Related Experiment Video
Updated: Jun 5, 2025
05:31
Sampling, Sorting, and Characterizing Microplastics in Aquatic Environments with High Suspended Sediment Loads and Large Floating Debris
Published on: July 28, 2018
16.0K
Predictive modeling of microplastic adsorption in aquatic environments using advanced machine learning models.
1School of Chemical Engineering and Technology, Xi'an Jiaotong University, PR China.
The Science of the Total Environment
|December 15, 2024
Summary
This study reveals that the n-octanol/water distribution coefficient (Log D) is key to predicting organic pollutant interactions with microplastics. The Recurrent Neural Network (RNN) model accurately predicts microplastic dynamics, aiding pollution control.
Area of Science:
- Environmental Science
- Environmental Chemistry
- Computational Chemistry
Background:
- Microplastic pollution poses significant environmental and health risks due to interactions with organic pollutants.
- Understanding the factors governing microplastic-pollutant sorption is crucial for effective environmental management.
Purpose of the Study:
- To investigate the key factors influencing microplastic sorption of organic pollutants.
- To evaluate the performance of various artificial neural network models in predicting microplastic-pollutant interactions.
- To identify the most accurate model for predicting microplastic dynamics.
Main Methods:
- Utilized advanced artificial neural network models: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN).
- Employed a dataset including organic compound composition, n-octanol/water partition coefficient (Log P), covalent acidity, covalent basicity, molecular polarizability to volume ratio, and logarithm of the partition coefficient (Log D).
- Conducted a comparative analysis of model predictions against empirical findings.
Main Results:
- The n-octanol/water distribution coefficient (Log D) is a significant predictor of organic pollutant affinity for microplastics.
- Acidity, molecular polarizability to volume ratio, and covalent basicity profoundly impact microplastic behavior.
- Recurrent Neural Network (RNN) model achieved the highest accuracy (0.967) with the lowest absolute error (0.38) in predicting microplastic dynamics.
- Convolutional Neural Networks (CNNs) demonstrated rapid prediction generation.
Conclusions:
- The RNN model shows exceptional efficacy in predicting microplastic-pollutant interactions, offering a powerful tool for environmental research.
- Accurate modeling of microplastic sorption is vital for understanding pollutant fate in aquatic ecosystems.
- Findings provide a foundation for developing strategies to mitigate microplastic pollution and its associated risks.
Related Concept Videos
01:30Typical Model Studies
340
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
340
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
40
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
40