Machine learning-based tools for water digitalisation

2021 ◽  
Author(s):  
Asma Slaimi ◽  
Susan Hegarty ◽  
Fiona Regan ◽  
Michael Scriney ◽  
Noel O’Connor
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Data Warehouse ◽  
New Technologies ◽  
Short Term Memory ◽  
Water Quality Management ◽  
Water Levels ◽  
Quality Data ◽  
Quality Information ◽  
Water Quality Data

<p>Advanced technologies have proven to deliver significant outcomes in the water management sector. New technologies provide the capability to collect and correlate the information from remote devices, introducing smart tools that can leverage augmented intelligence for interpreting structured and unstructured, text-based or sensory data. However, most of the single feature or non-sequential prediction machine learning methods for understanding water quality achieve poor results due to the fact that water quality information exists in the form of multivariate time-series datasets.</p><p>At the catchment scale, there are many layers where relevant data needs to be measured and captured. For that, data warehouses play an essential role in decision support systems as they provide adequate information. </p><p>In this paper, we started by extracting, transforming, cleaning and consolidating data from several data sources into a data warehouse. Then, the data in the warehouse was used to develop a computer tool to predict river water level using Artificial Neural Networks (ANNs), in particular, Long Short-Term Memory networks (LSTM). As the prediction performance is significantly affected by the model inputs, the feature selection step, which considers the multivariate correlation of water quality information in terms of similarity and proximity, is particularly important. The features obtained from the previous steps are the inputs to the prediction model based on LSTM, which naturally takes the time sequence of water quality information into account.</p><p>The proposed method is applied to two different catchments in the island of Ireland. Experimental results indicate that our model provides accurate predictions for water levels and is a useful supportive tool for water quality management. </p><p>Ultimately, digitised representations of water environments will guarantee situational awareness of water flow and quality monitoring. The digitalisation of water is no longer optional but a necessity to solve many of the challenges faced by the water industry.</p><p><br><strong>Keywords:</strong> Water digitalisation, water quality, data warehouse, machine learning, predictive model, LSTM.</p><p><br><br></p>

scholarly journals Dampak Limbah Penambangan Emas Tanpa Izin (Peti) Terhadap Kualitas Air Sungai Limun Kabupaten Sarolangun Propinsi Jambi - The Impact Of Illegal Gold Mining Activity To The Water Quality Of Limun River, Sarolangun District, Jambi Province

2017 ◽  
Vol 14 (3) ◽  
pp. 251
Author(s):  
Rita Yulianti ◽  
Emi Sukiyah ◽  
Nana Sulaksana
Keyword(s):  
Water Quality ◽  
Gold Mining ◽  
Quality Standard ◽  
Water Levels ◽  
Quality Analysis ◽  
Quality Data ◽  
Mining Activities ◽  
Water Quality Data ◽  
The Impact

