Long-term water quality monitoring in Lake Simcoe based on the empirical method and machine learning

2021 ◽  
Author(s):  
Bo Wang ◽  
Jinhui Huang ◽  
Hongwei Guo
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Chlorophyll A ◽  
Total Phosphorus ◽  
Water Quality Monitoring ◽  
Quality Parameters ◽  
Empirical Method ◽  
Quality Monitoring ◽  
Lake Simcoe

<p><strong>Abstract:</strong> The traditional water quality monitoring methods are time-consuming and laborious, which can only reflect the water quality status of single point scale, and have some problems such as irregular sampling time and limited sample size. Remote sensing technology provides a new idea for water quality monitoring, and the temporal resolution of MODIS is one day, which is suitable for long-term, continuous real-time large-scale monitoring of lakes. In this study, Lake Simcoe (located in Ontario, Canada) was selected as the research area. The long-term spatiotemporal changes of chlorophyll-a, transparency, total phosphorus and dissolved oxygen were analyzed by comparing the empirical method, multiple linear regression, random forest and neural network with MODIS data. Finally, the water quality condition of Lake Simcoe is evaluated. The results show that the overall retrieval results of two machine learning models are better than that of the empirical method. The optimal retrieval accuracy R² for four water quality parameters are 0.976, 0.988, 0.943, 0.995, and RMSE are 0.13μg/L, 0.3m, 0.002mg/L and 0.14mg/L, respectively. On the annual scale, the annual mean values of the four water quality parameters during the 10-year period from 2009 to 2018 were 1.37μg/L, 6.9m, 0.0112mg/L and 10.17mg/L, respectively. On the monthly scale, chlorophyll a, total phosphorus and dissolved oxygen first decreased and then increased at the time of year. The higher concentrations of chlorophyll a and total phosphorus in the south and east of Lake Simcoe are related to the input of nutrients from the surrounding residents and farmland.</p><p><strong>Key words: </strong>water quality monitoring; MODIS; empirical method; machine learning</p>

scholarly journals Comparing PlanetScope to Landsat-8 and Sentinel-2 for Sensing Water Quality in Reservoirs in Agricultural Watersheds

2021 ◽  
Vol 13 (9) ◽  
pp. 1847
Author(s):  
Abubakarr S. Mansaray ◽  
Andrew R. Dzialowski ◽  
Meghan E. Martin ◽  
Kevin L. Wagner ◽  
Hamed Gholizadeh ◽  
...  
Keyword(s):  
Water Quality ◽  
Chlorophyll A ◽  
Water Quality Monitoring ◽  
Agricultural Runoff ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Quality Monitoring ◽  
Landsat 8 ◽  
Spectral Bands ◽  
Sentinel 2

Agricultural runoff transports sediments and nutrients that deteriorate water quality erratically, posing a challenge to ground-based monitoring. Satellites provide data at spatial-temporal scales that can be used for water quality monitoring. PlanetScope nanosatellites have spatial (3 m) and temporal (daily) resolutions that may help improve water quality monitoring compared to coarser-resolution satellites. This work compared PlanetScope to Landsat-8 and Sentinel-2 in their ability to detect key water quality parameters. Spectral bands of each satellite were regressed against chlorophyll a, turbidity, and Secchi depth data from 13 reservoirs in Oklahoma over three years (2017–2020). We developed significant regression models for each satellite. Landsat-8 and Sentinel-2 explained more variation in chlorophyll a than PlanetScope, likely because they have more spectral bands. PlanetScope and Sentinel-2 explained relatively similar amounts of variations in turbidity and Secchi Disk data, while Landsat-8 explained less variation in these parameters. Since PlanetScope is a commercial satellite, its application may be limited to cases where the application of coarser-resolution satellites is not feasible. We identified scenarios where PS may be more beneficial than Landsat-8 and Sentinel-2. These include measuring water quality parameters that vary daily, in small ponds and narrow coves of reservoirs, and at reservoir edges.

scholarly journals Machine learning based soft sensor model for BOD estimation using intelligence at edge

2021 ◽  
Author(s):  
Bhawani Shankar Pattnaik ◽  
Arunima Sambhuta Pattanayak ◽  
Siba Kumar Udgata ◽  
Ajit Kumar Panda
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Real Time ◽  
Water Quality Monitoring ◽  
Quality Parameters ◽  
Soft Sensor ◽  
Quality Monitoring ◽  
Sensor Model ◽  
Statistical Measures ◽  
Computational Performance

