AI and machine learning in environmental monitoring: enhancing legal compliance and public trust
Environment and Social Psychology · 18.11.2025 · 10 (11)
DOI: 10.59429/esp.v10i11.4109 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environment and Social Psychology, online erschienen am 18.11.2025. Verfasst von Adel Subhe Abedalkader Abraheem und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
As environmental pollution becomes more complex over the years, finding effective monitoring methods becomes crucial. In real-time monitoring, artificial intelligence (AI) and machine learning (ML) models can be integrated to obtain information about air, water, and soil quality assessment. To improve the accuracy of pollution detection and forecasting, this study proposes a comprehensive framework that integrates IoT-enabled sensor networks, predictive AI models, and statistical validation techniques. The article assesses the relative performance of Gradient Boosting Machines (GBM), Long Short-Term Memory (LSTM) networks, and Transformer-based split networks to predict environmental changes. The study was conducted across multi-domain urban, suburban, and rural monitoring zones using multimodal datasets derived from IoT sensors, remote sensing streams, and laboratory-validated environmental indicators. Similar integrated AI–IoT ecological monitoring strategies have been highlighted in recent literature as essential for sustainable environmental protection and high-fidelity pollution forecasting. The dataset comprised 216 air samples, 144 water samples, and 96 soil assays collected from three monitoring regions. Results show that PM2.5 concentrations decreased by 12% (p < 0.01), water turbidity declined by 15% (p < 0.01), and lead levels in soil were reduced by up to 16.1% in agricultural sites. The GBM model achieved the highest predictive performance with Root Mean Square Error (RMSE) = 2.1 µg/m³, Coefficient of Determination (R²) = 0.94, and F1-Score = 92.0%, outperforming LSTM and Transformer models. Beyond technical performance, this study also highlights the legal and societal dimensions of AI-driven monitoring. By improving accuracy and transparency, these systems strengthen regulatory compliance frameworks while fostering public trust in environmental governance. Understanding how citizens and policymakers perceive the reliability of AI-based platforms is essential to ensuring policy acceptance and compliance behavior. This dual perspective—technological and psychological—illustrates that sustainable outcomes depend not only on advanced algorithms but also on social legitimacy and institutional accountability.
Zitieren
APA
Abraheem, A. S. A., Abbas, J. K., Ahmed, D. K. I., Abbas, N. H., Khalil, B. M., & Ponochovnyi, P. (2025). AI and machine learning in environmental monitoring: enhancing legal compliance and public trust. Environment and Social Psychology, 10(11). https://doi.org/10.59429/esp.v10i11.4109
Vancouver
Abraheem ASA, Abbas JK, Ahmed DKI, Abbas NH, Khalil BM, Ponochovnyi P. AI and machine learning in environmental monitoring: enhancing legal compliance and public trust. Environment and Social Psychology. 2025;10(11). doi:10.59429/esp.v10i11.4109
BibTeX
@article{Abraheem2025,
author = {Abraheem, Adel Subhe Abedalkader and Abbas, Jameela Khedher and Ahmed, Duha Khalil Ibrahim and Abbas, Nazar Habeeb and Khalil, Baker Mohammed and Ponochovnyi, Petro},
title = {AI and machine learning in environmental monitoring: enhancing legal compliance and public trust},
journal = {Environment and Social Psychology},
year = {2025},
volume = {10},
number = {11},
doi = {10.59429/esp.v10i11.4109}
}
EUVIMED