Daerah penelitian terletak di desa Muaro Limun, Kecamatan Limun Kabupaten Sarolangun Provinsi Jambi. Sungai limun, salah satu sungai besar di daerah kabupaten sarolangun yang dimanfaatkan oleh mayarakat sekitarnya sebagai sumber penghidupan. Penelitian bertujuan untuk mengetahui pengaruh kegiatan penambangan terhadap kualitas air sungai Batang Limun, dan perubahan sifat fisik dan  kimia yang diakibatkan   kegiatan penambangan.Metode yang digunakan adalah  metode grab sampel, serta stream sedimen untuk dianalis di laboratorium. Sejumlah sampel diambil di beberapa lokasi Penambangan Emas berdasarkan Aliran Sub-DAS dan dibandingkan dengan beberapa sampel lain yang diambil pada lokasi yang belum terkontaminasi oleh kegiatan penambangan. Analisis kualitas air mengacu pada  SMEWWke 22 tahun 2012 dan standar baku mutu air kelas II dalam PP No 82 yang dikeluarkan oleh Menteri Kesehatan No. 492/Menkes/Per/IV/2010. Diketahui sungai Batang Limun telah mengalami perubahan karakteristik fisika dan kimia. Dari grafik  kosentrasi kekeruhan, pH, TSS, TDS  Cu, Pb, Zn, Mn, Hg terlihat bahwa penambang emas tanpa izin (PETI) dengan cara amalgamasi yang menyebabkan terjadinya penurunan kualitas air sungai. Sejak tahun 2009 sampai tahun 2015  sungai Limun dan sekitarnya terus mengalami penurunan kualitas air. Penurunan kualitas yang cukup tinggi terjadi  yaitu peningkatan nilai Rata-rata konsentrasi merkuri pada sungai Batang Limun dari 0,18ppb (0,00018 mg/l)  menjadi 0,3ppb (0,0003 mg/l), peningkatan tersebut dipengaruhi oleh proses kegiatan penambangan dan nilai tersebut masih dibawah standar baku mutu air kelas II  pp nomor 82 tahun 2010.Kata kunci :   Kualitas Air, Sungai Limun,TSS, Merkuri, PETI Limun river is one of the major rivers in the area of Sarolangun, which utilized by the society as a source of livelihood. The aim of study  to analyze the effect of mining activities on  the water quality of Batang Limun River, and the changes of physical and chemical properties of water. The method used are grab  and stream samples to  sediment analyzed in the laboratory. A number of samples were taken at several locations based Flow Gold Mining Sub-watershed and compared to some other samples taken at the location that has not been contaminated by mining activities. Water quality analysis referring to SMEWW, 22nd edition 2012 and refers to Regulation No 82 that issued by Minister of Health No. 492 / Menkes / Per / IV / 2010.The results showed that the Limun river has undergone chemical changes in physical characteristics. These symptoms can be seen from the discoloration of clear water in the river before the mine becomes brownish after mining, based on graphic of muddiness concentration: pH, TSS, TDS Cu, Pb, Zn, Mn, Hg have seen that  the illegal miner which used amalgamation caused deterioration in water quality, data from 2009 to 2015 Limun river and surrounding areas continue to experience a decrease in water quality. The decreasing of water quality showed in the TSS parameter which found in the area is to high based on  the standard of water quality class II pp number 82 of 2010. An increase in the value of average concentrations of mercury in the Batang Limun river before mine 0,18ppb (0.00018 mg / l) into 0,3ppb (0.0003 mg / l) on the river after the mine. The increase was affected by the mining activities and the value is still below the air quality standard Grade II pp numbers 82 years 2010, although the value is still below with the standards quality standard, the mercury levels in water should still be a major concern because if it accumulates continuously in the water levels will increase and will be bad for health. In contrast to the concentration of mercury in sediments that have a higher value is 153 ppb (0,513ppm ) .Key Words :   Water Quality, Limun River, Mercury, Illegal gold mining

scholarly journals A Multivariate and Spatiotemporal Analysis of Water Quality in Code River, Indonesia

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Mochamad A. Pratama ◽  
Yan D. Immanuel ◽  
Dwinanti R. Marthanty
Keyword(s):  
Water Quality ◽  
Land Cover ◽  
Agricultural Land ◽  
Water Quality Management ◽  
Temporal Trends ◽  
Oxygen Demand ◽  
Principal Component ◽  
Water Quality Monitoring ◽  
Quality Data ◽  
Water Quality Data

The efficacy of a water quality management strategy highly depends on the analysis of water quality data, which must be intensively analyzed from both spatial and temporal perspectives. This study aims to analyze spatial and temporal trends in water quality in Code River in Indonesia and correlate these with land use and land cover changes over a particular period. Water quality data consisting of 15 parameters and Landsat image data taken from 2011 to 2017 were collected and analyzed. We found that the concentrations of total dissolved solid, nitrite, nitrate, and zinc had increasing trends from upstream to downstream over time, whereas concentrations of parameter biological oxygen demand, cuprum, and fecal coliform consistently undermined water quality standards. This study also found that the proportion of natural vegetation land cover had a positive correlation with the quality of Code River’s water, whereas agricultural land and built-up areas were the most sensitive to water pollution in the river. Moreover, the principal component analysis of water quality data suggested that organic matter, metals, and domestic wastewater were the most important factors for explaining the total variability of water quality in Code River. This study demonstrates the application of a GIS-based multivariate analysis to the interpretation of water quality monitoring data, which could aid watershed stakeholders in developing data-driven intervention strategies for improving the water quality in rivers and streams.

scholarly journals River Dissolved Oxygen Prediction Based on Random Forest and LSTM

2021 ◽  
Vol 37 (5) ◽  
pp. 901-910
Author(s):  
Juan Huan ◽  
Bo Chen ◽  
Xian Gen Xu ◽  
Hui Li ◽  
Ming Bao Li ◽  
...  
Keyword(s):  
Water Quality ◽  
Random Forest ◽  
Quality Management ◽  
Dissolved Oxygen ◽  
Prediction Model ◽  
Water Quality Management ◽  
Quality Data ◽  
Mean Square ◽  
Water Quality Data ◽  
Better Than

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.