AbstractReal-time water quality monitoring is a complex system as it involves many quality parameters to be monitored, the nature of these parameters, and non-linear interdependence between themselves. Intelligent algorithms crucial in building intelligent systems are good candidates for building a reliable and convenient monitoring system. To analyze water quality, we need to understand, model, and monitor the water pollution in real time using different online water quality sensors through an Internet of things framework. However, many water quality parameters cannot be easily measured online due to several reasons such as high-cost sensors, low sampling rate, multiple processing stages by few heterogeneous sensors, the requirement of frequent cleaning and calibration, and spatial and application dependency among different water bodies. A soft sensor is an efficient and convenient alternative approach for water quality monitoring. In this paper, we propose a machine learning-based soft sensor model to estimate biological oxygen demand (BOD), a time-consuming and challenging process to measure. We also propose a system architecture for implementing the soft sensor both on the cloud and edge layers, so that the edge device can make adaptive decisions in real time by monitoring the quality of water. A comparative study between the computational performance of edge and cloud nodes in terms of prediction accuracy, learning time, and decision time for different machine learning (ML) algorithms is also presented. This paper establishes that BOD soft sensors are efficient, less costly, and reasonably accurate with an example of a real-life application. Here, the IBK ML technique proves to be the most efficient in predicting BOD. The experimental setup uses 100 test readings of STP water samples to evaluate the performance of the IBK technique, and the statistical measures are reported as correlation coefficient = 0.9273, MAE = 0.082, RMSE = 0.1994, RAE = 17.20%, RRSE = 37.62%, and edge response time = 0.15 s only.

scholarly journals Field Spectroscopy as a Tool for Enhancing Water Quality Monitoring in the ACE Basin, SC

2017 ◽  
pp. 41-55 ◽  
Author(s):  
Caitlyn C. Mayer ◽  
Khalid A. Ali
Keyword(s):  
Water Quality ◽  
South Carolina ◽  
Chlorophyll A ◽  
Algal Species ◽  
Water Quality Monitoring ◽  
Water Systems ◽  
Quality Monitoring ◽  
Least Squares Regression ◽  
Monitoring Methods

The Ashepoo, Combahee, Edisto (ACE) Basin in South Carolina is one of the largest undeveloped estuaries in the Southeastern United States. This system is monitored and protected by several government agencies to ensure its health and preservation. However, as populations in surrounding cities rapidly expand and land is urbanized, the surrounding water systems may decline from an influx of contaminants, leading to hypoxia, fish kills, and eutrophication. Conventional in situ water quality monitoring methods are timely and costly. Satellite remote sensing methods are used globally to monitor water systems and can produce an instantaneous synopsis of color-producing agents (CPAs), including chlorophyll-a, suspended matter (TSM), and colored-dissolved organic matter by applying bio-optical models. In this study, field, laboratory, and historical land use land cover (LULC) data were collected during the summers of 2002, 2011, 2015, and 2016. The results indicated higher levels of chlorophyll, ranging from 2.94 to 12.19 μg/L, and TSM values were from 60.4 to 155.2 mg/L between field seasons, with values increasing with time. A model was developed using multivariate, partial least squares regression (PLSR) to identify wavelengths that are more sensitive to chlorophyll-a (R2 = 0.49; RMSE = 1.8 μg/L) and TSM (R2 = 0.40; RMSE = 12.9 mg/L). The imbrication of absorption and reflectance features characterizing sediments and algal species in ACE Basin waters make it difficult for remote sensors to distinguish variations among in situ concentrations. The results from this study provide a strong foundation for the future of water quality monitoring and for the protection of biodiversity in the ACE basin.

scholarly journals Analysis of recurring patchiness in satellite-derived chlorophyll a to aid the selection of representative sites for lake water quality monitoring

