Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier’s abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

Present study evaluated the low-temperature destruction of n-hexane and benzene using mesh-type transition-metal platinum(Pt)/stainless steel(SS) catalyst. The parameters tested for the evaluation of catalytic destruction efficiencies of the two volatile organic compounds(VOC) included input concentration, reaction time, reaction temperature, and surface area of catalyst. It was found that the input concentration affected the destruction efficiencies of n-hexane and benzene, but that this input-concentration effect depended upon VOC type. The destruction efficiencies increased as the reaction time increased, but they were similar between two reaction times for benzene(50 and 60 sec), thereby suggesting that high temperatures are not always proper for thermal destruction of VOCs, when considering the destruction efficiency and operation costs of thermal catalytic system together. Similar to the effects of the input concentration on destruction efficiency of VOCs, the reaction temperature influenced the destruction efficiencies of n-hexane and benzene, but this temperature effect depended upon VOC type. As expected, the destruction efficiencies of n-hexane increased as the surface area of catalyst, but for benzene, the increase rate was not significant, thereby suggesting that similar to the effects of the reaction temperature on destruction efficiency of VOCs, high catalyst surface areas are not always proper for economical thermal destruction of VOCs. Depending upon the inlet concentrations and reaction temperatures, almost 100% of both n-hexane and benzene could be destructed. The current results also suggested that when applying the mesh type transition Metal Pt/SS catalyst for the better catalytic pyrolysis of VOC, VOC type should be considered, along with reaction temperature, surface area of catalyst, reaction time and input concentration.