Centre for Green Technology, School of Civil and Environmental Engineering, University of Technology Sydney, NSW 2007, Australia.
Centre for Green Technology, School of Civil and Environmental Engineering, University of Technology Sydney, NSW 2007, Australia.
Bioresour Technol. 2022 Jan;343:126111. doi: 10.1016/j.biortech.2021.126111. Epub 2021 Oct 11.
Dark fermentation process for simultaneous wastewater treatment and H production is gaining attention. This study aimed to use machine learning (ML) procedures to model and analyze H production from wastewater during dark fermentation. Different ML procedures were assessed based on the mean squared error (MSE) and determination coefficient (R) to select the most robust models for modeling the process. The research showed that gradient boosting machine (GBM), support vector machine (SVM), random forest (RF) and AdaBoost were the most appropriate models, which were optimized by grid search and deeply analyzed by permutation variable importance (PVI) to identify the relative importance of process variables. All four models demonstrated promising performances in predicting H production with high R values (0.893, 0.885, 0.902 and 0.889) and small MSE values (0.015, 0.015, 0.016 and 0.015). Moreover, RF-PVI demonstrated that acetate, butyrate, acetate/butyrate, ethanol, Fe and Ni were of high importance in decreasing order.
用于同时进行废水处理和氢气生产的暗发酵工艺正受到关注。本研究旨在使用机器学习（ML）程序来模拟和分析暗发酵过程中从废水中生产氢气。根据均方误差（MSE）和确定系数（R）评估了不同的 ML 程序，以选择最稳健的模型来对该过程进行建模。研究表明，梯度提升机（GBM）、支持向量机（SVM）、随机森林（RF）和自适应增强（AdaBoost）是最合适的模型，这些模型通过网格搜索进行了优化，并通过排列变量重要性（PVI）进行了深入分析，以确定过程变量的相对重要性。所有四个模型在预测氢气生产方面均表现出良好的性能，具有较高的 R 值（0.893、0.885、0.902 和 0.889）和较小的 MSE 值（0.015、0.015、0.016 和 0.015）。此外，RF-PVI 表明，按降序排列，乙酸盐、丁酸盐、乙酸盐/丁酸盐、乙醇、Fe 和 Ni 具有较高的重要性。
