Inspiration
The UC Santa Cruz Arboretum & Botanic Garden served as the inspiration for Grotime.
What it does
Grotime, the proposed website, leverages predictive modeling to recommend the most suitable plants based on the prevailing weather conditions at the time of user access.
How we built it
- Front end: Developed using Figma, HTML, and CSS.
- Back end: Implemented with Python, integrating a Weather API and utilizing Flask.
Challenges we ran into
- Aggregating Weather Data: Faced difficulties in gathering weather data for extended periods to enhance predictive accuracy.
- Plant Data Acquisition: Encountered challenges in finding comprehensive data on various plants to train and optimize the predictive model.
Accomplishments that we're proud of
- Single Score Conversion: Successfully transformed the model's predictions into a cohesive single score for user convenience.
- Simplistic Design: Accomplished the implementation of a simplistic and user-friendly design for an enhanced user experience.
What we learned
- Front-End and Back-End Integration: Discovered the complexities of seamlessly integrating front-end and back-end functionalities.
- Dataset Organization: Recognized the pivotal role of well-organized datasets in the success of predictive modeling.
What's next for Grotime
- Integration with Soil Data: Planning to integrate soil data for more accurate predictions and personalized plant recommendations.
- Expanding User Base: Aiming to extend the platform's utility beyond the UC Santa Cruz Arboretum, supporting gardeners in diverse locations.
Log in or sign up for Devpost to join the conversation.