Harmful algal bloom (HAB) events have alarmed authorities of human health that have caused severe illness and fatalities, death of marine organisms, and massive fish killings. This work aimed to perform the long short-term memory (LSTM) method and convolution neural network (CNN) method to predict the HAB events in the West Coast of Sabah. The results showed that this method could be used to predict satellite time series data in which previous studies only used vector data. This paper also could identify and predict whether there is HAB occurrence in the region. A chlorophyll a concentration (Chl-a; mg/L) variable was used as an HAB indicator, where the data were obtained from MODIS and GEBCO bathymetry. The eight-day dataset interval was from January 2003 to December 2018. The results obtained showed that the LSTM model outperformed the CNN model in terms of accuracy using RMSE and the correlation coefficient r as the statistical criteria.
Lower temperature biohydrogen production has always been attractive, due to the lower energy requirements. However, the slow metabolic rate of psychrotolerant biohydrogen-producing bacteria is a common problem that affects their biohydrogen yield. This study reports on the improved substrate synthesis and biohydrogen productivity by the psychrotolerant Klebsiella sp. strain ABZ11, isolated from Antarctic seawater sample. The isolate was screened for biohydrogen production at 30°C, under facultative anaerobic condition. The isolate is able to ferment glucose, fructose and sucrose with biohydrogen production rate and yield of 0.8 mol/l/h and 3.8 mol/g, respectively at 10 g/l glucose concentration. It also showed 74% carbohydrate uptake and 95% oxygen uptake ability, and a wide growth temperature range with optimum at 37°C. Klebsiella sp. ABZ11 has a short biohydrogen production lag phase, fast substrate uptake and is able to tolerate the presence of oxygen in the culture medium. Thus, the isolate has a potential to be used for lower temperature biohydrogen production process.