EcoBuild Ops

AI-assisted ESG & Carbon Tracking for Construction Projects

EcoBuild Ops is a demonstration prototype of an Automated Management Information System (MIS) designed to support environmental accounting, waste disposal management, and carbon footprint control in construction organizations.

The system supports the full operational lifecycle:

Waste generation → Disposal request → Approval → Disposal act (DONE)

An AI-assisted module is integrated to support automatic waste categorization, illustrating the application of AI-assisted decision-support techniques in environmental management systems.

The project was developed for academic and portfolio purposes, with a focus on Automated Information Systems, ESG digitalization, and AI-assisted decision support.

---

Environmental and ESG Motivation

The construction industry is one of the largest contributors to material waste generation and greenhouse gas emissions worldwide. In recent years, environmental accountability, carbon footprint transparency, and ESG compliance have become key priorities for construction companies, regulators, and investors.

Effective environmental management in construction projects requires not only regulatory compliance, but also reliable data collection, structured workflows, and analytical support for decision-making. Automated information systems play a crucial role in enabling consistent waste tracking, disposal control, and carbon-related data aggregation.

EcoBuild Ops addresses this challenge by demonstrating how an automated management information system can support environmental accounting and carbon footprint control at the operational level. The project illustrates how digital workflows and AI-assisted components can be integrated into ESG-oriented management systems, providing a foundation for scalable, data-driven environmental governance.

---

Key Features

• Environmental waste accounting for construction projects
• Disposal request management and approval workflow
• Disposal act generation and status tracking
• Centralized SQLite database
• Lightweight web interface (Flask + HTML)
• AI-assisted waste category suggestion (rule-based prototype)
• Clear system logic suitable for academic demonstrations

---

Technology Stack

• Python 3.11+
• Flask 3.x
• SQLite
• HTML (Jinja2 templates)
• Rule-based AI prototype for waste classification

---

Project Structure

EcoBuildOps/
│
├── app.py                 # Flask application (controllers & routes)
├── ai.py                  # AI-assisted waste classification module
├── db.py                  # Database connection and transaction handling
├── init_db.py             # Database schema initialization
├── requirements.txt       # Python dependencies
│
├── data/
│   └── ecobuildops.db     # SQLite database (created at runtime)
│
├── templates/
│   ├── base.html
│   ├── index.html
│   ├── waste_list.html
│   ├── waste_form.html
│   ├── request_list.html
│   ├── request_form.html
│   └── act_list.html
│
└── README.md

---

Installation & Run (Windows / macOS / Linux)

1. Clone the repository

git clone https://github.com/your-username/EcoBuildOps.git cd EcoBuildOps

2. Create and activate virtual environment

python -m venv .venv

Windows: .venv\Scripts\Activate.ps1

macOS / Linux: source .venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Initialize the database

python init_db.py

5. Run the application

python app.py

6. Open in browser

http://127.0.0.1:5000

---

Demonstration Scenario (2–3 minutes)

1. Waste

• Create a waste record
• Example description: "concrete and brick debris after demolition"
• Verify AI category suggestion

2. Requests

• Create a disposal request
• Select existing waste records
• Approve the request (status → APPROVED)

3. Acts

• Create a disposal act
• Verify that the request status changes to DONE

---

AI Module Note

The AI module is implemented as a rule-based classifier using keyword matching.

In the academic context, it represents a prototype of an intelligent subsystem that can be extended or replaced by:

• supervised machine learning models,
• NLP-based text classification,
• ESG-oriented analytical pipelines,
• carbon footprint estimation models,
• this design allows the system to evolve from a prototype into a full-scale AI-driven environmental analytics platform.

---

Academic Context

This project was developed as part of coursework in:

• Automated Systems of Information Processing and Control (MIS)
• Management Information Systems
• Environmental and ESG-oriented digital systems

The prototype is suitable for:

• academic demonstrations,
• portfolio presentation,
• MSc / Master’s applications in Computer Science, Artificial Intelligence, or Information Systems.

---

Disclaimer

This system is a demonstration and educational prototype. It is not intended for production use.

---

License

Educational and demonstration use only.