A New Assessment Model for Coastal Water Quality Based on Nonlinear Mapping Theory

2013 ◽  
Vol 726-731 ◽  
pp. 1073-1077
Author(s):  
Ren Qiang Lu
Keyword(s):  
Water Quality ◽  
Coastal Water ◽  
Water Quality Management ◽  
Mapping Method ◽  
Assessment Model ◽  
Quality Data ◽  
Nonlinear Mapping ◽  
Water Quality Data ◽  
Coastal Water Quality ◽  
Mapping Theory

A new assessment model for coastal water quality was proposed based on the nonlinear mapping theory. Taking the water quality monitoring data of Tianjins coastal marine as an example, firstly, the high-dimension water quality data were mapped to the two-dimension plane by nonlinear mapping method. Secondly, the water quality assessment model was established according to the position relationship of mapping points. Then, the water quality was assessed based on the model. Through application we could found the method proposed in this paper was simple and practicable. It is science and effectiveness of applying the nonlinear mapping method to assessment the water quality. It could be used to supply the decision support for the coastal water quality management.

Water quality management in the Crocodile River catchment, Eastern Transvaal, South Africa

1995 ◽  
Vol 32 (5-6) ◽  
pp. 201-208
Author(s):  
P. J. Ashton ◽  
F. C. van Zyl ◽  
R. G. Heath
Keyword(s):  
South Africa ◽  
Water Quality ◽  
Quality Management ◽  
Water Quality Management ◽  
Quality Data ◽  
Catchment Management ◽  
Land Uses ◽  
Water Quality Data ◽  
River Catchment ◽  
Management Actions

The Crocodile River catchment lies in an area which currently has one of the highest rates of sustained economic growth in South Africa and supports a diverse array of land uses. Water quality management is vital to resource management strategies for the catchment. A Geographic Information System (GIS) was used to display specific catchment characteristics and land uses, supplemented with integrative overlays depicting land-use impacts on surface water resources and the consequences of management actions on downstream water quality. The water quality requirements of each water user group were integrated to optimise the selection of rational management solutions for particular water quality problems. Time-series water quality data and cause-effect relationships were used to evaluate different water supply scenarios. The GIS facilitated the collation, processing and interpretation of the enormous quantity of spatially orientated information required for integrated catchment management.

scholarly journals A prediction model of aquaculture water quality based on multiscale decomposition

2021 ◽  
Vol 18 (6) ◽  
pp. 7561-7579
Author(s):  
Huanhai Yang ◽  
◽  
Shue Liu ◽  
◽  
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Prediction Model ◽  
Short Term Memory ◽  
Normal Growth ◽  
Original Data ◽  
Quality Data ◽  
Water Quality Data ◽  
Water Quality Prediction ◽  
Aquaculture Water

<abstract><p>In the field of intensive aquaculture, the deterioration of water quality is one of the main factors restricting the normal growth of aquatic products. Predicting water quality in real time constitutes the theoretical basis for the evaluation, planning and intelligent regulation of the aquaculture environment. Based on the design principles of decomposition, recombination and integration, this paper constructs a multiscale aquaculture water quality prediction model. First, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method is used to decompose the different water quality variables at different time scales step by step to generate a series of intrinsic mode function (IMF) components with the same characteristic scale. Then, the sample entropy of each IMF component is calculated, the components with similar sample entropies are combined, and the original data are recombined into several subsequences through the above operations. In this paper, a prediction model based on a long short-term memory (LSTM) neural network is constructed to predict each recombination subsequence, and the Adam optimization algorithm is used to continuously update the weight of neural network to train and optimize the prediction performance. Finally, the predicted value of each subsequence is superimposed to predict the original water quality data. The dissolved oxygen and pH data of an aquaculture base were collected for prediction experiments, the results of which show that the proposed model has a high prediction accuracy and strong generalization performance.</p></abstract>

scholarly journals Multiple stressors threaten the imperiled coastal foundation species eelgrass (Zostera marina) in Chesapeake Bay, USA

2017 ◽  
Author(s):  
Jonathan S Lefcheck ◽  
David J Wilcox ◽  
Rebecca R Murphy ◽  
Scott R Marion ◽  
Robert J Orth
Keyword(s):  
Water Quality ◽  
Chesapeake Bay ◽  
Zostera Marina ◽  
Multiple Stressors ◽  
Physiological Stress ◽  
Carbon Sink ◽  
Water Quality Management ◽  
Water Clarity ◽  
Quality Data ◽  
Water Quality Data

