Developing a novel water quality prediction model for a South African aquaculture farm
Subjectsaquaculture water quality
Water Quality Index
Subject Categories::H122 Water Quality Control
MetadataShow full item record
AbstractProviding an accurate prediction of water quality parameters for improved water quality management is a topical issue in the aquaculture industry. Conventional prediction methods have shown different challenges like a poor generalization, poor prediction accuracy, and high time complexity. Aiming at these challenges, a novel hybrid prediction model with ensemble empirical mode decomposition (EEMD) and deep learning (DL) long-short term memory (LSTM) neural network is proposed in this paper. In this innovative hybrid EEMD-DL-LSTM model, firstly, the integrity of the datasets is enhanced by applying moving average filtering and linear interpolation techniques of water quality parameter datasets pre-treatment. Secondly, the measured real sensor water quality parameters dataset is decomposed with the aid of the EEMD algorithm into disparate IMFs and a corresponding residual item. Thirdly, a multi-feature selection process is applied to make a careful selection of a strongly correlated group of IMFs with the measured real water quality parameter datasets and integrate them as inputs to the DL-LSTM neural network. The presented model is built on water quality sensor data collected from an Abalone farm in South Africa. The performance of the novel hybrid prediction model is validated by comparing the results against the real datasets. To measure the overall accuracy of the novel hybrid prediction model, different statistical indices, namely the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), are used.
CitationEze E, Halse S, Ajmal T (2021) 'Developing a novel water quality prediction model for a South African aquaculture farm', Water, 13 (13), 1782.
SponsorsInnovate UK/BBSRC (ref: 86204028, BB/S020896/1)
The following license files are associated with this item:
- Creative Commons
Except where otherwise noted, this item's license is described as Green - can archive pre-print and post-print or publisher's version/PDF
Showing items related by title, author, creator and subject.
Water quality investigations of the River Lea (NE London)Patroncini, Deborah (University of BedfordshireUniversity of Bedfordshire, 2013-01)The Lea Navigation in the north-east of London, a canalised reach of the River Lea, is affected by episodes of very low levels of dissolved oxygen. The problem was detected by the Environment Agency in the stretch from the confluence with Pymmes Brook (which receives the final effluent of Deephams sewage treatment works) to the Olympic area (Marshgate Lane, Stratford). In this project, possible causes and sources of the poor water quality in the Lea Navigation have been investigated using a multi-parameter approach. A study of physico-chemical parameters, obtained from Environment Agency automated monitoring stations, gave a clear picture of the poor river water quality at three sites in this reach. River water ecotoxicity to the freshwater alga Pseudokirchneriella subcapitata was determined by algal growth inhibition tests, following the OECD guidelines. Moreover, a novel protocol was developed which involved the use of E. coli biosensors (CellSense) operating at a lower potential than the standard protocol and using pre-concentrated river water samples. This protocol is promising and it has the potential to be a useful tool to determine the toxicity of contaminants at environmental concentrations. Furthermore, the developed protocol is a rapid, easy to perform bioassay, with potential application in achieving the aims of the Water Framework Directive (WFD). In addition to the data from the Environment Agency automatic monitoring stations and the laboratory-based tests, two in situ monitoring approaches were performed: 1) a detailed spatial seasonal monitoring of physico-chemical parameters of river water at twenty-three sites, and 2) algal growth inhibition tests, with algae entrapped in alginate beads, at seven monitoring stations. Results showed chronic pollution, and identified polar compounds in the river water and high bacterial concentrations as possible causes of low dissolved oxygen levels. This study confirmed the negative impact of Deephams STW (throughout Pymmes Brook) on the water quality of the Lea Navigation. However, there was evidence of other sources of pollution, in particular Stonebridge Brook was identified as uncontrolled source of pollution and untreated wastewater. Other possible sources include Old Moselle Brook, diffuse pollution from surface runoff, boat discharges and other undetected misconnections. Finally, in the light of the WFD, this project provides a case study on the investigation of river water quality, providing evidence that the multiparameter approach is reliable, and low cost approach for the monitoring of freshwater bodies.
Evaluating urban surface water quality in LutonAjmal, Tahmina; Anyachebelu, Tochukwu Kene; Conrad, Marc; Rawson, David M.; University of Bedfordshire (Springer, 2019-02-09)Using a single numerical value to indicate the quality of water, a so-called Water Quality Index (WQI) is a well-established way of rating the overall water quality status of a given water body. During the last few years, researchers in the water sector have developed different such indices to address their specific needs. In this study, we attempt to obtain a WQI formula suited for evaluating the water quality of the River Lea. We have selected four different sites on the River Lea and explore the possibility of monitoring using a minimum number of parameters only. The results obtained are very encouraging and provide a strong indication that only three parameters are enough to indicate water quality of a water body.
A 'human-in-the-loop' mobile image recognition application for rapid scanning of water quality test resultsLoudon, Melissa; Ajmal, Tahmina; Rivett, Ulrike; De Jager, Dirk; Bain, Robert Edward Shenton; Matthews, Robert; Gundry, Stephen (British Computer Society, 2009)This paper describes an interactive system for drinking water quality testing in small community supplies, particularly in the developing world. The system combines a low-cost field test (the Aquatest field kit), a mobile phone for data processing and communications, and a human operator who is able to react immediately to a test result. Once a water sample has been collected and incubated, the mobile phone camera is used to 'scan' the test and obtain the result, which is displayed to the user along with information about the health implications of the water quality. Initial prototypes, while not yet sufficiently robust for real-world use, demonstrate that the system is technically feasible. This opens up interesting possibilities for wider use of 'human-in-the-loop' sensor systems in environmental monitoring.