2021 ◽  
Vol 104 ◽  
pp. 102547
Author(s):  
Moritz K Lehmann ◽  
Eike M Schütt ◽  
Martin Hieronymi ◽  
James Dare ◽  
Hajo Krasemann
Keyword(s):  
Water Quality ◽  
Chlorophyll A ◽  
Lake Water ◽  
Water Quality Monitoring ◽  
Quality Monitoring ◽  
Lake Water Quality ◽  
Selection Of

scholarly journals Water monitoring and analytic based thingspeak

2020 ◽  
Vol 10 (4) ◽  
pp. 3588
Author(s):  
Abbas Hussien Miry ◽  
Gregor Alexander Aramice
Keyword(s):  
Water Quality ◽  
Normal Values ◽  
Water Quality Monitoring ◽  
Lag Time ◽  
Quality Parameters ◽  
Quality Monitoring ◽  
Proposed Model ◽  
Response To Water ◽  
Matlab Programming ◽  
The Internet Of Things

Diseases associated with bad water have largely reported cases annually leading to deaths, therefore the water quality monitoring become necessary to provide safe water. Traditional monitoring includes manual gathering of samples from different points on the distributed site, and then testing in laboratory. This procedure has proven that it is ineffective because it is laborious, lag time and lacks online results to enhance proactive response to water pollution. Emergence of the Internet of Things (IoT) and step towards the smart life poses the successful using of IoT. This paper presents a water quality monitoring using IoT based ThingSpeak platform that provides analytic tools and visualization using MATLAB programming. The proposed model is used to test water samples using sensor fusion technique such as TDS and Turbidity, and then uploading data online to ThingSpeak platform to monitor and analyze. The system notifies authorities when there are water quality parameters out of a predefined set of normal values. A warning will be notified to user by IFTTT protocol.

Water quality monitoring with purpose: Using a novel framework and leveraging long-term data

2021 ◽  
pp. 151729
Author(s):  
Nelson da Luz ◽  
John E. Tobiason ◽  
Emily Kumpel
Keyword(s):  
Water Quality ◽  
Water Quality Monitoring ◽  
Quality Monitoring ◽  
Term Data

scholarly journals Use of Artificial Neural Networks and Multiple Linear Regression Model for the Prediction of Dissolved Oxygen in Rivers: Case Study of Hydrographic Basin of River Nyando, Kenya

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-23 ◽  
Author(s):  
Yashon O. Ouma ◽  
Clinton O. Okuku ◽  
Evalyne N. Njau
Keyword(s):  
Water Quality ◽  
Linear Regression ◽  
Dissolved Oxygen ◽  
Multiple Linear Regression ◽  
Pearson Correlation ◽  
Multiple Linear Regression Model ◽  
Water Quality Monitoring ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Quality Monitoring

The process of predicting water quality over a catchment area is complex due to the inherently nonlinear interactions between the water quality parameters and their temporal and spatial variability. The empirical, conceptual, and physical distributed models for the simulation of hydrological interactions may not adequately represent the nonlinear dynamics in the process of water quality prediction, especially in watersheds with scarce water quality monitoring networks. To overcome the lack of data in water quality monitoring and prediction, this paper presents an approach based on the feedforward neural network (FNN) model for the simulation and prediction of dissolved oxygen (DO) in the Nyando River basin in Kenya. To understand the influence of the contributing factors to the DO variations, the model considered the inputs from the available water quality parameters (WQPs) including discharge, electrical conductivity (EC), pH, turbidity, temperature, total phosphates (TPs), and total nitrates (TNs) as the basin land-use and land-cover (LULC) percentages. The performance of the FNN model is compared with the multiple linear regression (MLR) model. For both FNN and MLR models, the use of the eight water quality parameters yielded the best DO prediction results with respective Pearson correlation coefficient R values of 0.8546 and 0.6199. In the model optimization, EC, TP, TN, pH, and temperature were most significant contributing water quality parameters with 85.5% in DO prediction. For both models, LULC gave the best results with successful prediction of DO at nearly 98% degree of accuracy, with the combination of LULC and the water quality parameters presenting the same degree of accuracy for both FNN and MLR models.

