首页|ENHANCED URBAN ENVIRONMENTAL MONITORING NETWORKS: AI-DRIVEN PREDICTIVE ANALYTICS FOR POLLUTION HOTSPOT IDENTIFICATION

ENHANCED URBAN ENVIRONMENTAL MONITORING NETWORKS: AI-DRIVEN PREDICTIVE ANALYTICS FOR POLLUTION HOTSPOT IDENTIFICATION

扫码查看
原文链接
  • NETL
  • NSTL
The rapid urbanisation of urban environments faces significant increment in the PM_(2.5) levels, influencing major health and environmental problems. The existing models often struggles to precisely forecasting the pollution levels and their inability to integrate the various datasets and estimate more intricate relationship between the climatic variables and the past pollution data. To overcome this limitation, the proposed system innovati vely employs a deep learning (DL) techniques, of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, to enhance PM_(2.5) accurate predictions. The proposed model efficiently learns the both historical and real-time data using the hybrid design, integrating the temporal sequence modelling of LSTMs with the spatial feature extraction using CNNs. The system employs a numerous data sources of past pollution records and climate change data (such wind direction, speed, and precipitation), to detect temporal and spatial patterns in air quality. After that, the pre-processing process is enabled to remove the missing values and improve the dataset's quality and ensure the model performance using data pre-processing techniques. The proposed system offers appropriate insights into the pollution dynamics, ensures an efficient pollution control plans and well-informed urban decision-making. Overall, the above results include an improved prediction accuracy and enhanced identification of pollution hotspots that contributes better air quality management and public health outcomes in urban environments.

urban environmentsdeep learningConvolutional Neural Networks (CNN)Long Short-Term Memory (LSTM)air quality monitoringpollution management

C. KOTTEESWARAN、S. SHEEBA RANI、RAENU KOLANDAISAM Y、ARUN ANTHONISAMY、A. MADHAN KUMAR、ASAN MOHIDEEN KHANSADURAI

展开 >

Department of Computer Science and Engineering, School of Computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, 600 062 Chennai, Tamil Nadu, India

Department of Electronics and Communication Engineering, Sri Eshwar College of Engineering, 641 202 Coimbatore, Tamil Nadu, India

Institute of Computer Science and Digital Innovation, UCSI University, Taman Connaught, 56 000 Kuala Lumpur, Wilayah Persekutuan, Kuala Lumpur, Malaysia

Department of Computer Science and Business System, Panimalar Engineering College, 600 123 Chennai, Tamil Nadu, India

Department of Mechanical Engineering, Saveetha Engineering College (Autonomous), Thandalam, 602 105 Chennai, Tamil Nadu, India

Department of Electronics and Communication Engineering, Sudharsan Engineering College, 622 501 Pudukkottai, Tamil Nadu, India

展开 >

2024

Journal of environmental protection and ecology

Journal of environmental protection and ecology

ISSN：1311-5065
年,卷(期)：2024.25(8)