Interactions among global change stressors and their effects at large scales are often proposed, but seldom evaluated. This situation is primarily due to lack of comprehensive, sufficiently long-term, and spatially-extensive datasets. Seagrasses, which provide nursery habitat, improve water quality, and constitute a globally-important carbon sink, are among the most vulnerable habitats on the planet. Here, we unite 31-years of high-resolution aerial monitoring and water quality data to elucidate the patterns and drivers of eelgrass (Zostera marina) abundance in Chesapeake Bay, USA, one of the largest and most valuable estuaries in the world with an unparalleled history of regulatory efforts. We show that eelgrass area has declined 29% in total since 1991, with wide-ranging and severe ecological and economic consequences. We go on to identify an interaction between decreasing water clarity and warming temperatures as the primary driver of this trend. Declining clarity has gradually reduced eelgrass over the past two decades, primarily in deeper beds where light is already limiting. In shallow beds, however, reduced visibility exacerbates the physiological stress of acute warming, leading to recent instances of decline approaching 80%. While degraded water quality has long been known to influence underwater grasses worldwide, we demonstrate a clear and rapidly emerging interaction with climate change. We highlight the urgent need to integrate a broader perspective into local water quality management, in the Chesapeake Bay and in the many other coastal systems facing similar stressors.

scholarly journals Monitoring Lotic Ecosystem by the Application of Water Quality Index (CCMEWQI)

2020 ◽  
Vol 17 (1) ◽  
pp. 0023
Author(s):  
Salman Et al.
Keyword(s):  
Water Quality ◽  
Water Quality Index ◽  
Quality Index ◽  
Water Quality Management ◽  
Water Quality Monitoring ◽  
Quality Data ◽  
Total Hardness ◽  
Water Quality Data ◽  
Quality Of Water ◽  
Lotic Ecosystem

Water Quality Index (WQI) as a tool to assess the water quality status provides advice related to the use of water quality monitoring data and it is a way for combining the complex water quality data into a single value or single statement.The present study was conducted on Al- Hilla river in the middle of Iraq from August 2012 to July 2013 at five selected stations in the river, from Al- Musaib city to Al- Hashimya at the south of Hilla to determine its suitability for aquatic environment (GWQI), drinking water (PWSI) and irrigation (IWQI).This index offers a useful representation of the overall quality of water for public or any intended use as well as indicating pollution, water quality management, and decision making. According to the obtained results, it can be concluded that the EC, TSS, Total hardness, Ca, Mg, DO, BOD5, and NO3 moved away from the desired standards when the temperature rises. The variable of value of this index may be due to increasing the ration of organic matters and converting the carbonate to bicarbonate. The results recorded high value of calcium and magnesium more than the standard value of WHO and IQS (50 mg/l and high value of total hardness more than 500 mg/l). Irrigation water quality index (IWQI) in the study sites were ranged between 66-83 ranged between fair and good.                                                  

scholarly journals Investigation of the Soan River Water Quality Using Multivariate Statistical Approach

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Zakaullah ◽  
Naeem Ejaz
Keyword(s):  
Water Quality ◽  
River Water ◽  
Water Quality Management ◽  
Oxygen Demand ◽  
River Water Quality ◽  
Quality Data ◽  
Spatiotemporal Pattern ◽  
Multivariate Statistical ◽  
Water Quality Data

Evaluating the quality of river water is a critical process due to pollution and variations of natural or anthropogenic origin. For the Soan River (Pakistan), seven sampling sites were selected in the urban area of Rawalpindi/Islamabad, and 18 major chemical parameters were examined over two seasons, i.e., premonsoon and postmonsoon 2019. Multivariate statistical approaches such as the Spearman correlation coefficient, cluster analysis (CA), and principal component analysis (PCA) were used to evaluate the water quality of the Soan River based on temporal and spatial patterns. Analytical results obtained by PCA show that 92.46% of the total variation in the premonsoon season and 93.11% in the postmonsoon season were observed by only two loading factors in both seasons. The PCA and CA made it possible to extract and recognize the origins of the factors responsible for water quality variations during the year 2019. The sampling stations were grouped into specific clusters on the basis of the spatiotemporal pattern of water quality data. The parameters dissolved oxygen (DO), biochemical oxygen demand (BOD), chemical oxygen demand (COD), turbidity, and total suspended solids (TSS) are among the prominent contributing variations in water quality, indicating that the water quality of the Soan River deteriorates gradually as it passes through the urban areas, receiving domestic and industrial wastewater from the outfalls. This study indicates that the adopted methodology can be utilized effectively for effective river water quality management.

Sign in / Sign up

Export Citation Format

Share Document