0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

Artificial Intelligence and Environmental Challenges

2026
Manohar Gowdru Shridhara, Ľubomír Antoni, Gabriel Semanišin, Joachim J. Włodarz, Dijana Oreški, Vjeran Strahonja, Marija Pokos Lukinec, Eugenijus Gabrielius Ivanauskas, Liepa Urbonaitė, Saulius Jokubaitis, Dominykas Vilčinskas, Lukas Voveris, Jolita Bernatavičienė, Ivan Maslov, Agnieszka Głowacka Agnieszka Głowacka, Bartosz Dziewit, Paulina Trybek, Jakub Kraus, Piotr Mika, Mateusz Wiśniewski, Zbigniew Dendzik, Robert Leskovar

Summary

This book pulls together research on how AI can help tackle environmental problems, from predicting solar and wind energy to spotting solar panel malfunctions to simulating how nanoplastics interact with living cells. The bottom line: AI shows real promise, but its usefulness depends heavily on having good-quality data and results that humans can actually understand and trust—especially since decisions about pollution, plastics exposure, and climate ultimately require human judgment, not just algorithms. For everyday health, this matters because better AI tools could eventually improve our ability to track air quality, emissions, and plastic contamination that affect the air we breathe and the

This volume examines where artificial intelligence can provide genuine insight into environmental problems, and at what cost. Across eight chapters, contributors apply machine learning, deep learning, econometric modelling, and computational simulation to a range of pressing challenges: forecasting wind and solar energy output, deploying efficient AI on resource-constrained edge devices, quantifying risk in sustainable finance, detecting faults in photovoltaic installations, analysing air quality and CO₂ emissions data, simulating nanoplastic interactions with biological systems, and modelling urban heat transfer. A recurring theme is the critical importance of data quality — sparse, biased, or poorly curated datasets remain a fundamental obstacle to trustworthy modelling. The volume equally emphasises interpretability, recognising that environmental decision-making is ultimately a human and political process. Taken together, the chapters offer an honest, domain-grounded assessment of the current capabilities and limitations of AI as a tool for addressing environmental challenges.

Share this paper