🌱 About the Project Our project is a smart environmental monitoring and plant recommendation system designed to help gardeners and plant enthusiasts grow plants more successfully. By combining Internet of Things (IoT) sensors with machine learning and a web-based dashboard, the system analyzes real-time environmental conditions and suggests plants that are most likely to thrive in that environment.
The system uses an ESP32 microcontroller connected to multiple sensors that measure key environmental factors such as temperature, humidity, soil moisture, and light intensity. These readings are sent to a backend server built with Flask, where they are processed and analyzed.
A machine learning model evaluates the environmental data and predicts the most suitable plants for those conditions. The results are then refined using additional filters based on light availability and soil moisture levels to ensure the recommendations are realistic and practical.
Users can interact with the system through a web dashboard that displays live sensor data, environmental readings, and suggested plants. This interface allows users to quickly understand their growing conditions and make informed decisions about what to plant.
PlantSense aims to make gardening more accessible by transforming complex environmental data into simple, actionable recommendations. In the future, the system can be expanded to include automated watering, plant health monitoring, and mobile notifications, creating a fully intelligent plant care assistant
How we built it Our past experience provided the foundation for understanding basic electronics and programming, while AI programs helped supplement our learning and help us overcome hurdles. We also used online tutorials to understand how components interact with each other.
Challenges we ran into As much as we tried to avoid this, towards the end, we ran into some component compatibility issues, forcing us to work with what we got and design new circuits or make new plans with the new set of components that we are forced to work with.
Accomplishments that we're proud of We were able to change to the ESP32 microcontroller in the last minute and still make it work.
What we learned How to research, design and construct a device using well-documented Arduino or related machinery parts. We learned about what could go wrong and/or what to account for in the future as well.
What's next for Soil Sensor project Develop a 3D model of how the components will be put together for the long-term use case, maybe accounting for needing it to be waterproof and durable. We also need to find ways to attach/clamp all the sensors to the 3D skeleton in a lasting way.
Built With
- ai
- arduino
- c++
- css3
- csv
- dataset
- docker
- esp32
- flask
- html5
- javascript
- json
- machine-learning
- python
- sensor
Log in or sign up for Devpost to join the conversation.