Dissolved Oxygen Prediction Model Research Articles

A long-term dissolved oxygen prediction model in aquaculture using transformer with a dynamic adaptive mechanism

The prediction of Dissolved Oxygen (DO) in oceans is crucial for the survival of marine life and the management of marine farms. However, due to the inherent instability and uncertainty of DO, prediction models frequently necessitate parameter adjustments, posing challenges to maintaining reliable predictive performance and generalization capabilities. Based on this, a long-term dissolved oxygen prediction model in aquaculture using Transformer with a dynamic adaptive mechanism is proposed in the paper. A multi-scale latent correlation decomposition strategy was devised, merging both time and frequency domain decompositions. This approach proficiently untangles time series exhibiting intricate non-linear cycles, thereby delving deeper into and furnishing a more comprehensive array of feature data. Furthermore, an uncertainty-aware attention mechanism was posited, ensuring accurate pinpointing of pivotal data amidst a highly volatile data environment, thus cementing prediction accuracy. Finally, the incorporation of an adaptive hyperparameter adjustment mechanism enables the model to recalibrate in line with feature insights, bolstering its generalization potential across marine farms in diverse regions. Empirical results show that the model proposed in this study can effectively accomplish high-precision long-term forecasting. When juxtaposed with other models under comparable conditions, its mean squared error significantly diminished by 40.2%, the mean absolute error contracted by 55.4%, and concurrently, the R2 value ascended by 7%. This research proffers a fresh vantage point for long-term marine chemical data predictions and extends robust technical bolstering for refining and augmenting aquacultural strategies.

A dissolved oxygen prediction model based on GRU–N-Beats

Dissolved oxygen is one of the most important water quality parameters in aquaculture, and the level determines whether fish can grow healthily. Since there is a delay in equipment control in the aquaculture environment, dissolved oxygen prediction is needed to reduce the loss due to low dissolved oxygen. To solve the problem of insufficient accuracy and poor interpretability of traditional methods in predicting dissolved oxygen from multivariate water quality parameters, this paper proposes an improved N-Beats-based prediction network. First, the maximum expectation algorithm [expectation–maximization (EM)] was used to fill in the original data by fitting the missing values. Second, the discrete wavelet transform (DWT) was used to reduce the overall noise of the sample, then the gated recurrent unit (GRU) feature extraction network was employed to extract the water quality information from the temporal dimension, the N-Beats was utilized to predict the preprocessed data, and the residual operation through Stack was performed to obtain the prediction results. The improved algorithm overcomes the challenge of insufficient prediction accuracy of the traditional algorithm. The GRU–N-Beats network proposed in this paper can extract features from multivariate time dimensions for prediction. The values of root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R2 for the proposed algorithm were 0.171, 0.120, 0.015, and 0.97, respectively. In particular, they were 28.5%, 32.1%, 51.6%, 24.3%, 14.9%, 36.4%, and 19.3% higher than those of long short-term memory (LSTM), GRU, temporal convolutional network (TCN), LSTM–TCN, PatchTST, back-propagation neural network (BPNN), and N-Beats on RMSE, respectively.

A spatiotemporal dissolved oxygen prediction model based on graph attention networks suitable for missing data.

The accurate prediction of dissolved oxygen concentration is crucial for the effective prevention and control of water pollution. A spatiotemporal prediction model for dissolved oxygen content that is suitable for missing data is proposed in this study. The model utilizes a module based on neural controlled differential equations (NCDEs) to handle missing data and graph attention networks (GATs) to capture the spatiotemporal relationship of dissolved oxygen content. To enhance the performance of model, it is optimized from three aspects: an iterative optimization method based on the k-nearest neighbor graph is proposed to enhance the quality of graph; Shapley additive explanations model (SHAP) is used to select the main features into model, enabling it to handle multiple features; and a fusion graph attention mechanism is introduced to improve the robustness of model to noise. The model is evaluated using data from water quality monitoring sites in Hunan Province, China, from January 14, 2021, to June 16, 2022. The proposed model outperforms other models in long-term prediction (step = 18), with MAE of 0.194, NSE of 0.914, RAE of 0.219, and IA of 0.977. The results demonstrate that constructing appropriate spatial dependencies can enhance the accuracy of dissolved oxygen prediction models, and the NCDE module confers robustness to missing data in the model.

