Since graphene is a miracle material of the 21st century, a considerable number of researchers have studied the oxidation of graphite to synthesize graphene oxide and its applications. In this study, polymeric resin (amberlite XAD7HP) supported graphene oxide (GO) nanocomposite was synthesized successfully. Analytical methods, namely Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), and scanning electron microscopy (SEM) were utilized to characterize the new structure. Methylene blue (MB) solution was selected as a model discharged textile wastewater for adsorption application of synthesized nanocomposite. The adsorption data were modelled by response surface methodology (RSM), random forest (RF) and artificial neural networks (ANN) methods. The optimal condition parameters, which maximize the adsorption uptake capability, were determined by the genetic algorithm. Statistical errors and correlation coefficient values of each developed model were calculated independently to compare models’ performance. According to the results, the developed RF model outperformed the other models. On the other hand, the ANN model had the lowest correlation coefficient value among the models.

中文翻译：

---

氧化石墨烯/琥珀石纳米复合材料上快速有效的亚甲基蓝吸附：优化技术的评估和比较

由于石墨烯是21世纪的奇迹材料，相当多的研究人员对石墨氧化合成氧化石墨烯及其应用进行了研究。在这项研究中，聚合物树脂（amberlite XAD7HP）负载的氧化石墨烯（GO）纳米复合材料被成功合成。利用分析方法，即傅里叶变换红外光谱 (FTIR)、X 射线衍射 (XRD) 和扫描电子显微镜 (SEM) 来表征新结构。选择亚甲蓝（MB）溶液作为排放纺织废水的模型，用于合成纳米复合材料的吸附应用。吸附数据通过响应面方法 (RSM)、随机森林 (RF) 和人工神经网络 (ANN) 方法建模。使吸附吸收能力最大化的最佳条件参数，由遗传算法确定。独立计算每个开发模型的统计误差和相关系数值以比较模型的性能。根据结果​​，开发的 RF 模型优于其他模型。另一方面，ANN 模型在模型中具有最低的相关系数值。