Department of Civil Engineering, Sri Lanka Institute of Information Technology, Sri Lanka.
Department of Civil Engineering, Sri Lanka Institute of Information Technology, Sri Lanka.
Environ Pollut. 2024 Sep 15;357:124389. doi: 10.1016/j.envpol.2024.124389. Epub 2024 Jun 19.
This research utilized machine learning to analyze experiments conducted in an open channel laboratory setting to predict microplastic transport with varying discharge, velocity, water depth, vegetation pattern, and microplastic density. Four machine learning (ML) models, incorporating Random Forest (RF), Decision Tree (DT), Extreme Gradient Boost (XGB) and K-Nearest Neighbor (KNN) algorithms, were developed and compared with the Linear Regression (LR) statistical model, using 75% of the data for training and 25% for validation. The predictions of ML algorithms were more accurate than the LR, while XGB and RF provided the best predictions. To explain the ML results, Explainable artificial intelligence (XAI) was employed by using Shapley Additive Explanations (SHAP) to predict the global behavior of variables. RF was the most reliable model, with a coefficient of correlation of 0.97 and a mean absolute percentage error of 1.8% after hyperparameter tuning. Results indicated that discharge, velocity, water depth, and vegetation all influenced microplastic transport. Discharge and vegetation enhanced and reduced microplastic transport, respectively, and showed a response to different vegetation patterns. A strong linear positive correlation (R = 0.8) was noted between microplastic density and retention. In the absence of dedicated microplastic transport analytical models and infeasibility of using classical sediment transport models in predicting microplastic transport, ML proved to be helpful. Moreover, the use of XAI will reduce the black-box nature of ML models with effective interpretation enhancing the trust of domain experts in ML predictions. The developed model offers a promising tool for real-world open channel predictions, informing effective management strategies to mitigate microplastic pollution.
本研究利用机器学习分析在明渠实验室环境中进行的实验，以预测不同流量、流速、水深、植被模式和微塑料密度下的微塑料迁移。开发了四种机器学习 (ML) 模型，包括随机森林 (RF)、决策树 (DT)、极端梯度提升 (XGB) 和 K-最近邻 (KNN) 算法，并与线性回归 (LR) 统计模型进行了比较，使用 75%的数据进行训练，25%的数据进行验证。ML 算法的预测比 LR 更准确，而 XGB 和 RF 提供了最佳预测。为了解释 ML 结果，使用 Shapley 加法解释 (SHAP) 通过可解释人工智能 (XAI) 来预测变量的全局行为。经过超参数调整后，RF 是最可靠的模型，相关系数为 0.97，平均绝对百分比误差为 1.8%。结果表明，流量、流速、水深和植被都对微塑料迁移有影响。流量和植被分别增强和减少了微塑料的迁移，并对不同的植被模式表现出不同的响应。微塑料密度和保留之间存在很强的线性正相关关系 (R = 0.8)。在缺乏专门的微塑料迁移分析模型和在预测微塑料迁移时使用经典泥沙迁移模型不可行的情况下，ML 被证明是有用的。此外，XAI 的使用将降低 ML 模型的黑盒性质，通过有效解释增强领域专家对 ML 预测的信任。所开发的模型为明渠实际预测提供了一个有前途的工具，为制定有效的管理策略以减轻微塑料污染提供了信息。