Dissolved Oxygen Prediction Model for the Yangtze River Estuary Basin Using IPSO-LSSVM

Water ecology has always been key to environmental protection, and the combination of human activities and natural factors has caused eutrophication in the Yangtze estuary and adjacent waters. Among them, dissolved oxygen (DO) concentration is the key indicator to judge the quality of water. Firstly, using principal component analysis (PCA) to determine the number of parameters affecting dissolved oxygen concentration, the least squares support vector machine (LSSVM) prediction model with improved particle swarm optimization (IPSO) is proposed to be applied to the dissolved oxygen prediction in Shanghai’s Yangtze River basin through the data-driven modeling approach and the regression prediction capability of the neural network. Eight parameters of water temperature (WT), pH, potassium permanganate (KMnO4), ammonia nitrogen (NH4+-N), total phosphorus (TP), total nitrogen (TN), conductivity (Cond), and nephelometric turbidity unit (NTU) are selected as model inputs in the published public data, and the output is the dissolved oxygen concentration. The optimal combination of model parameters is found according to the IPSO algorithm, which effectively overcomes the parameter selection problem of regular support vector machines (SVM). The mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and correlation coefficients of the evaluation indexes of this model (R2) are 0.1702, 0.2221, 0.0267, and 0.9751, respectively. Compared with other similar data driven models, this model has improved model accuracy and stability in predicting DO concentrations in the estuary, and thus it provides technical support for assessing and monitoring offshore water quality.

Urban River Dissolved Oxygen Prediction Model Using Machine Learning

This study outlines the preliminary stages of the development of an algorithm to predict the optimal WQ of the Hwanggujicheon Stream. In the first stages, we used the AdaBoost algorithm model to predict the state of WQ, using data from the open artificial intelligence (AI) hub. The AdaBoost algorithm has excellent predictive performance and model suitability and was selected for random forest and gradient boosting (GB)-based boosting models. To predict the optimized WQ, we selected pH, SS, water temperature, total nitrogen(TN), dissolved total phosphorus(DTP), NH3-N, chemical oxygen demand (COD), dissolved total nitrogen (DTN), and NO3-N as the input variables of the AdaBoost model. Dissolved oxygen (DO) was used as the target variable. Third, an algorithm showing excellent predictive power was selected by analyzing the prediction accuracy according to the input variable by using the random forest or GB series algorithm in the initial model. Finally, the performance evaluation of the ultimately developed predictive model demonstrated that RMS was 0.015, MAE was 0.009, and R2 was 0.912. The coefficient of the variation of the root mean square error (CVRMSE) was 17.404. R2 0.912 and CVRMSE were 17.404, indicating that the predictive model developed meets the criteria of ASHRAE Guideline 14. It is imperative that government and administrative agencies have access to effective tools to assess WQ and pollution levels in their local bodies of water.

Non-Linear Autoregressive Dissolved Oxygen Prediction Model for Paddy Irrigation Channel

This study has proposed a non-linear autoregressive model to predict one-day ahead dissolved oxygen in paddy field irrigation channel. A 32-day data is obtained from Kampung Padang To’ La in Pasir Mas, Kelantan using off-the shelf water quality parameter sensors. Analysis has revealed no correlation between dissolved oxygen with pH and electrical conductivity. A non-linear autoregressive model is then developed using the dissolved oxygen measurements and artificial neural network. A prediction model developed using Levenberg- Marquardt algorithm yielded the best results with overall regression of 0.9253. The model has also passed all correlation tests and can therefore, be accepted.

A novel dissolved oxygen prediction model based on enhanced semi-naive Bayes for ocean ranches in northeast China.

A challenge of achieving intelligent marine ranching is the prediction of dissolved oxygen (DO). DO directly reflects marine ranching environmental conditions. Through accurate DO predictions, timely human intervention can be made in marine pasture water environments to avoid problems such as reduced yields or marine crop death due to low oxygen concentrations in the water. We use an enhanced semi-naive Bayes model for prediction based on an analysis of DO data from marine pastures in northeastern China from the past three years. Based on the semi-naive Bayes model, this paper takes the possible values of a DO difference series as categories, counts the possible values of the first-order difference series and the difference series of the interval before each possible value, and selects the most probable difference series value at the next moment. The prediction accuracy is optimized by adjusting the attribute length and frequency threshold of the difference sequence. The enhanced semi-naive Bayes model is compared with LSTM, RBF, SVR and other models, and the error function and Willmott’s index of agreement are used to evaluate the prediction accuracy. The experimental results show that the proposed model has high prediction accuracy for DO attributes in marine pastures.

