Machine learningdriven framework for realtime air quality assessment and predictive environmental health risk mapping.

Sci Rep

School of Engineering and Technology, Sunway University, No. 5, Jalan Universiti, Bandar Sunway, 47500, Petaling Jaya, Selangor Darul Ehsan, Malaysia.

Published: August 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

This research introduces a practical and innovative approach for real-time air quality assessment and health risk prediction, focusing on urban, industrial, suburban, rural, and traffic-heavy environments. The framework integrates data from multiple sources, including fixed and mobile air quality sensors, meteorological inputs, satellite data, and localised demographic information. Using a combination of machine learning techniques such as Random Forest, Gradient Boosting, XGBoost, and Long Short-Term Memory (LSTM) networks the system predicts pollutant concentrations and classifies air quality levels with high temporal accuracy. Interpretability is achieved through SHAP analysis, which provides insight into the most influential environmental and demographic variables behind each prediction. A cloud-based architecture enables continuous data flow and live updates through a web dashboard and mobile alert system. Visual risk maps and health advisories are generated every five minutes to support timely decision-making. The framework not only forecasts pollution trends but also identifies vulnerable populations through spatial overlays. Future validation will include real-world sensor deployment and comparison with health impact records to ensure both scientific accuracy and community relevance.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12328577PMC
http://dx.doi.org/10.1038/s41598-025-14214-6DOI Listing

Publication Analysis

Top Keywords

air quality
16
quality assessment
8
health risk
8
machine learningdriven
4
learningdriven framework
4
framework realtime
4
air
4
realtime air
4
quality
4
assessment predictive
4

Similar Publications

Aims/hypothesis: Severe hypoglycaemia events (SHE) remain frequent in people with type 1 diabetes despite advanced diabetes technologies. We examined whether time below range (TBR) 3.9 mmol/l (70 mg/dl; TBR70) or 3.

View Article and Find Full Text PDF

Background: Climate distress is a psychological reaction to adverse weather events and climate change. These events can increase people's vulnerability to develop psychiatric disorders like anxiety, depression, and PTSD particularly in disaster-prone regions like India.

Aim: To explore the relationship between climate distress and psychological impact with a particular emphasis on women, elderly, and other at risk populations who owing to their health vulnerabilities, lack of resources or social roles that make them dependent on others, experience stress in the face of climate change.

View Article and Find Full Text PDF

Differences in physicochemical and functional properties of from-concentrate and not-from-concentrate apple pomace: an investigation based on different drying methods.

J Sci Food Agric

September 2025

Key Laboratory of Agricultural Product Processing and Storage, Ministry of Agriculture and Rural Affairs, Institute of Food Science and Technology, Chinese Academy of Agricultural Sciences (CAAS), Beijing, China.

Background: Apple pomace (AP), a byproduct of apple processing, is nutrient-rich, and its properties are influenced by both the quality of the apples and the juice extraction process. Drying technology can enhance its economic utilization. This study compared the effects of industrial drum drying (ID) and laboratory hot-air drying, heat pump drying and freeze drying (FD) on the physicochemical, functional and structural properties of from-concentrate AP (FC-AP) and not-from-concentrate AP (NFC-AP).

View Article and Find Full Text PDF

Epidemiological studies have already established associations between air pollutants and adverse health outcomes, but the causal associations between air pollutants and chest pain (CP) and gingival pain (GP) remain unclear. This study aimed to explore the potential causal effects of air pollutants on CP and GP. Utilizing genome-wide association study summary statistics from European-ancestry populations, we conducted bidirectional two-sample Mendelian randomization (MR) analyses.

View Article and Find Full Text PDF

This study compared the effects of phosphorylated modified long-chain inulin (PF) with low (PF1), medium (PF3), and high (PF6) degrees of substitution on the rheological, thermal, gluten network depolymerization characteristics, and microstructure of unfrozen and frozen dough. The results showed that PF increased G', G", Tp, and ΔH of unfrozen and frozen dough. Gluten protein analysis revealed that PF significantly increased the SS and α-helix content in gluten, with 3 %FPF3 showing an 11.

View Article and Find Full Text PDF