Challenge background
Urban farming plays a crucial role in the fight against climate change by supporting sustainable food production within cities. As urbanization continues to expand, integrating agriculture into urban areas not only strengthens local food security but also reduces transportation emissions and the carbon footprint associated with conventional farming practices.
Additionally, urban farming contributes to the creation of green spaces, helps mitigate the urban heat island effect, and improves air quality. By connecting communities with locally grown food, it encourages environmental responsibility and raises awareness about the impact of traditional agriculture on climate change. Embracing urban farming is essential for the development of environmentally friendly and resilient cities, while also fostering a sustainable future in the face of global climate challenges.
The problem
Climate change and sustainable food production within cities.
Goal of the project
1. Selection of optimal locations for urban farming
- Develop an algorithm using machine learning to identify optimal urban locations for community gardens based on soil and climate data, sunlight exposure, and local conditions by using satellite images.
2. Crop Selection and Yield Prediction
- Use machine learning models to recommend the most suitable and resilient crop varieties based on historical climate data and local conditions.
- Implement predictive models for estimating crop yields to enhance planning and resource allocation.
3. Smart Pest Management
- Implement a machine learning-based pest prediction system to identify potential pest outbreaks and automate targeted interventions, reducing the reliance on chemical pesticides.
Project timeline
- 1
Week 1
Week 1: Project Setup
Assemble a multidisciplinary team including data scientists, agricultural experts, and AI specialists.
- 2
Week 2
Week 2: Data Collection
Collecting tabular data, satellite images, and review scientific articles on urban farming.
- 3
Week 3
Week 3: Model Development and Training
Develop machine learning models for site selection, crop selection, yield prediction and pest management. Train models using collected data and
- 4
Week 4
Week 4: Continuously refine models for accuracy
- 5
Week 5
Week 5: Prototyping
AI-driven systems crop selection, yield prediction and pest management on a small scale.
- 6
Week 6
Week 6: Testing application
- 7
Week 7
Week 7: Deployment
Deploy optimized machine learning models across all selected urban farming sites. Launch the application on free platform and make it available to the community
- 8
Week 8
Week 8: Report
Report the project findings to all stakeholders
What you'll learn
- Rapid Implementation: Completion of the project within the 8-week timeframe.
- Efficient Resource Utilisation: Open source data, tools and machine learning techniques.
- Increased Community Engagement: Active participation within the community through Slack, Google Drive, Notion, Github and any other open source platform for project management and team communication.
- Climate-Resilient Agriculture management app: Crop selection and pest management for urban agricultural systems to enhance societal resilience to climate change.
- Report on best locations for urban agriculture in Milan, Italy.