, and encourages resource-efficient agriculture.
      Policy & Research: Aggregated data can inform government policy and agricultural research for broader impact.

    Research and References

    Research and References

    • - AgriTech in India – NITI Aayog Report A comprehensive government report on how AI and digital technologies are transforming Indian agriculture, with case studies and policy recommendations. - Plantix – AI-Based Crop Advisory App A popular mobile app that uses image recognition to diagnose crop diseases and offers localized advice to farmers. - CropIn Technology A leading AgriTech company offering AI and data-driven solutions for farm management, crop analytics, and advisory services. - Digital Green A nonprofit that uses technology and community-based approaches to deliver agricultural knowledge to smallholder farmers. - Wadhwani AI – Cotton Pest Management An AI-powered solution developed in collaboration with the Indian government to help cotton farmers detect pests and reduce pesticide use.
    Screenshot 2025-09-30 174445

    About

    No description, website, or topics provided.

    Resources

    Stars

    Watchers

    Forks

    Releases

    No releases published

    Packages

     
     
     

    Contributors