Lagoon water quality monitoring based on digital image analysis and machine learning estimators

2020 ◽  
Vol 172 ◽  
pp. 115471 ◽  
Author(s):  
Yuanhong Li ◽  
Xiao Wang ◽  
Zuoxi Zhao ◽  
Sunghwa Han ◽  
Zong Liu
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Image Analysis ◽  
Digital Image ◽  
Digital Image Analysis ◽  
Water Quality Monitoring ◽  
Quality Monitoring ◽  
Lagoon Water

scholarly journals Monitoring Water Quality of Valle de Bravo Reservoir, Mexico, Using Entire Lifespan of MERIS Data and Machine Learning Approaches

2020 ◽  
Vol 12 (10) ◽  
pp. 1586
Author(s):  
Leonardo F. Arias-Rodriguez ◽  
Zheng Duan ◽  
Rodrigo Sepúlveda ◽  
Sergio I. Martinez-Martinez ◽  
Markus Disse
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Water Quality ◽  
Water Quality Monitoring ◽  
Temporal Variations ◽  
Quality Parameters ◽  
Parameters Estimation ◽  
Learning Approaches ◽  
Effects Of Drought

Remote-sensing-based machine learning approaches for water quality parameters estimation, Secchi Disk Depth (SDD) and Turbidity, were developed for the Valle de Bravo reservoir in central Mexico. This waterbody is a multipurpose reservoir, which provides drinking water to the metropolitan area of Mexico City. To reveal the water quality status of inland waters in the last decade, evaluation of MERIS imagery is a substantial approach. This study incorporated in-situ collected measurements across the reservoir and remote sensing reflectance data from the Medium Resolution Imaging Spectrometer (MERIS). Machine learning approaches with varying complexities were tested, and the optimal model for SDD and Turbidity was determined. Cross-validation demonstrated that the satellite-based estimates are consistent with the in-situ measurements for both SDD and Turbidity, with R2 values of 0.81 to 0.86 and RMSE of 0.15 m and 0.95 nephelometric turbidity units (NTU). The best model was applied to time series of MERIS images to analyze the spatial and temporal variations of the reservoir’s water quality from 2002 to 2012. Derived analysis revealed yearly patterns caused by dry and rainy seasons and several disruptions were identified. The reservoir varied from trophic to intermittent hypertrophic status, while SDD ranged from 0–1.93 m and Turbidity up to 23.70 NTU. Results suggest the effects of drought events in the years 2006 and 2009 on water quality were correlated with water quality detriment. The water quality displayed slow recovery through 2011–2012. This study demonstrates the usefulness of satellite observations for supporting inland water quality monitoring and water management in this region.

scholarly journals Real-time water quality monitoring through Internet of Things and ANOVA-based analysis: a case study on river Krishna

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Prasad M. Pujar ◽  
Harish H. Kenchannavar ◽  
Raviraj M. Kulkarni ◽  
Umakant P. Kulkarni
Keyword(s):  
Water Quality ◽  
Internet Of Things ◽  
Real Time ◽  
River Basin ◽  
Water Quality Monitoring ◽  
Quality Parameters ◽  
Quality Monitoring ◽  
Quality Analysis ◽  
Water Quality Analysis

AbstractIn this paper, an attempt has been made to develop a statistical model based on Internet of Things (IoT) for water quality analysis of river Krishna using different water quality parameters such as pH, conductivity, dissolved oxygen, temperature, biochemical oxygen demand, total dissolved solids and conductivity. These parameters are very important to assess the water quality of the river. The water quality data were collected from six stations of river Krishna in the state of Karnataka. River Krishna is the fourth largest river in India with approximately 1400 km of length and flows from its origin toward Bay of Bengal. In our study, we have considered only stretch of river Krishna flowing in state of Karnataka, i.e., length of about 483 km. In recent years, the mineral-rich river basin is subjected to rapid industrialization, thus polluting the river basin. The river water is bound to get polluted from various pollutants such as the urban waste water, agricultural waste and industrial waste, thus making it unusable for anthropogenic activities. The traditional manual technique that is under use is a very slow process. It requires staff to collect the water samples from the site and take them to the laboratory and then perform the analysis on various water parameters which is costly and time-consuming process. The timely information about water quality is thus unavailable to the people in the river basin area. This creates a perfect opportunity for swift real-time water quality check through analysis of water samples collected from the river Krishna. IoT is one of the ways with which real-time monitoring of water quality of river Krishna can be done in quick time. In this paper, we have emphasized on IoT-based water quality monitoring by applying the statistical analysis for the data collected from the river Krishna. One-way analysis of variance (ANOVA) and two-way ANOVA were applied for the data collected, and found that one-way ANOVA was more effective in carrying out water quality analysis. The hypotheses that are drawn using ANOVA were used for water quality analysis. Further, these analyses can be used to train the IoT system so that it can take the decision whenever there is abnormal change in the reading of any of the water quality parameters.

Sign in / Sign up

Export Citation Format

Share Document