Introduction to the Use Case Structure

Aralia Use Case: SDGs Inclusive Growth

Aralia Use Case: Public Works Bid Management and Risk Alert System

Aralia Use Case: Cabbage Supply and Demand Imbalance Analysis

🎯 1. Problem Statement & Background

• Description of the Problem: Cabbage production and sales in Taiwan often suffer from imbalance between supply and demand due to extreme weather conditions and farmers' concentrated planting. The price of cabbages fluctuates drastically from NT$3 to NT$80 per kilogram, affecting the income of farmers and the stability of the industry.
• Context Statement
  • Concentrated supply in winter, sharp price fluctuations
  • Farmers anticipate price increases and rush to plant, which can easily lead to oversupply.
  • There is an urgent need to establish an early warning mechanism to identify early variables that can predict price changes.
• Stakeholder/User Persona
  • Farmers: Want to get advice on planting and harvesting to minimize the risk of losing money.
  • Nursery operators: Adjust seedling production planning to avoid concentrated supply.
  • Policymakers: Establish agricultural risk alerts to enhance food safety.
• Possible Questions
  • "Can winter cabbage prices in a certain region be predicted in advance?
  • "How do seedling production and weather factors affect prices?"

📊 2. Data Sources

• Data Sources and Links
  • Civil IoT Platform (weather, air, temperature, sunshine, etc.)
  • Aralia Open Data Platform
  • Agricultural market price data
• Data Fields and Format
  • Seedling emergence (every 10 days)
  • Temperature, sunshine, cumulative precipitation (daily)
  • Market price of cabbage (daily)
• Update Frequency
  • Weather: Daily/Instant
  • Market price: Daily
• Pre-processing
  • Completion of missing values (temperature, sunshine, etc.)
  • Manufacturer and region name standardization
  • Creation of delay variables (90 days) as analytical factors

🛠️ 3. Aralia Demo

• User’s Operation Workflow
  1. Import the Civil IoT and market price data.
  2. Create graphs: price trends, climate variability comparison.
  3. Save Data Landmarks, create "cabbage risk alert" dashboard
• Visualization Examples
  • Time series plot: Cabbage price vs. Growing Degree Days (GDD)
  • PCA (Principal Component Analysis)
• Landmark Preview
  • Landmark charts refresh automatically when weather and market prices are updated.

📈 4. Analysis Results and Insights

• Results in Brief

  • Cauliflower prices show a 90-day delayed effect with seedling production and climate factors.
  • PCA model explains more than 70% of the variance.

• Insight Highlights

  • Growing Degree Days (GDD) and Daily Light Integral (DLI) are key factors.

    

  • Winter harvest cycle lasts about 90 days, and weather anomalies can cause prices to fluctuate earlier or later.

  

• Recommended Actions

  • Farmers should adjust planting levels based on the platform's warnings.
  • Governments can incorporate risk factors into agricultural policy decisions.

🧠 5. AI Agent Demo

• Currently, the Agent for this case is still being set up

🔧 6. Agent Setup Tutorial

• To be released after the Agent is built

🧾 7. Conclusion & Next Steps

• Extended Application:
  • Price forecast for other fruits and vegetables (e.g. onions, tomatoes).
  • Agricultural data alerts for other counties and cities
  • Integration with ESG or food safety issues
• We Encourage Users to:
  • Create their first agricultural Landmark
  • Activate agriculture AI Agent for decision-making assistance
• Call to Action (CTA)
  • Register Aralia → Create Landmark → Activate Agri-Risk Alert Agent