scholarly journals Implementation of Long-Short Term Memory Neural Network (LSTM) for Predicting The Water Quality Parameters in Sungai Selangor

2021 ◽  
Vol 6 (4) ◽  
pp. 40-49
Author(s):  
Nur Natasya Mohd Anuar ◽  
Nur Fatihah Fauzi ◽  
Huda Zuhrah Ab Halim ◽  
Nur Izzati Khairudin ◽  
Nurizatul Syarfinas Ahmad Bakhtiar ◽  
...  
Keyword(s):  
Water Quality ◽  
Short Term Memory ◽  
Oxygen Demand ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Short Term ◽  
Term Memory ◽  
Quality Of Water ◽  
Long Short Term Memory

Predictions of future events must be factored into decision-making. Predictions of water quality are critical to assist authorities in making operational, management, and strategic decisions to keep the quality of water supply monitored under specific criteria. Taking advantage of the good performance of long short-term memory (LSTM) deep neural networks in time-series prediction, the purpose of this paper is to develop and train a Long-Short Term Memory (LSTM) Neural Network to predict water quality parameters in the Selangor River. The primary goal of this study is to predict five (5) water quality parameters in the Selangor River, namely Biochemical Oxygen Demand (BOD), Ammonia Nitrogen (NH3-N), Chemical Oxygen Demand (COD), pH, and Dissolved Oxygen (DO), using secondary data from different monitoring stations along the river basin. The accuracy of this method was then measured using RMSE as the forecast measure. The results show that by using the Power of Hydrogen (pH), the dataset yielded the lowest RMSE value, with a minimum of 0.2106 at station 004 and a maximum of 1.2587 at station 001. The results of the study indicate that the predicted values of the model and the actual values were in good agreement and revealed the future developing trend of water quality parameters, showing the feasibility and effectiveness of using LSTM deep neural networks to predict the quality of water parameters.

De-noising of transient electromagnetic data based on the long short-term memory-autoencoder

2020 ◽  
Vol 224 (1) ◽  
pp. 669-681
Author(s):  
Sihong Wu ◽  
Qinghua Huang ◽  
Li Zhao
Keyword(s):  
Field Data ◽  
Short Term Memory ◽  
Noise Removal ◽  
Data Sets ◽  
Late Time ◽  
Short Term ◽  
Term Memory ◽  
Transient Electromagnetic ◽  
Long Short Term Memory

SUMMARY Late-time transient electromagnetic (TEM) data contain deep subsurface information and are important for resolving deeper electrical structures. However, due to their relatively small signal amplitudes, TEM responses later in time are often dominated by ambient noises. Therefore, noise removal is critical to the application of TEM data in imaging electrical structures at depth. De-noising techniques for TEM data have been developed rapidly in recent years. Although strong efforts have been made to improving the quality of the TEM responses, it is still a challenge to effectively extract the signals due to unpredictable and irregular noises. In this study, we develop a new type of neural network architecture by combining the long short-term memory (LSTM) network with the autoencoder structure to suppress noise in TEM signals. The resulting LSTM-autoencoders yield excellent performance on synthetic data sets including horizontal components of the electric field and vertical component of the magnetic field generated by different sources such as dipole, loop and grounded line sources. The relative errors between the de-noised data sets and the corresponding noise-free transients are below 1% for most of the sampling points. Notable improvement in the resistivity structure inversion result is achieved using the TEM data de-noised by the LSTM-autoencoder in comparison with several widely-used neural networks, especially for later-arriving signals that are important for constraining deeper structures. We demonstrate the effectiveness and general applicability of the LSTM-autoencoder by de-noising experiments using synthetic 1-D and 3-D TEM signals as well as field data sets. The field data from a fixed loop survey using multiple receivers are greatly improved after de-noising by the LSTM-autoencoder, resulting in more consistent inversion models with significantly increased exploration depth. The LSTM-autoencoder is capable of enhancing the quality of the TEM signals at later times, which enables us to better resolve deeper electrical structures.

