We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Common issues of data science on the eco-environmental risks of emerging contaminants.
Summary
This review examines common methodological pitfalls in data science approaches to emerging contaminants research, highlighting issues such as data leakage, inadequate ecological complexity, and over-reliance on laboratory data. Researchers argue that future work should integrate ensemble models, spatiotemporal causal frameworks, and field-based validation to close gaps between data-driven predictions and real-world environmental outcomes.
Data-driven approaches (e.g., machine learning) are increasingly used to replace or assist laboratory studies in the study of emerging contaminants (ECs). In the past ten years, an increasing number of models or approaches have been applied to ECs, and the datasets used are continuously enriched. However, there are large knowledge gaps between what we have found and the natural eco-environmental meaning. For most published reviews, the contents are organized by the types of ECs, but the common issues of data science, regardless of the type of pollutant, are not sufficiently addressed. To close or narrow the knowledge gaps, we highlight the following issues ignored in the field of data-driven EC research. Complicated biological and ecological data and ensemble models revealing mechanisms and spatiotemporal trends with strong causal relationships and without data leakage deserve more attention in the future. In addition, the matrix influence, trace concentration, and complex scenario have often been ignored in previous works. Therefore, an integrated research framework related to natural fields, ecological systems, and large-scale environmental problems, rather than relying solely on laboratory data-related analysis, is urgently needed. Beyond the current prediction purposes, data science can inspire the discovery of scientific questions, and mutual inspiration among data science, process and mechanism models, and laboratory and field research is a critical direction. Focusing on the above urgent and common issues related to data, frameworks, and purposes, regardless of the type of pollutant, data science is expected to achieve great advancements in addressing the eco-environmental risks of ECs.
Sign in to start a discussion.
More Papers Like This
Ecological risk assessment of emerging contaminants on soil and terrestrial ecosystems (2005-2024): a bibliometric and scientometric review.
A 20-year (2005–2024) bibliometric review of ecological risk assessment studies on emerging contaminants identified key trends and gaps in understanding the risks of microplastics, pharmaceuticals, and other pollutants to soil and terrestrial ecosystems. The review found rapid growth in the field but persistent data gaps on long-term ecosystem-level effects.
Characterizing Freshwater Ecotoxicity of More Than 9000 Chemicals by Combining Different Levels of Available Measured Test Data with In Silico Predictions
Researchers developed a method combining laboratory toxicity data with computer predictions to estimate the ecological hazards of over 9,000 chemicals in freshwater environments. They found that using even limited experimental data alongside predictive models significantly improved the accuracy of environmental risk assessments. The approach could help regulators better evaluate the ecological impact of the thousands of chemicals, including plastic-related compounds, that currently lack comprehensive toxicity data.
Unraveling the ecotoxicity of micro(nano)plastics loaded with environmental pollutants using ensemble machine learning.
Researchers developed an ensemble machine learning algorithm to predict the ecotoxicity of micro(nano)plastics loaded with environmental pollutants, addressing a key knowledge gap where most studies examine plastic particles alone. The model revealed that co-pollutant loading substantially amplifies toxicity and that particle characteristics govern outcomes.
Environmental Behaviors, Ecological Risks, and Toxic Mechanisms of Emerging and Legacy Contaminants in China: From Distribution to Management
Researchers reviewed the environmental distribution, ecological risks, and toxic mechanisms of both emerging and legacy contaminants in China's aquatic environments, examining how industrialization and urbanization drive the co-occurrence and combined pollution that threatens ecosystem integrity and human health.
Confounding factors in nano and microplastic ecological risk assessment
This review identified and discussed the major confounding factors in micro- and nanoplastic ecotoxicology research, including particle variability, contamination during testing, and inconsistent methodology. The authors highlighted how these confounders lead to discrepancies across studies and outlined best practices for improving data quality and comparability.