Artificial Intelligence for Ecological Discovery, Biodiversity, and Ecosystem Dynamics

Ecology and evolution are entering a data-intensive era driven by rapid advances in Earth observation, automated biodiversity monitoring, environmental sensor networks, environmental DNA (eDNA), and ecological informatics. These developments provide unprecedented opportunities to investigate ecological and evolutionary processes across spatial and temporal scales. At the same time, accelerating climate change, biodiversity loss, habitat degradation, and biological invasions have increased the need for more accurate ecological prediction and adaptive management. Artificial intelligence (AI) has emerged as a powerful tool for analysing complex ecological datasets, identifying patterns across multiple scales, and addressing processes that were previously difficult to quantify. Recent studies demonstrate the potential of machine learning and deep learning for biodiversity monitoring, species distribution modelling, ecological forecasting, and the analysis of ecosystem dynamics. However, challenges remain regarding data quality and bias, model transferability, interpretability, reproducibility, uncertainty quantification, and the integration of AI outputs with ecological and evolutionary theory. Further investigation is therefore needed to ensure that AI advances ecological understanding rather than functioning solely as a predictive or computational tool.This Research Topic aims to advance ecological and evolutionary research by integrating AI with ecological theory, biodiversity science, evolutionary biology, and ecosystem analysis. We seek studies that use AI to reveal ecological and evolutionary mechanisms, improve biodiversity monitoring, understand species interactions and ecosystem dynamics, forecast ecological responses to global change, and support conservation and sustainable ecosystem management. We particularly encourage research that evaluates the ecological meaning, limitations, uncertainty, and transferability of AI-based approaches, and that bridges computational innovation with testable hypotheses and improved understanding of ecological and evolutionary processes.To gather further insights into the application of AI to ecological and evolutionary processes across terrestrial, freshwater, coastal, and marine ecosystems, this Research Topic will focus on studies with clear ecological or evolutionary relevance and will not be limited to the development of AI methods without demonstrated applications or implications for these fields. We welcome articles addressing, but not limited to, the following themes:o AI-supported biodiversity monitoring and conservationo Species distribution, habitat, and occupancy modellingo Remote sensing and automated ecological observationo Environmental DNA and other molecular biodiversity applicationso Community ecology and species interaction networkso Ecosystem functioning, stability, and resilienceo Evolutionary ecology, adaptation, and responses to environmental changeo Ecological forecasting under climate change and other global change driverso Biological invasions and the prediction of invasion risko Integration of multi-source ecological and evolutionary datao Machine learning, deep learning, and foundation models for ecology and evolutiono Explainable, interpretable, and uncertainty-aware AI in ecological researcho Ecological digital twins and data-driven ecosystem analysiso Reproducible, transferable, and ethically responsible AI approacheso Applications of AI to biodiversity conservation, ecosystem management, and ecological predictionWe welcome Original Research, Review, Mini Review, Methods, Perspective, and Data Report articles that provide methodological innovation, ecological or evolutionary insights, or practical applications for biodiversity conservation, ecosystem management, and ecological prediction.This Research Topic is part of a series developed in collaboration with the 1st International Conference on Artificial Intelligence for Ecology and Environment. Explore the companion topics in this series: Artificial Intelligence for Environmental Monitoring, Prediction, and Sustainable Ecosystem Management, Frontiers in Environmental Science.Artificial Intelligence for Forest Monitoring, Resilience, and Sustainable Management under Global Change, Frontiers in Forests and Global Change. Topic editors: Jinran Wu, Jie Gao, Si Wu Source: https://www.frontiersin.org/research-topics/84605/artificial-intelligence-for-ecological-discovery-biodiversity-and-ecosystem-dynamics