ANALISIS KUALITAS AIR PADA KOLAM PENDEDERAN IKAN LELE DUMBO (Clarias gariepinus) DENGAN PENAMBAHAN TEPUNG DAUN SINGKONG (Manihot utillisima) SEBAGAI PAKAN BUATAN

2019 ◽  
Vol 5 ◽  
pp. 131
Author(s):  
Andi Alifia Fara Dhiba ◽  
Husain Syam ◽  
Ernawati Ernawati
Keyword(s):  
Water Quality ◽  
Clarias Gariepinus ◽  
Quality Parameters ◽  
T Test ◽  
Water Quality Parameters ◽  
African Catfish ◽  
Nursery Pond ◽  
Quality Of Water ◽  
Commercial Feed

This study aims to determine the effect of artificial feed by adding cassava leaf flour (Manihot utillisima) to the water quality of the African catfish nursery pond (Clarias gariepinus). This study used the T test (one sample T test) to compare the treatment with artificial feed and commercial feed consisting of 3 replications. The feeding dose was 3% of the weight of the fish for 30 days of maintenance with the frequency of feeding twice a day. Parameters observed were NH3, NO2, NO3, pH, temperature, DO and survival of African catfish. The results showed that the provision of artificial feed in the African catfish nursery did not have a significant effect (P> 0.05) on the observed water quality parameters. The quality of water obtained during maintenance by providing commercial and artificial feed is still supporting the survival of African catfish.

Impact of climate change on the future quality of surface waters: case study of the Ardak River, northeast of Iran

2019 ◽  
Vol 11 (3) ◽  
pp. 685-702 ◽  
Author(s):  
Morteza Nikakhtar ◽  
Seyedeh Hoda Rahmati ◽  
Ali Reza Massah Bavani
Keyword(s):  
Climate Change ◽  
Water Quality ◽  
General Circulation ◽  
Oxygen Demand ◽  
Circulation Model ◽  
Quality Parameters ◽  
Quality Of Water ◽  
Monthly Streamflow

Abstract In recent decades, climate change has influenced the quantity and quality of water resources, affecting water supply for various demands. In this case study, the effects of climate change on the quality of the Ardak River in the northeast of Iran are discussed. The Qual2kW model was used to simulate water quality parameters, by sampling dissolved oxygen (DO), pH, chemical oxygen demand (COD), and NO3. The rainfall-streamflow model IHACRES was used for simulating monthly streamflow. Monthly general circulation model (GCM) temperature and rainfall data from representative concentration pathways (RCP) RCP2.6 and RCP8.5 were downloaded for 1986 to 2005 and 2020 to 2039. The previously verified model LARS-WG was used to predict future temperatures and rainfall. By importing this data into IHACRES, stream flows were simulated, enabling Qual2kW to predict future effects on water quality. Although changes in temperature of 0.5 to 1.2 °C were predicted, maximum changes in temperature and rainfall will occur in winter and summer in series. Therefore, water quality was predicted to decrease only on the Abghad branch, due to increased temperature and lower flow rates. The highest percentage variations in DO and NO3 are −12.19 and 31.25 in RCP8.5 and in COD and PH, −35.4 and 0.29 in RCP2.6.

scholarly journals Evaluation of Water Quality of Kaveri River in Tiruchirappalli District, Tamil Nadu by Principal Component Analysis

2016 ◽  
Vol 11 (1) ◽  
pp. 89-95 ◽  
Author(s):  
Monikandon Sukumaran ◽  
Kesavan Devarayan
Keyword(s):  
Water Quality ◽  
Principal Component Analysis ◽  
Tamil Nadu ◽  
Oxygen Demand ◽  
Principal Component ◽  
Component Analysis ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Linear Relationships

Principal component analysis is a unique technique for reducing the dimensionality of the data. In this study, ten water quality parameters of the river Kaveri observed at five different stations of Tiruchirappalli for six years were collected and subjected to principal component analysis. A computational program was prepared in order to process and understand the data as a cluster. At first necessary data for compiling the program were listed and then fed to the program. Then the outputs were analyzed and possible linear and non-linear relationships between the water quality parameters and the timeline. It is understood that biological oxygen demand and fecal coli had a linear relationship. Further, the results suggested for group of factors that influence the water quality in a particular year.

