Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models
Understanding the causal mechanisms underlying PM2.5 generation is critical for developing effective prevention strategies, necessitating an approach that goes beyond prediction and seeks deeper causal explanations to support decision-making. This study addresses these concerns through a novel causa...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125001244 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725397223079936 |
|---|---|
| author | Mallika Kliangkhlao Apaporn Tipsavak Thanathip Limna Racha Dejchanchaiwong Perapong Tekasakul Kirttayoth Yeranee Thanyabun Phutson Bukhoree Sahoh |
| author_facet | Mallika Kliangkhlao Apaporn Tipsavak Thanathip Limna Racha Dejchanchaiwong Perapong Tekasakul Kirttayoth Yeranee Thanyabun Phutson Bukhoree Sahoh |
| author_sort | Mallika Kliangkhlao |
| collection | DOAJ |
| description | Understanding the causal mechanisms underlying PM2.5 generation is critical for developing effective prevention strategies, necessitating an approach that goes beyond prediction and seeks deeper causal explanations to support decision-making. This study addresses these concerns through a novel causal artificial intelligence framework employing structural causal models (SCMs) to interpret PM2.5 dynamics. The research uncovers hidden cause-and-effect relationships between meteorological factors and PM2.5 exposure by leveraging a data-driven causal structure discovery approach, effectively representing complex data-generating processes. The proposed SCMs undergo systematic validation across two critical dimensions: demonstrating human-like intelligence understanding and achieving significant alignment with real-world observations. The PC-based SCM is particularly outstanding when compared to other algorithms like GES- and Chow-Lui-based SCMs, delivering a remarkable performance in discovering cause-and-effect relationships with an F-measure of approximately 80 % compared to the gold-standard SCM. Statistical validation provided robust evidence of the model's reliability, with fit indices—including NFI, TLI, CFI, GFI, and AGFI—reaching approximately 0.98 and RMSEA approximating 0.05. These findings demonstrate that SCM can encode human-like reasoning and naturally align with real-world meteorological systems. This method is especially effective for urban air quality monitoring, where accessible meteorological data and transparent causal relationships are essential. Its capacity to inform evidence-based policy decisions makes it a powerful tool for creating intelligent decision-support systems in PM2.5 analysis and environmental mitigation strategies. |
| format | Article |
| id | doaj-art-582fb0df8c09496ea419ee039f7eaad3 |
| institution | DOAJ |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-582fb0df8c09496ea419ee039f7eaad32025-08-20T03:10:28ZengElsevierEcological Informatics1574-95412025-07-018710311510.1016/j.ecoinf.2025.103115Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal modelsMallika Kliangkhlao0Apaporn Tipsavak1Thanathip Limna2Racha Dejchanchaiwong3Perapong Tekasakul4Kirttayoth Yeranee5Thanyabun Phutson6Bukhoree Sahoh7School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80160, ThailandCollege of Graduate Studies, Walailak University, Tha Sala, Nakhon Si Thammarat 80160, ThailandDepartment of Computer Engineering, Faculty of Engineering, Prince of Songkla University, Songkhla 90110, ThailandDepartment of Chemical Engineering, Faculty of Engineering, Prince of Songkla University, Songkhla 90110, ThailandDepartment of Mechanical and Mechatronics Engineering, Faculty of Engineering, Prince of Songkla University, Songkhla 90110, Thailand; Department of Computer Engineering, Faculty of Engineering, Prince of Songkla University, Songkhla 90110, ThailandSchool of Mechanical Engineering, Shanghai Jiao Tong University, Minhang, Shanghai 200240, ChinaSchool of Informatics, Walailak University, Tha Sala, Nakhon Si Thammarat 80160, ThailandSchool of Informatics, Walailak University, Tha Sala, Nakhon Si Thammarat 80160, Thailand; Corresponding author.Understanding the causal mechanisms underlying PM2.5 generation is critical for developing effective prevention strategies, necessitating an approach that goes beyond prediction and seeks deeper causal explanations to support decision-making. This study addresses these concerns through a novel causal artificial intelligence framework employing structural causal models (SCMs) to interpret PM2.5 dynamics. The research uncovers hidden cause-and-effect relationships between meteorological factors and PM2.5 exposure by leveraging a data-driven causal structure discovery approach, effectively representing complex data-generating processes. The proposed SCMs undergo systematic validation across two critical dimensions: demonstrating human-like intelligence understanding and achieving significant alignment with real-world observations. The PC-based SCM is particularly outstanding when compared to other algorithms like GES- and Chow-Lui-based SCMs, delivering a remarkable performance in discovering cause-and-effect relationships with an F-measure of approximately 80 % compared to the gold-standard SCM. Statistical validation provided robust evidence of the model's reliability, with fit indices—including NFI, TLI, CFI, GFI, and AGFI—reaching approximately 0.98 and RMSEA approximating 0.05. These findings demonstrate that SCM can encode human-like reasoning and naturally align with real-world meteorological systems. This method is especially effective for urban air quality monitoring, where accessible meteorological data and transparent causal relationships are essential. Its capacity to inform evidence-based policy decisions makes it a powerful tool for creating intelligent decision-support systems in PM2.5 analysis and environmental mitigation strategies.http://www.sciencedirect.com/science/article/pii/S1574954125001244Explainable artificial intelligenceCausal machine learningStructural equation modelCausal discoveryFine particleMeteorological factor |
| spellingShingle | Mallika Kliangkhlao Apaporn Tipsavak Thanathip Limna Racha Dejchanchaiwong Perapong Tekasakul Kirttayoth Yeranee Thanyabun Phutson Bukhoree Sahoh Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models Ecological Informatics Explainable artificial intelligence Causal machine learning Structural equation model Causal discovery Fine particle Meteorological factor |
| title | Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models |
| title_full | Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models |
| title_fullStr | Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models |
| title_full_unstemmed | Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models |
| title_short | Toward causal artificial intelligence approach for PM2.5 interpretation: A discovery of structural causal models |
| title_sort | toward causal artificial intelligence approach for pm2 5 interpretation a discovery of structural causal models |
| topic | Explainable artificial intelligence Causal machine learning Structural equation model Causal discovery Fine particle Meteorological factor |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125001244 |
| work_keys_str_mv | AT mallikakliangkhlao towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT apaporntipsavak towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT thanathiplimna towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT rachadejchanchaiwong towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT perapongtekasakul towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT kirttayothyeranee towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT thanyabunphutson towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels AT bukhoreesahoh towardcausalartificialintelligenceapproachforpm25interpretationadiscoveryofstructuralcausalmodels |