Timezone-Aware Auto-Regressive Long Short-Term Memory Model for Multipollutant Prediction

Air pollution poses a significant threat to urban environments, and accurate prediction of multiple air pollutants is crucial for effective mitigation strategies. This study introduces a novel time-aware auto-regressive long-short-term memory (TAR LSTM) approach to address this challenge by developing a multivariate prediction model using artificial intelligence (AI) for SMART city applications. Existing models often fall short of predicting all six major criteria pollutants comprehensively. In response, this work proposes an autoregressive (AR) neural network model based on the long short-term memory (LSTM) architecture, which excels in capturing temporal dependencies within sequential data. The proposed method uses the AR model that captures the linear dependencies in the time series, while the LSTM captures the nonlinear dependencies and long-term patterns. This enables the model to consider past pollutant concentrations and their relationships, resulting in a more accurate and dynamic prediction. Rigorous testing on datasets from low-cost air quality sensors (LAQSs) validates the model’s superior performance. Datasets from diverse locations, including India, Malaysia, and the Philippines, contribute to the robustness of the model, showcasing its efficacy in varied urban environments. This research contributes to advancing predictive modeling for air quality, addressing the limitations of previous approaches, and providing a promising solution for SMART city implementations. The findings highlight the AR LSTM model’s potential as a valuable tool for precise and comprehensive air pollution forecasting, which has implications for informed decision making and better urban environmental management.

I. Introduction

Rapid urbanization and the expansion of industrial processes have significantly impacted air quality. In numerous cities across the globe, poor air quality has become a pervasive problem with severe implications for public health and the environment. On the other hand, cutting-edge research and technology are used to meet the essential requirement for air quality in smart cities. Some nations worldwide have identified specific air contaminants to measure air quality. Commonly, six contaminants, including ground-level ozone , sulfur dioxide , particulate matter ( and ), carbon monoxide (CO), and nitrogen dioxide , are categorized as the primary air pollutants. The air quality index (AQI) is a measurement of air quality dependent upon the concentrations of these pollutants. Air quality alerts, health advisories, and targeted measures can minimize the exposure to air pollutants of the general public and safeguard human health by precisely anticipating pollutant concentrations. Internet’s effective monitoring systems and accessibility for customers facilitate the adoption of precautionary measures at the individual level. In addition, multivariate pollutant prediction helps improve environmental management and public health resource allocation. Resources may be redirected toward monitoring, mitigation, and research by selecting the contaminants with the highest health risk. This maximizes intervention efficacy and resource efficiency. Effective multipollutant prediction affects policy, public health, and environmental management. It equips decision makers with vital data to tackle complicated pollution issues, safeguard public health, and create sustainable environmental policy. Hence, this work proposes advancing air quality prediction for SMART city applications by implementing a timezone-aware autoregressive long short-term memory (TAR LSTM) model. The core proposition lies in addressing the inadequacies of existing models by leveraging the long short-term memory (LSTM)’s capacity to capture and utilize temporal dependencies within sequential air quality data. By focusing on all six major “criteria” pollutants and deploying low-cost sensors in diverse urban environments across India, Malaysia, and the Philippines, our model aims to provide a holistic and adaptable solution. The model’s predictive accuracy is expected to surpass conventional approaches, offering an invaluable tool for urban planners, policymakers, and environmentalists to make informed decisions for improved air quality management. This proposition contributes to the scientific understanding of air pollution dynamics and holds practical implications for the sustainable development of SMART cities globally.