IoT-Based Prediction of Ornamental Plant Water Needs Using Sugeno Fuzzy Algorithm

Urban plant care is increasingly important amid growing concerns about air pollution and limited time for manual maintenance. In Indonesia, air quality has deteriorated significantly, with PM2.5 pollution levels exceeding World Health Organization standards, particularly in major cities like Jakarta. Ornamental plants play a crucial role in improving air quality; however, urban residents often struggle to consistently water them. This study addresses that problem by developing an Internet of Things (IoT)-based smart irrigation system that utilizes the Sugeno fuzzy algorithm to predict the water needs of ornamental plants. The system combines a capacitive soil moisture sensor and a DHT11 temperature-humidity sensor with an ESP8266 microcontroller to monitor environmental conditions. Data is transmitted to Firebase and visualized in an Android application, which provides real-time monitoring and specific volume recommendations ranging from 10 ml to 240 ml, calibrated for medium-sized plant pots which is also based on 27 fuzzy rules derived from three input parameters: air temperature, humidity, and soil moisture. Real-world testing with the Aglaonema Snow White plant confirmed that the system functions reliably, helping users optimize water usage and support sustainable, data-driven plant care in urban environments. The system achieved an average prediction accuracy of 89.14% and a mean absolute error of 7.6% in guiding soil moisture toward a 70% target, confirming its practical effectiveness. While the system was tested on Aglaonema Snow White, the fuzzy rule base can be recalibrated for other ornamental plant species with different water needs.