scholarly journals A Comparison of Water Quality Indexes for an Inland River

2021 ◽  
pp. 1-14
Author(s):  
F. A. Kondum ◽  
R. T. Iwar ◽  
E. T. Kon
Keyword(s):  
Water Quality ◽  
Sewage Treatment ◽  
Oxygen Demand ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Inland River ◽  
Weighted Arithmetic ◽  
Quality Guidelines ◽  
Quality Indexes

The present study assessed water quality parameters and attempts to compare four different Water Quality Indexes (WQIs) for consistency, similarity and reliability in assessing the water quality of river Benue -an inland river- under wet and dry seasons. The results demonstrate that River Benue is continually being polluted in both dry and wet seasons by different sources, particularly domestic sewage and storm runoffs from farmlands. The quality of the water generally exceeded physiochemical and microbiological infection risk limits recommended in water quality guidelines concerning their use for domestic, recreational and irrigational purposes. Proper sewage treatment and river quality monitoring are needed to guard against hazards to public health and vulnerable river water resources. The WQIs applied were: CCME WQI, BC WQI, Dinius’ WQI and Weighted Arithmetic WQI. To evaluate the differences between these indexes, data on ten water quality parameters (Temperature, pH, total dissolved solids, electrical conductivity, Nitrates, Phosphates, biochemical oxygen demand, dissolved oxygen and faecal coliform count) for two distinct seasons from 6 river monitoring sites along the river Benue at Makurdi reach, were used. Significant discrepancies were observed in classification results between the Dinius’ WQI and the other three WQIs. Similarly, the WA and BC WQIs showed an over-optimistic rating due to their eclipsing limitation. Among others, it was concluded that any of the four indexes except Dinius’ index can be adopted but the CCME water quality index would be best suited for assessing water quality in River Benue.

scholarly journals Comparison of Long Short-Term Memory and Weighted Regressions on Time, Discharge, and Season Models for Nitrate-N Load Estimation

2020 ◽  
Vol 12 (15) ◽  
pp. 5942
Author(s):  
Kichul Jung ◽  
Myoung-Jin Um ◽  
Momcilo Markus ◽  
Daeryong Park
Keyword(s):  
Water Quality ◽  
Short Term Memory ◽  
Water Quality Management ◽  
Model Performance ◽  
The United States ◽  
Percentage Error ◽  
Short Term ◽  
Term Memory ◽  
Nitrate N ◽  
Long Short Term Memory

The long short-term memory (LSTM) model has been widely used for a broad range of applications entailing the estimation of variables in different fields to improve water quality management in rivers. The main objectives of this study are (1) to develop a novel LSTM-based model for the estimation of nitrate-N loads, which adversely affect water resources, and (2) to evaluate the performance of the model by comparing it with that of Monte Carlo sub-sampling and the weighted regressions on time discharge and season (WRTDS) model. We evaluated the model performance using various numbers of hidden layers, ranging from one to four, in the LSTM model to determine the appropriate number of hidden layers; furthermore, we applied the sampling frequencies of 6, 12, and 24 to assess their impact. Seven polluted river basins in the United States were used for analysis, and the relative root mean squared error (rRMSE) and the mean percentage error (MPE) metrics were applied for the validation of the model estimates. The proposed model achieved accurate nitrate-N load estimates using three to four hidden layers, and improved model performance was observed when the sampling frequency was increased. The differences among the results obtained using the LSTM model were examined based on a binning technique via a log-log plot of nitrate-N concentration against discharge. The binning analysis showed that the slope obtained from the average rates of discharge and low discharge values apparently influenced the estimates. Furthermore, box plot analyses of the statistical indices such as rRMSE and MPE demonstrate that the LSTM model seems to exhibit better performance than the WRTDS model. The results of the examination demonstrate that the LSTM model may be a good alternative with regard to estimating nitrate-N loads for the control of water quality constituents.

Sign in / Sign up

Export Citation Format

Share Document