A three-dimensional prediction method of dissolved oxygen in pond culture based on Attention-GRU-GBRT

Pond culture is an open water body, the distribution of dissolved oxygen in water is three-dimensional. The demand for dissolved oxygen in aquatic products living in different water layers is different. The traditional one-dimensional prediction at one single monitoring point can‘t reflect the real situation of dissolved oxygen in different spaces in the pond. To solve these problems, a three-dimensional prediction method of dissolved oxygen based on Attention-Gated Recurrent Unit (GRU) - Gradient Boost Regression Tree (GBRT) was proposed in this paper. Firstly, the environmental factors affecting the distribution of dissolved oxygen were collected, and the dissolved oxygen prediction model of the central monitoring point was constructed using Attention-GRU. The three-dimensional coordinate system with the central monitoring point as the origin was then established, and the GBRT algorithm optimized by the Random Search algorithm(RS) was used to predict the dissolved oxygen in any position of the pond water. In the one-dimensional prediction of dissolved oxygen at the central monitoring point, the Attention-GRU model proposed in this paper had MSE of 0.121, MAE of 0.219, and RMSE of 0.348, which was a big improvement compared with LSTM model, ELM model and CNN model. In the three-dimensional prediction of dissolved oxygen in the pond, the RS-GBRT model proposed had MSE of 0.097, MAE of 0.191, and RMSE of 0.313. Compared with the models such as ExtraTree model, RandomForest model, and Bagging model, each evaluation index had been greatly improved. The experimental results indicated that the proposed method can accurately predict the dissolved oxygen in the three-dimensional space of the pond.

River Dissolved Oxygen Prediction Based on Random Forest and LSTM

HighlightsRandom Forest (RF) and LSTM were developed for river DO prediction.PH is the most important feature affecting DO prediction.The model base on RF is better than the model not on RF, and the dimensionality of the input data is reduced by RF.RF-LSTM model is outperformed SVR, RF-SVR, BP, RF-BP, LSTM, RNN models in DO prediction.Abstract. In order to improve the prediction accuracy of dissolved oxygen in rivers, a dissolved oxygen prediction model based on Random Forest (RF) and Long Short Term Memory networks (LSTM) is proposed. First, the Random Forest performs feature selection, which reduces the input dimension of the data and eliminates the influence of irrelevant variables on the prediction of dissolved oxygen. Then build the LSTM river dissolved oxygen prediction model to fit the relationship between water quality data and dissolved oxygen, and finally use real water quality data in the river for verification. The experimental results show that the mean square error (MSE), absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and coefficient of determination (R2) of the RF-LSTM model are 0.658, 0.528, 13.502, 0.811, 0.744, respectively, which are better than other models. The RF-LSTM model has good predictive performance and can provide a reference for river water quality management. Keywords: Dissolved oxygen prediction, LSTM, Random forest, Time series, Water quality management.

Prediction of dissolved oxygen in pond culture water based on K-means clustering and gated recurrent unit neural network

Dissolved oxygen in water is an important ecological factor in ensuring the healthy growth of aquatic products, as hypoxic stress is known to restrict the growth of aquatic products. The accurate monitoring and prediction of dissolved oxygen is the key to precise regulation and control of pond aquaculture water quality. The current dissolved oxygen prediction model has some limitations, such as a short prediction period and inadequate prediction accuracy for actual production demands. Therefore, a prediction model of dissolved oxygen in pond culture was proposed based on K-means clustering and Gated Recurrent Unit (GRU) neural network. Firstly, the key factors affecting the changes in dissolved oxygen were selected by principal component analysis (PCA). The dissolved oxygen time series was then subjected to K-means clustering, and the dissolved oxygen prediction model was constructed using GRU. To improve the clustering effect, we enhanced the similarity calculation for the time series based on the variation of dissolved oxygen. This process combined the Euclidean distance with the dynamic time-warping distance. The proposed method can predict the dissolved oxygen content of aquaculture water over different time intervals according to the demands of real-world scenarios. The average absolute error of the 30-min interval model was 0.264, and the mean absolute percentage error was 3.5 %. Experimental results indicated that the proposed method achieves higher prediction accuracy and flexibility than the conventional approach.

