Green Wall CO₂ Reduction & Monitoring Application

Introduction

This comprehensive application combines two powerful models for designing and monitoring green walls in indoor spaces:

1. Planning Model: Predicts CO₂ assimilation rates and potential energy savings for different plant species and environmental conditions
2. Monitoring Model: Analyzes hyperspectral images to monitor plant health and CO₂ sequestration performance over time

By integrating both planning and monitoring capabilities, this tool provides a complete solution for green wall implementation and maintenance, helping users optimize their installations for maximum environmental benefits.

Planning Model

The planning model leverages machine learning to predict the CO₂ assimilation rate of various indoor plant species and calculates the potential energy savings achievable through the implementation of vertical green walls (VGWs).

Key Features

• CO₂ Assimilation Prediction: Accurately predict the CO₂ assimilation rate of different plant species based on user-defined room conditions.
• Energy Saving Calculation: Estimate potential energy savings by calculating the reduction in air changes per hour (ACH) due to the implementation of a VGW.
• Species Comparison: Compare the energy-saving potential of different plant species for your specific conditions.
• Interactive Interface: A user-friendly Streamlit interface with sliders and input fields for easy parameter adjustment.
• ASHRAE Standard Reference: Guidance for setting the ACH parameter according to the ASHRAE Standard 62.1–2019.
• Visualizations: Clear results, including a Plotly bar chart comparing the energy saving potential of each plant species.

How to Use the Planning Model

1. Input Parameters: Use the sidebar to specify your indoor conditions, such as room volume, number of occupants, lighting intensity, ambient CO₂, relative humidity, and the area of the green wall.
2. Select Plant Species: Choose the desired plant species from the available options.
3. Set ACH: Set the Air Changes per Hour (ACH) parameter based on the requirements for your space (refer to ASHRAE standard 62.1–2019 for guidance).
4. Run the Model: Click the "Run Model" button to generate predictions.
5. View Results:
   • The predicted CO₂ assimilation rate will be displayed for the selected plant species.
   • The potential reduction in ACH and the estimated energy savings will be calculated and displayed.
   • A comparison of potential energy savings for all available plant species will be shown in a Plotly bar graph.

Monitoring Model

The monitoring model analyzes hyperspectral images of green walls to predict CO₂ flux and detect changes in plant health over time. This helps identify areas of stress or reduced performance, enabling timely interventions.

Key Features

• Hyperspectral Analysis: Process hyperspectral images to extract critical information about plant health and photosynthetic activity.
• CO₂ Flux Prediction: Use a trained machine learning model to predict CO₂ sequestration rates across the green wall.
• Change Detection: Compare images over time to identify areas where performance has improved or degraded.
• Visual Interpretation: Clear visualizations with RGB views and color-mapped CO₂ flux representations.
• Demo Mode: Built-in demonstration capability for users without hyperspectral imaging equipment.

How to Use the Monitoring Model

1. Upload Images: Upload two hyperspectral images (.hdr and .dat files) of your green wall taken at different times.
2. Process Data: The application will automatically extract spectral indices and predict CO₂ flux.
3. View Results:
   • RGB visualizations of the hyperspectral data
   • CO₂ flux maps for both images
   • A difference map highlighting changes between the two images
4. Interpret Results: Use the provided guidelines to interpret changes in CO₂ flux and identify potential issues.
5. Take Action: Based on the results, implement targeted interventions to maintain optimal green wall performance.

Installation and Setup

To run this application on your local machine:

1. Clone this repository:

   git clone <repository-url>
   

2. Navigate to the project directory:

   cd CO2_Reduce_app
   

3. Install required dependencies:

   pip install -r requirements.txt
   

4. Run the application:

   streamlit run app.py
   

Scientific Background

This application is based on scientific research published in:

Yungstein, Y., & Helman, D. (2023). Cooling, CO2 reduction, and energy-saving benefits of a green-living wall in an actual workplace. Building and Environment, 236, 110220.

The monitoring model is based on ongoing research into hyperspectral monitoring of plant health and carbon sequestration.

Usage Examples

Planning a New Green Wall

• Use the planning model to compare different plant species for your specific environment
• Estimate the potential energy savings before installation
• Choose the most effective plant species based on predicted CO₂ assimilation rates

Monitoring an Existing Green Wall

• Take regular hyperspectral images of your green wall (typically monthly)
• Upload the images to the monitoring model to track changes in performance
• Identify areas that show decreased CO₂ sequestration for targeted maintenance
• Verify the effectiveness of interventions by comparing before and after images

Contact

If you have any questions or feedback, feel free to reach out using the contact information provided at the bottom of the application.

Developed by: Yehuda Yungstein