Prof. Pasquale Avino, University of Molise, Italy

Bio: Pasquale Avino received his Master Degree in Chemistry in 1992 and his Ph.D. in Chemical Sciences at the University of Rome “La Sapienza” in 1997. He was appointed as Post-Doc (1997-1998) at the Department of Chemistry of the University of California, Irvine (UCI) in the Rowland (Nobel Prize in chemistry in 1995) and Blake group. From 1999 until January 2018, he was appointed as Researcher at the ISPESL/INAIL Research Center and from February 2018 to January 2021 Prof. Avino was appointed as Three-years Term Researcher contract and from February 2021 he is currently Associate Professor at the Department of Agricultural, Environmental and Food Sciences of the University of Molise, Campobasso, in Analytical Chemistry and Environmental Chemistry. He is following the studies devoted to the development of innovative analytical methodologies for development and application of analytical and sampling methods for the qualitative and quantitative determination of chemical compounds (e.g., contaminants, pollutants, nutrients) in food, agricultural, biological and anthropogenic matrices.

He was the recipient of the “Group Achievement NASA Award” in 1998. In 1998 he was awarded with the “Next Generation Award” during the 22nd International Symposium on Chromatography. In 2003 he was the recipient of the “Environmental Sapio” Award for his research in the environmental field. In 2022 he received the Medal for Ecology from the Moldavian Chemical Society. In 2024 he received the highest honor of the Institute of Ecotoxicology and Environmental Sciences (IE&ES), the “Fellowship Award” for your outstanding contribution to the society through the field of environmental science.

Prof. Avino is author and co-author of different scientific publications including original papers published on national and international journals and books (from Scopus data-base, https://www.scopus.com/authid/detail.uri?authorId=55916508700: 231 papers, 4722 citations, hindex 41).

Speech Title: Artificial Intelligence for Air Quality Assessment and Management: Current Challenges, Emerging Applications, and Future Perspectives

Abstract: Air quality—both indoors and outdoors—has become one of the most urgent and multifaceted environmental issues of our time, attracting growing concern from scientists, policymakers, and the public alike. The increasing body of research underscores how deeply air pollution affects not only human health, but also social and economic stability on a global scale (Wu et al., 2024). Exposure to pollutants such as particulate matter, nitrogen oxides, and volatile organic compounds is now recognized as a leading contributor to respiratory and cardiovascular diseases, cognitive decline, and premature mortality. Beyond health, deteriorating air quality exacerbates environmental degradation, influencing climate dynamics and reducing overall quality of life in urban and rural areas alike.

Despite considerable scientific progress and the establishment of monitoring networks worldwide, the field of air quality research continues to face significant challenges. Many key variables—such as pollutant dispersion, source attribution, and chemical transformations in the atmosphere—remain difficult to quantify with precision. The prediction of short-term pollution peaks or long-term concentration trends is complicated by the intricate interplay of meteorological, geographical, and anthropogenic factors (Jin et al., 2022). These complexities highlight the limitations of conventional monitoring and modeling approaches, which often struggle to capture non-linear relationships and spatial variability at fine scales.

In recent years, artificial intelligence (AI) has emerged as a transformative ally in addressing these limitations. A growing number of studies (Amin Al-Habaibeh et al., 2024) demonstrate the capacity of AI to revolutionize air quality monitoring and forecasting systems. Machine learning and deep learning algorithms have been successfully applied to tasks such as vehicle detection, traffic volume estimation, and pollutant concentration prediction, often achieving levels of accuracy that surpass those of traditional statistical methods prone to human error and data gaps. Furthermore, AI offers the ability to process vast amounts of heterogeneous data—from satellite imagery and sensor networks to social media feeds—in near real time, substantially accelerating both data collection and analysis while minimizing anomalies and uncertainty in results.

Among the most promising AI approaches are Decision Trees, Random Forests, Convolutional Neural Networks (CNNs), and hybrid frameworks that combine multiple algorithms to capture complex variable interactions. These methods not only enhance predictive performance but also improve interpretability and scalability across diverse urban and climatic contexts. However, despite their potential, the widespread adoption of AI-based air quality systems remains constrained by several factors, including high computational and equipment costs, limited access to high-quality training datasets, and a persistent shortage of interdisciplinary expertise capable of bridging environmental science and data science (Olawade et al., 2024). Overcoming these barriers will be crucial to fully harnessing the power of AI for cleaner air and healthier, more resilient communities.

.