Biodiversity Warrior

Inspiration Biodiversity loss is a pressing global issue, driven by human activities such as deforestation, pollution, and climate change. We wanted to create an interactive tool that helps users visualize the impact of environmental changes on endangered species, empowering individuals to make informed decisions and advocate for conservation efforts.

What it does Biodiversity Warrior is a Streamlit-powered web application that allows users to explore the relationships between key environmental factors (such as CO₂ levels, mining activity, and forest coverage) and endangered species. By adjusting sliders, users can simulate changes in these factors and see estimated impacts on biodiversity, based on historical data and statistical models.

How we built it We used Python and Streamlit to develop the interactive interface, leveraging pandas for data handling and seaborn/matplotlib for visualizations. We applied linear regression models using NumPy to estimate the correlation between environmental changes and the number of endangered species in key biodiversity areas (KBAs).

Challenges we ran into Finding high-quality, reliable datasets that capture the relationships between environmental factors and biodiversity threats.

Accomplishments that we're proud of Successfully integrating real-world environmental data into an interactive, user-friendly application. Implementing dynamic visualizations that make complex ecological relationships easier to understand. Creating an educational tool that raises awareness about biodiversity conservation.

What we learned

How to use Streamlit to rapidly develop and deploy data-driven web applications. The importance of data preprocessing and feature selection in building meaningful regression models. New insights into the relationship between human activities and endangered species, reinforcing the need for sustainable environmental policies.

What's next for Biodiversity Warrior

Enhancing the prediction model by incorporating machine learning techniques for better accuracy. Expanding the dataset to include more factors like water pollution, temperature variations, and urban expansion. Adding an educational module with case studies, quizzes, and actionable steps for conservation efforts. Deploying the app as a public platform to engage students, researchers, and policymakers in biodiversity conservation discussions.

Built With

• python
• streamlit