A combined model of dissolved oxygen prediction in the pond based on multiple-factor analysis and multi-scale feature extraction

As dissolved oxygen (DO) is an important indicator of water quality in aquaculture, an accurate prediction for DO can effectively improve quantity and quality of product. Accordingly, a novel hybrid dissolved oxygen prediction model, which combines the multiple-factor analysis and the multi-scale feature extraction, is proposed. Firstly, considering that dissolved oxygen is affected by complex factors, water temperature and pH are chosen as the most relevant environmental factors for dissolved oxygen, using grey relational degree method. Secondly, the ensemble empirical mode decomposition (EEMD) is adopted to decompose the dissolved oxygen, water temperature and pH data into several sub-sequences, respectively. Then, the sample entropy (SE) algorithm reconstructs the sub-sequences to obtain the trend component, random component and detail component. Lastly, regularized extreme learning machine (RELM), a currently effective and stable artificial intelligent (AI) tool, is applied to predict three components independently. The prediction models of random component, detail component and trend component are RELM1, RELM2 and RELM3 respectively. The dissolved oxygen, water temperature and pH of the random component forms the input layer of RELM1, and predicted value of dissolved oxygen in the random component is the output layer of RELM1. The input and output of RELM2 and RELM3 are similar to that of RELM1. Final prediction results are obtained by superimposing three components predicted values. One of the main features of the proposed approach is that it integrates the multiple-factor analysis and the multi-scale feature extraction using grey correlation analysis and EEMD. Its performance is compared with several outstanding algorithms. Results for experiment show that the proposed model has satisfactory performance and high precision.

A method for predicting dissolved oxygen in aquaculture water in an aquaponics system

Aquaponics systems combine vegetable cultivation with fish culture (Rao et al., 2017). Several environmental factors influence water quality, among which dissolved oxygen is the most critical. The dissolved oxygen-related processes are nonlinear and unstable and are characterized by considerable time delays and time variances. In an aquaponics system, the dissolved oxygen content is affected by changes in the aquaculture water and in the greenhouse climate. Understanding the changes in dissolved oxygen and ensuring its stability requires effective prediction approaches and corrective measures. Traditional prediction methods are characterized by low stability, low accuracy and poor timeliness. A dissolved oxygen prediction model based on fuzzy neural networks is proposed in this paper. With a large number of inputs, the fuzzy network has high dimensonality, a complex model structure, and low precision, among other limitations. A genetic algorithm can be used to optimize the centre and width of the fuzzy neural network’s middle layer and determine the optimal parameter combination, thus improving the efficiency and predictive accuracy of the model (Liu et al., 2014). The results show that a fuzzy neural network optimized using a genetic algorithm is more stable, more accurate, and more suitable for predicting dissolved oxygen than a fuzzy neural network and backpropagation neural network in an aquaponics system. Predicting dissolved oxygen is critical to the stability of an aquaponics system.

Prediction model of dissolved oxygen in ponds based on ELM neural network

Dissolved oxygen in ponds is affected by many factors, and its distribution is unbalanced. In this paper, in order to improve the imbalance of dissolved oxygen distribution more effectively, the dissolved oxygen prediction model of Extreme Learning Machine (ELM) intelligent algorithm is established, based on the method of improving dissolved oxygen distribution by artificial push flow. Select the Lake Jing of Guangxi University as the experimental area. Using the model to predict the dissolved oxygen concentration of different voltage pumps, the results show that the ELM prediction accuracy is higher than the BP algorithm, and its mean square error is MSEELM=0.0394, the correlation coefficient RELM=0.9823. The prediction results of the 24V voltage pump push flow show that the discrete prediction curve can approximate the measured values well. The model can provide the basis for the artificial improvement of the dissolved oxygen distribution decision.

Study on Prediction Model of Dissolved Oxygen about Water Quality Monitoring System Based on BP Neural Network

Eriocheir sinensis should cultivate in high water quality ponds, which is affected by many combined factors such as physics, chemistry, biology etc. Using the real-time water quality monitoring historical data to test one of the water quality indexes and predict this index in the next time has great significance. The dissolved oxygen is one of the most important indexes in aquaculture, such as in the Eriocheir sinensis pond. This paper established a dissolved oxygen prediction model of water quality monitoring system based on BP neural network. The forecast data which is predicted by the established model could fit the actual monitoring data very well.