<![CDATA[Ornamental plant farmers face various challenges due to climate change and environmental stress that significantly affect plant health and growth. This research overcomes these challenges by developing an intelligent watering system that uses internet of things (IoT) technology and decision trees (DTs) algorithms to optimize the use of planting land by ensuring plants grow in the most optimal conditions, both in terms of water and nutrients and increase land productivity. The system is built by integrating various sensors to monitor soil moisture, air humidity, temperature, and light intensity in real-time. The collected data is used to automate watering schedules and provide recommendations on suitable plant species based on the soil nutrient content of nitrogen (N), phosphorus (P), and potassium (K). The use of the DTs algorithm helps in analyzing the data from the sensors and providing recommendations on the most suitable plants for the land. The smart watering system was tested in three zones, each simulating a different watering scenario, and successfully maintained optimal conditions for plant growth in each zone. The machine learning (ML) model with the DTs algorithm can predict the right type of ornamental plants based on the existing land conditions in three watering zones, with an accuracy of 89 %, 90 %, and 91 %, respectively. Furthermore, farmers can follow these recommendations to minimize damage and death of plants so that the level of productivity on the land becomes optimal.]]>
Copyrights © 2024
