Back

Integrating Artificial Intelligence and Machine Learning to Forecast Air Pollution Impacts on Climate Variability and Public Health

Shafaghat, A.

2025-11-03 bioinformatics
10.1101/2025.10.31.685968 bioRxiv
Show abstract

This study presents a machine learning based simulation for predicting air pollution impact on climate temperature fluctuations and human health. Using synthetic data generated through statistical modeling, seven types of air pollution sources and seven key pollutants were simulated. Machine learning models, including Random Forest, XGBoost, Neural Networks, and others, were applied to evaluate the correlation between pollution levels, air quality index (AQI), and predicted health impacts. Results indicate strong predictive capabilities of ensemble models for environmental monitoring, demonstrating accuracy levels between 70 to 99%. This approach provides a scalable framework for forecasting pollution-driven health risks where measured data are unavailable.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 13%
14.0%
Similar papers in this journal
2
Science of The Total Environment
○ 186 papers in training set
Top 0.2%
13.8%
Similar papers in this journal
3
Environment International
○ 43 papers in training set
Top 0.1%
10.4%
Similar papers in this journal
4
Environmental Science & Technology Letters
● 21 papers in training set
Top 0.1%
5.9%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 15%
5.5%
Similar papers in this journal
6
International Journal of Environmental Research and Public Health
○ 128 papers in training set
Top 1%
4.3%
50% of probability mass above
7
Ecotoxicology and Environmental Safety
○ 10 papers in training set
Top 0.1%
3.4%
8
PLOS Computational Biology
● 1863 papers in training set
Top 11%
2.8%
9
PeerJ
◐ 308 papers in training set
Top 4%
2.3%
10
Bioinformatics
◐ 1204 papers in training set
Top 7%
1.8%
11
Nature Communications
○ 5641 papers in training set
Top 44%
1.8%
12
Environmental Research
○ 49 papers in training set
Top 0.6%
1.6%
13
The Innovation
○ 13 papers in training set
Top 0.1%
1.4%
14
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 4%
1.2%
15
Indoor Air
○ 10 papers in training set
Top 0.1%
1.2%
16
Environmental Health Perspectives
● 17 papers in training set
Top 0.3%
1.2%
17
eClinicalMedicine
○ 77 papers in training set
Top 2%
1.1%
18
Environmental Pollution
○ 37 papers in training set
Top 0.9%
1.1%
19
Environmental Science & Technology
● 64 papers in training set
Top 0.9%
1.1%
20
Remote Sensing
○ 10 papers in training set
Top 0.2%
1.1%
21
One Health
○ 29 papers in training set
Top 0.5%
1.0%
22
Royal Society Open Science
● 214 papers in training set
Top 6%
0.9%
23
Chemical Research in Toxicology
● 10 papers in training set
Top 0.3%
0.9%
24
Water Research
○ 79 papers in training set
Top 1%
0.7%
25
mSystems
● 394 papers in training set
Top 6%
0.7%
26
Toxicology and Applied Pharmacology
○ 14 papers in training set
Top 0.3%
0.7%
27
The Journal of the Acoustical Society of America
● 35 papers in training set
Top 0.3%
0.7%
28
Patterns
○ 78 papers in training set
Top 3%
0.5%
29
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.5%
30
Journal of Neurotrauma
○ 31 papers in training set
Top 0.6%
0.5%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.