Conclusion
The project presents a practical concept for combining Artificial Intelligence, Machine Learning, IoT sensing and computer vision within an organic gardening system. Environmental readings support irrigation decisions, while image analysis assists with visible disease recognition. A responsive website brings the information together in a format that is easier for gardeners to understand.
The proposed approach can improve monitoring, reduce unnecessary water use and support earlier intervention. It is particularly relevant to home gardeners, small growers and educational environments where commercial smart-farming systems may be unsuitable.
Limitations
- Limited or simulated sensor data
- Dependence on image quality and training data
- No large-scale commercial deployment
- Incomplete long-term field testing
Future Work
- Real Arduino or Raspberry Pi sensors
- Transfer learning for improved image classification
- Mobile notifications and cloud deployment
- Weather-forecast integration
- Testing across more plant species and environments
Final Statement
The research demonstrates how intelligent technologies can make organic gardening more data-informed, efficient and sustainable while keeping the gardener in control of final decisions.