IoT-Enabled Dual-Sensing Smart Waste Management System: Enhancing Urban Cleanliness and Sustainability in Smart Cities

The management of trash in urban areas encounters substantial obstacles because of the increasing population density and ineffective collection methods, resulting in environmental and health risks in urban cities. Current Internet of Things solutions generally concentrate on monitoring bin fill levels, but fail to include important factors such as garbage decomposing and route optimization. This study presents a novel data-driven artificial intelligence method for garbage management by combining dual-sensing smart bins with real-time analytics. The system we use utilizes ultrasonic sensors to detect the fill-level and methane sensors to monitor spoiling in bins located in Dehiwala, Sri Lanka. The data is transmitted by ESP32 WiFi modules to a cloud-based platform. An individualized Node-RED integration enables the processing of data, while machine learning models enhance the efficiency of collection routes and forecast trends of trash generation. During the pilot implementation involving three smart bins over a four-month duration, the system exhibited several critical capabilities: precise real-time fill-level detection with 95% accuracy, dependable spoilage monitoring with 92% accuracy in methane detection, and effective pattern recognition for weekly and monthly waste generation trends. The route optimization technique demonstrated a 15% enhancement in path efficiency relative to fixed routes during simulation testing. Analysis of temporal patterns identified constant peak fill times and spoiling trends, facilitating predictive scheduling possibilities. This study demonstrates the capacity of data-driven intelligence formulate a paradigm for scalable intelligent waste management systems, showcasing the potential for biogas system integration and adaptive capacity planning.