scholarly journals Prediction of DO Concentration in Nakdong River Estuary through Case Study Based on Long Short Term Memory Model

2021 ◽  
Vol 33 (6) ◽  
pp. 238-245
Author(s):  
Seongsik Park ◽  
Kyunghoi Kim
Keyword(s):  
Dissolved Oxygen ◽  
Short Term Memory ◽  
River Estuary ◽  
Sequence Length ◽  
Nakdong River ◽  
Model Parameter ◽  
Study Results ◽  
Model Condition ◽  
Do Concentration

In this study, we carried out case study to predict dissolved oxygen (DO) concentration of Nakdong river estuary with LSTM model. we aimed to figure out a optimal model condition and appropriate predictor for prediction in dissolved oxygen concentration with model parameter and predictor as cases. Model parameter case study results showed that Epoch = 300 and Sequence length = 1 showed higher accuracy than other conditions. In predictor case study, it was highest accuracy where DO and Temperature were used as a predictor, it was caused by high correlation between DO concentration and Temperature. From above results, we figured out an appropriate model condition and predictor for prediction in DO concentration of Nakdong river estuary.

scholarly journals Dissolved Oxygen Forecasting in Aquaculture: A Hybrid Model Approach

2020 ◽  
Vol 10 (20) ◽  
pp. 7079
Author(s):  
Elias Eze ◽  
Tahmina Ajmal
Keyword(s):  
Dissolved Oxygen ◽  
Mean Square Error ◽  
Short Term Memory ◽  
Sensor Data ◽  
Percentage Error ◽  
Forecasting Model ◽  
Mean Square ◽  
Intrinsic Mode Functions ◽  
Short Term ◽  
Do Concentration

Dissolved oxygen (DO) concentration is a vital parameter that indicates water quality. We present here DO short term forecasting using time series analysis on data collected from an aquaculture pond. This can provide the basis of data support for an early warning system, for an improved management of the aquaculture farm. The conventional forecasting approaches are commonly characterized by low accuracy and poor generalization problems. In this article, we present a novel hybrid DO concentration forecasting method with ensemble empirical mode decomposition (EEMD)-based LSTM (long short-term memory) neural network (NN). With this method, first, the sensor data integrity is improved through linear interpolation and moving average filtering methods of data preprocessing. Next, the EEMD algorithm is applied to decompose the original sensor data into multiple intrinsic mode functions (IMFs). Finally, the feature selection is used to carefully select IMFs that strongly correlate with the original sensor data, and integrate into both inputs for the NN. The hybrid EEMD-based LSTM forecasting model is then constructed. The performance of this proposed model in training and validation sets was compared with the observed real sensor data. To obtain the exact evaluation accuracy of the forecasted results of the hybrid EEMD-based LSTM forecasting model, four statistical performance indices were adopted: mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Results are presented for the short term (12-h) and the long term (1-month) that are encouraging, indicating suitability of this technique for forecasting DO values.

scholarly journals Practical Options for Adopting Recurrent Neural Network and Its Variants on Remaining Useful Life Prediction

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Youdao Wang ◽  
Yifan Zhao ◽  
Sri Addepalli
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Short Term Memory ◽  
Parameter Tuning ◽  
Prediction Performance ◽  
Remaining Useful Life ◽  
Sequence Length ◽  
Great Success ◽  
Useful Life

AbstractThe remaining useful life (RUL) of a system is generally predicted by utilising the data collected from the sensors that continuously monitor different indicators. Recently, different deep learning (DL) techniques have been used for RUL prediction and achieved great success. Because the data is often time-sequential, recurrent neural network (RNN) has attracted significant interests due to its efficiency in dealing with such data. This paper systematically reviews RNN and its variants for RUL prediction, with a specific focus on understanding how different components (e.g., types of optimisers and activation functions) or parameters (e.g., sequence length, neuron quantities) affect their performance. After that, a case study using the well-studied NASA’s C-MAPSS dataset is presented to quantitatively evaluate the influence of various state-of-the-art RNN structures on the RUL prediction performance. The result suggests that the variant methods usually perform better than the original RNN, and among which, Bi-directional Long Short-Term Memory generally has the best performance in terms of stability, precision and accuracy. Certain model structures may fail to produce valid RUL prediction result due to the gradient vanishing or gradient exploring problem if the parameters are not chosen appropriately. It is concluded that parameter tuning is a crucial step to achieve optimal prediction performance .

scholarly journals Dissolved Oxygen Forecasting in Aquaculture: A Hybrid Model Approach

2020 ◽  
Author(s):  
Elias Eze ◽  
Tahmina Ajmal
Keyword(s):  
Dissolved Oxygen ◽  
Short Term Memory ◽  
Moving Average ◽  
Warning System ◽  
Linear Interpolation ◽  
Sensor Data ◽  
Forecasting Model ◽  
Intrinsic Mode Functions ◽  
Short Term ◽  
Do Concentration

