Novel Surrogates for Membrane Fouling and the Application of Support Vector Machine in Analyzing Fouling Mechanism.

It is difficult to recognize specific fouling mechanisms due to the complexity of practical feed water, thus the current studies usually employ foulant surrogates to carry out research, such as alginate and xanthan gum. However, the representativeness of these surrogates is questionable. In this work, the classical surrogates (i.e., alginate and xanthan gum) were systematically studied, and results showed that they behaved differently during filtration. For the mixture of alginate and xanthan gum, both filtration behaviors and adsorption tests performed by quartz-crystal microbalance with dissipation monitoring (QCM-D) indicated that alginate plays a leading role in fouling development. Furthermore, by examining the filtration behaviors of extracellular polymeric substances (EPS) extracted from practical source water, it turns out that the gel layer formation is responsible for EPS fouling, and the properties of gel layer formed by EPS share more similarities with that formed from pectin instead of alginate. In addition, with the use of experimental data sets extracted from this study and our previous studies, a modeling method was established and tested by the support vector machine (SVM) to predict complex filtration behaviors. Results showed that the small differences of fouling mechanisms lying between alginate and pectin cannot be recognized by Hermia's models, and SVM can show a discrimination as high as 76.92%. As such, SVM may be a powerful tool to predict complex filtration behaviors.

Hyperspectral Imaging for Identification of an Invasive Plant Mikania micrantha Kunth.

Mile-a-minute weed (Mikania micrantha Kunth) is considered as one of top 100 most dangerous invasive species in the world. A fast and accurate detection technology will be needed to identify M. micrantha. It will help to mitigate the extensive ecologic and economic damage on our ecosystems caused by this alien plant. Hyperspectral technology fulfills the above requirement. However, when working with hyperspectral images, preprocessing, dimension reduction, and classifier are fundamental to achieving reliable recognition accuracy and efficiency. The spectral data of M. micrantha were collected using hyperspectral imaging in the spectral range of 450-998 nm. A different combination of preprocessing methods, principal component analysis (for dimension reduction), and three classifiers were used to analyze the collected hyperspectral images. The results showed that a combination of Savitzky-Golay (SG) smoothing, principal component analysis (PCA), and random forest (RF) achieved an accuracy (A) of 88.71%, an average accuracy (AA) of 88.68%, and a Kappa of 0.7740 with an execution time of 9.647 ms. In contrast, the combination of SG, PCA and a support vector machine (SVM) resulted in a weaker performance in terms of A (84.68%), AA(84.66%), and Kappa (0.6934), but with less execution time (1.318 ms). According to the requirements for specific identification accuracy and time cost, SG-PCA-RF and SG-PCA-SVM might represent two promising methods for recognizing M. micrantha in the wild.