Dissolved Oxygen Concentration Prediction Model Based on WT-MIC-GRU—A Case Study in Dish-Shaped Lakes of Poyang Lake

Chi, Dianwei; Huang, Qi; Liu, Lizhen

doi:10.3390/e24040457

Cited by 7 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current state of water quality will be affected by the previous state of water quality because the water quality cannot plummet or rise at a glance. That is, the factors which influence the water quality are timing sequence [48]. For an ANN, the output of a single hidden layer is only predicted based on the current data.…”

Section: Related Workmentioning

confidence: 99%

“…Ali et al [69] proposed a set of prediction models based on machine learning, deep learning, and statistics for predicting sea surface temperature (SST) and significant wave height (SWH), where in terms of deep learning, the authors used GRU-DNN model architecture. Chi et al [48] used a wavelet transform (WT) to denoise and used maximal information coefficient (MIC) to select features, then used GRU to predict the water quality of the dish-shaped lakes in Poyang Lake of Jiangxi Province, China.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence in Internet of Things System for Predicting Water Quality in Aquaculture Fishponds

Yang¹,

Liao²,

Chou³

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Aquaculture has long been a critical economic sector in Taiwan. Since a key factor in aquaculture production efficiency is water quality, an effective means of monitoring the dissolved oxygen content (DOC) of aquaculture water is essential. This study developed an internet of things system for monitoring DOC by collecting essential data related to water quality. Artificial intelligence technology was used to construct a water quality prediction model for use in a complete system for managing water quality. Since aquaculture water quality depends on a continuous interaction among multiple factors, and the current state is correlated with the previous state, a model with time series is required. Therefore, this study used recurrent neural networks (RNNs) with sequential characteristics. Commonly used RNNs such as long short-term memory model and gated recurrent unit (GRU) model have a memory function that appropriately retains previous results for use in processing current results. To construct a suitable RNN model, this study used Taguchi method to optimize hyperparameters (including hidden layer neuron count, iteration count, batch size, learning rate, and dropout ratio). Additionally, optimization performance was also compared between 5-layer and 7-layer network architectures. The experimental results revealed that the 7-layer GRU was more suitable for the application considered in this study. The values obtained in tests of prediction performance were mean absolute percentage error of 3.7134%, root mean square error of 0.0638, and R-value of 0.9984. Therefore, the water quality management system developed in this study can quickly provide practitioners with highly accurate data, which is essential for a timely response to water quality issues. This study was performed in collaboration with the Taiwan Industrial Technology Research Institute and a local fishery company. Practical application of the system by the fishery company confirmed that the monitoring system is effective in improving the survival rate of farmed fish by providing data needed to maintain DOC higher than the standard value.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence in Internet of Things System for Predicting Water Quality in Aquaculture Fishponds

Yang¹,

Liao²,

Chou³

2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Some studies have been conducted to investigate surface‐groundwater exchange and solute transport in seasonal lakes within floodplain systems (Chi et al., 2022; Huang et al., 2022; Wohl, 2021). Rahman et al.…”

Section: Introductionmentioning

confidence: 99%

“…One illustrative instance is the noticeable shrink of Poyang Lake following an extended period of reduced water levels ensuing from the impoundment of the Three Gorges Dam (Tan, Li, et al, 2019). Some studies have been conducted to investigate surface-groundwater exchange and solute transport in seasonal lakes within floodplain systems (Chi et al, 2022;Huang et al, 2022;Wohl, 2021). Rahman et al (2016) investigated the hydraulic relationship between surface water and groundwater in seasonal lakes in the Barak-Kushiyara floodplain (Bangladesh and India) based on the SWATrw model, and found that rivers maintain the water balance of seasonal lakes mainly through groundwater recharge.…”

mentioning

confidence: 99%

Effects of Periodic Fluctuation of Water Level on Solute Transport in Seasonal Lakes in Poyang Floodplain System

Chen,

Zhang,

Jin

et al. 2023

Water Resources Research

View full text Add to dashboard Cite

Seasonal lakes appear in floodplain systems due to the seasonal variation of water level of rivers or main lakes and play an important ecological function. Previous studies have focused on exchange flux between the surface water and groundwater in seasonal lakes, but the process of solute transport at the sediment‐water interface under the effect of seasonal water level fluctuations remains unclear. In this study, laboratory flume experiments and numerical simulations were conducted to investigate non‐reactive solute transport and exchange in a seasonal lake under effects of hydrological connectivity, water level amplitude, sediment permeability and solute source. The results show that the recharge pattern between seasonal lakes and rivers or main lakes is determined by the seasonal water level. The solute transports from the groundwater of seasonal lakes to the main lake during the dry season, while the reverse applies during the wet season. The perennial hydrological isolation increases the concentration in the overlying water and pore water of the seasonal lake by 20.5% and 28.7%, respectively. The solute concentration in the overlying water and pore water of the seasonal lake decreases by 55.2% and 51.5%, respectively, when solute source occurs in the main lake compared with that occurs in the seasonal lake. The amplification of water level amplitudes leads to an increase of 6.46% and 10.55% in the solute concentration drop from the overlying water, respectively. These findings contribute to improving water resource utilization and protecting aquatic ecological environment in floodplain systems.

show abstract

Forecasting DO of the river-type reservoirs using input variable selection and machine learning techniques - taking Shuikou reservoir in the Minjiang River as an example

Zhang,

Mei,

Shi

et al. 2023

Ecological Indicators

View full text Add to dashboard Cite

Dissolved Oxygen Concentration Prediction Model Based on WT-MIC-GRU—A Case Study in Dish-Shaped Lakes of Poyang Lake

Cited by 7 publications

References 22 publications

Artificial Intelligence in Internet of Things System for Predicting Water Quality in Aquaculture Fishponds

Artificial Intelligence in Internet of Things System for Predicting Water Quality in Aquaculture Fishponds

Effects of Periodic Fluctuation of Water Level on Solute Transport in Seasonal Lakes in Poyang Floodplain System

Forecasting DO of the river-type reservoirs using input variable selection and machine learning techniques - taking Shuikou reservoir in the Minjiang River as an example

Contact Info

Product

Resources

About