Dissolved Oxygen (DO) concentration is a vital parameter that indicates water quality. DO short term forecasting using time series analysis on data collected from an aquaculture pond is presented here. This can provide data support for an early warning system for an improved management of the aquaculture farm. The conventional forecasting approaches are commonly characterized by low accuracy and poor generalization problems. In this article, we present a novel hybrid DO concentration forecasting method with ensemble empirical mode decomposition (EEMD) based LSTM (Long short-term memory) neural network (NN). With this method, first, the sensor data integrity is improved through linear interpolation and moving average filtering methods of data preprocessing. Next, the EEMD algorithm is applied to decompose the original sensor data into multiple intrinsic mode functions (IMFs). Finally, the feature selection is used to carefully select IMFs that are strongly correlated with the original sensor data and integrate both into inputs for the NN. The hybrid EEMD-based LSTM forecasting model is then constructed. Performance of this proposed model in training and validation sets was compared with the observed real sensor data. To obtain the exact evaluation accuracy of the forecasted results of the hybrid EEMD-based LSTM forecasting model, three statistical performance indices were adopted: MAE, MSE, and RMSE. Results presented for short term (12-hour period) and long term (1-month period) give a strong indication of suitability of this method for forecasting DO values.

scholarly journals Seasonal Variation of Dissolved Oxygen in the Southeast of the Pearl River Estuary

Water ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2475
Author(s):  
Guangping Liu ◽  
Weihong He ◽  
Shuqun Cai
Keyword(s):  
Dissolved Oxygen ◽  
River Estuary ◽  
Pearl River Estuary ◽  
Empirical Orthogonal Functions ◽  
Pearl River ◽  
The Pearl River Estuary ◽  
Main Period ◽  
Do Concentration ◽  
The Pearl River ◽  
Bottom Hypoxia

Dissolved oxygen (DO) concentration in estuaries is highly variable at different spatial and temporal scales, which is affected by physical, chemical and biological processes. This study analyzed the spatial–temporal distributions of dissolved oxygen concentration and bottom hypoxia in the southeast of the Pearl River Estuary (PRE) using monthly water quality monitoring and hydrographic data covering the period 2000–2017. The seasonal spatial–temporal variation of DO concentration was studied using various methods, such as rotated empirical orthogonal functions, harmonic analysis, and correlation analysis. The results showed that DO stratification was significant in summer, but it was not distinct in winter, during which DO concentration peaked. DO stratification exhibited a significantly positive correlation with water stratification. In the south and west of Hong Kong (SHK and WHK, respectively), DO concentration fields exhibited distinct seasonal changes in the recent 18 years. In SHK, the main periods of the surface DO variation were 24, 12, and 6 months, whereas the main period was 12 months in WHK. The main period of the bottom DO variation was 12 months in both SHK and WHK. In SHK, the spatial–temporal variations in surface and bottom DO were highly related to the variations of salinity, dissolved inorganic nitrogen (DIN), and active phosphorus, and the variation of surface DO was also connected to the variation of temperature and chlorophyll a. In WHK, the variations in surface and bottom DO were highly related to the variations of salinity and temperature, and the variation of surface DO was also connected to the variation of DIN. The river discharge and wind had a different important influence on the temporal variability of DO in WHK and SHK. These findings suggested that the variations of DO may be controlled by coupled physical and biochemical processes in the southeast of PRE. From 2000 to 2017, bottom hypoxia in the southeast of PRE occurred in the summers of 7 years. SHK appeared to be more vulnerable to hypoxia than WHK.

Daily and hourly prediction of DO concentration using machine learning algorithm

2020 ◽  
Author(s):  
heesung lim ◽  
hyunuk an
Keyword(s):  
Water Quality ◽  
Target Location ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Water Quality Management ◽  
Practical Aspect ◽  
Weather Data ◽  
Sequence Length ◽  
Water Quality Prediction ◽  
Do Concentration

<p>In order to perform adequate water quality management, it is important to predict the water quality through measurement and data accumulation of the concentration of contaminants. However, daily measurement of water quality pollutant is unrealistic in practical aspect. In this study, the possibility of daily- or hourly-based water quality prediction through dissolved oxygen (DO) using RNN-LSTM (Recurrent Neural Network-Long Short-term Memory) algorithm, which is well-known for time-series learning, was performed. The research selected Bugok Bridge in Oncheon-stream, Busan, South Korea. Hourly-based DO, temperature, wind speed, relative humidity, rainfall data was collected at the target location and was converted to daily data. To forecast the DO concentration, TensorFlow, a deep learning open source library developed by Google, was utilized. Data of four years (2014-2017) was used for daily learning data and 2018 data was used for verification of the trained model. The performance with the adjusted number of hidden layers, number of repetitions, and the sequence length, as well as the accuracy of the model was analyzed. As a result of this research, it is proven that the performance of the prediction can be improved when weather data and large amount of data is available.</p>

Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design

2019 ◽  
Author(s):  
Niclas Ståhl ◽  
Göran Falkman ◽  
Alexander Karlsson ◽  
Gunnar Mathiason ◽  
Jonas Boström
Keyword(s):  
Reinforcement Learning ◽  
Short Term Memory ◽  
De Novo ◽  
De Novo Drug Design ◽  
Generative Process ◽  
New Methods ◽  
Multiparameter Optimization ◽  
Long Short Term Memory ◽  
New Compounds

<p>In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex and difficult multi-parameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modelled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improve these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output towards structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid, and a third satisfy the targeted objectives, while there were none in the initial set.</p>

Sign in / Sign up

Export Citation Format

Share Document