AI-Driven Temperature Analysis for Educational Environments in Tanzania

Developing an AI-driven predictive model using satellite imagery and environmental data to estimate indoor classroom temperatures in Tanzanian schools, enhancing learning environments and student safety, thereby aiding educational authorities in strategic infrastructure planning and policy making. In this 8-week challenge, you will join a collaborative team of 50 AI engineers from all around the world.

The problem

In countries with a hot climate, such as Tanzania, many schools experience classroom conditions characterized by extreme temperatures, which can severely impede the learning process and pose significant health risks to students. The primary challenge lies in the lack of detailed, actionable data regarding specific classroom features that influence indoor temperatures, such as roofing materials and the presence or absence of ceiling boards. Traditional methods for monitoring and improving these conditions often fall short because they do not provide the precise, localized information necessary for effective intervention.

Impact of the Problem:

• Ineffective Learning Environments: High temperatures in classrooms can lead to discomfort, reduced attention spans, and lower overall academic performance among students. Extreme heat can significantly diminish the effectiveness of the learning environment, making it difficult for students to focus and absorb information.
• Health Risks: Exposure to high temperatures poses health risks, including heat exhaustion and heatstroke, particularly in young children who may be more vulnerable to such conditions.
• Inadequate Resource Allocation: Without precise data on which classrooms are most affected by heat due to their specific structural features, efforts to improve conditions can be misdirected or inefficient. This results in wasted resources and missed opportunities to make meaningful improvements in the learning environment.
• Barriers to Policy Implementation: The absence of reliable data impedes the ability to make informed decisions regarding educational policies and infrastructure investments aimed at creating safer, more conducive learning environments. Without accurate temperature predictions and assessments, policy interventions cannot be effectively tailored to the schools that need them most.

The goal of this AI Innovation Challenge is to develop a predictive AI model using satellite imagery that aims to address these issues by providing accurate estimations of indoor classroom temperatures based on observable external features. This capability will enable more targeted interventions, better resource allocation, and improved educational outcomes by creating environments that are more conducive to learning and safe for students.

The goals

The primary goal of this project is to develop an AI-driven predictive model using satellite imagery and environmental data to estimate indoor classroom temperatures in Tanzanian schools, enhancing learning environments and health safety. The model aims to determine temperature conditions based on observable features like roofing material, which need to be complemented with classroom specifications (including the presence of ceiling boards). The project unfolds over a 8+2-week cycle, each phase planned to ensure successful development and deployment:

• Data Collection and Resources: The team will confirm the use of high-resolution satellite imagery from platforms like Google Maps or open-source imagery like Sentinel 2. Additional environmental data such as temperature, rainfall, greenery coverage, and historical weather conditions will be integrated to enrich the dataset.
• Problem Definition and Model Development: The project will improve the accuracy of school location data using satellite imagery and environmental data. Algorithms will be developed to infer indoor temperatures from observable external conditions, considering factors like roof type and regional weather data.
• Temperature Range Detection: The AI model will identify dangerous temperature ranges that could impact student health and learning. 
• Visualization and Reporting: A geospatial display of schools will be created, color-coded by temperature profiles to easily identify and prioritize interventions in hotter schools. 
• Flood Risk Assessment: As a nice-to-have feature, the team may integrate data on flood risks to enhance environmental safety planning for schools endangered by extreme weather events.
• Deliverables and Optimization: The project will deliver a predictive AI model capable of estimating indoor temperatures, a user-friendly dashboard for demonstrating the MVP solution, a comprehensive project report detailing the methodology and model accuracy, and a well-documented code repository.

Thus, the project aims to provide a transformative tool for Tanzanian educational authorities, significantly improving the safety and quality of learning environments through advanced AI and satellite technology. This initiative promises substantial benefits in educational policy-making and infrastructure planning, ensuring safer and more conducive learning environments for students.

Why join? The uniqueness of Omdena AI Innovation Challenges

A collaborative experience you never had in your working life! For the next eight weeks, you will build AI solutions to make a real-world impact and go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.

And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.