scholarly journals Monitoring Water Resources through a Bayesian Optimization-based Approach using Multiple Surface Vehicles: The Ypacarai Lake Case Study

2021 ◽  
Author(s):  
Federico Peralta Samaniego ◽  
Sergio Toral Marín ◽  
Daniel Gutierrez Reina
Keyword(s):  
Water Quality ◽  
Mean Squared Error ◽  
Bayesian Optimization ◽  
Water Quality Parameter ◽  
Optimization Approach ◽  
Decision Strategy ◽  
Sequential Decision ◽  
Partition System ◽  
Autonomous Surface Vehicle ◽  
Voronoi Partition

<div>Bayesian optimization is a popular sequential decision strategy that can be used for environmental monitoring. In this work, we propose an efficient multi-Autonomous Surface Vehicle system capable of monitoring the Ypacarai Lake (San Bernardino, Paraguay) (60 km<sup>2</sup>) using the Bayesian optimization approach with a Voronoi Partition system. The system manages to quickly approximate the real unknown distribution map of a water quality parameter using Gaussian Processes as surrogate models. Furthermore, to select new water quality measurement locations, an acquisition function adapted to vehicle energy constraints is used. Moreover, a Voronoi Partition system helps to distributing the workload with all the available vehicles, so that robustness and scalability is assured. For evaluation purposes, we use both the mean squared error and computational efficiency. The results showed that our method manages to efficiently monitor the Ypacarai Lake, and also provides confident approximate models of water quality parameters. It has been observed that, for every vehicle, the resulting surrogate model improves by 38%.</div>

Monitoring Water Resources through a Bayesian Optimization-based Approach using Multiple Surface Vehicles: The Ypacarai Lake Case Study

2021 ◽  
Author(s):  
Federico Peralta Samaniego ◽  
Sergio Toral Marín ◽  
Daniel Gutierrez Reina
Keyword(s):  
Water Quality ◽  
Mean Squared Error ◽  
Bayesian Optimization ◽  
Water Quality Parameter ◽  
Optimization Approach ◽  
Decision Strategy ◽  
Sequential Decision ◽  
Partition System ◽  
Autonomous Surface Vehicle ◽  
Voronoi Partition

<div>Bayesian optimization is a popular sequential decision strategy that can be used for environmental monitoring. In this work, we propose an efficient multi-Autonomous Surface Vehicle system capable of monitoring the Ypacarai Lake (San Bernardino, Paraguay) (60 km<sup>2</sup>) using the Bayesian optimization approach with a Voronoi Partition system. The system manages to quickly approximate the real unknown distribution map of a water quality parameter using Gaussian Processes as surrogate models. Furthermore, to select new water quality measurement locations, an acquisition function adapted to vehicle energy constraints is used. Moreover, a Voronoi Partition system helps to distributing the workload with all the available vehicles, so that robustness and scalability is assured. For evaluation purposes, we use both the mean squared error and computational efficiency. The results showed that our method manages to efficiently monitor the Ypacarai Lake, and also provides confident approximate models of water quality parameters. It has been observed that, for every vehicle, the resulting surrogate model improves by 38%.</div>

Deep learning for water quality prediction: the application of LSTM model to predict water quality in catchment scale

2021 ◽  
Author(s):  
Amir Sahraei ◽  
Lutz Breuer ◽  
Philipp Kraft ◽  
Tobias Houska
Keyword(s):  
Water Quality ◽  
Water Temperature ◽  
Mean Squared Error ◽  
Model Performance ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Bayesian Optimization ◽  
Optimization Approach ◽  
Quality Prediction ◽  
Water Quality Prediction

&lt;p&gt;The prediction of water quality is an efficient way for managing water resources and protecting ecosystems by providing an early warning against water quality deterioration. So far, the classical approach is to predict water quality by the utilization of complex process-based water quality models. However, these models are not easy to set up and require comprehensive input data. The local characteristics, detailed process understandings and eventually data from land users such as farmers are needed, to build up a valid model structure. Such constraints can end up in wrong scientific conclusions ranging from false alarms to unpredicted environmental pollution in practical water monitoring application. Long short-term memory (LSTM) algorithms are known to be able to overcome some of the typical constraints in hydrological model applications. However, their performance in water quality prediction has rarely been explored. In this study, we investigate the ability of a LSTM model to predict the complex, nonlinear behavior of water quality parameters in the Schwingbach Environmental Observatory (SEO), Germany.&amp;#160; We predict weekly nitrogen-nitrate concentrations, weekly stable isotopes of water concentrations (&amp;#948;&lt;sup&gt;18&lt;/sup&gt;O) and daily water temperature in six stream&amp;#8209; and six groundwater sources with different landuse and hillslope conditions. We use meteorological forcing data and catchment attributes as input variables. To ensure an efficient model performance, we employ a Bayesian optimization approach to optimize the hyperparameters of the LSTM. The model performance is evaluated by the Root Mean Squared Error (RMSE). Our LSTM is robust in capturing the dynamics of the water quality parameters over time. The RMSE for the LSTM performance ranges from 0.27 to 3.38 mg/l, from 0.069 to 0.27 &amp;#8240; and from 1.3 to 2.1 &amp;#176;C for nitrogen&amp;#8209;nitrate, &amp;#948;&lt;sup&gt;18&lt;/sup&gt;O and water temperature, respectively. We compare the RMSE with statistical parameters of data. Results confirm that the LSTM is a promising tool for early risk assessment of water quality, particularly in view that only a minimal set of catchment information is needed to gain robust results.&lt;/p&gt;

scholarly journals A Bayesian Optimization Approach for Multi-Function Estimation for Environmental Monitoring Using an Autonomous Surface Vehicle: Ypacarai Lake Case Study

Electronics ◽  
2021 ◽  
Vol 10 (8) ◽  
pp. 963
Author(s):  
Federico Peralta ◽  
Daniel Gutierrez Reina ◽  
Sergio Toral ◽  
Mario Arzamendia ◽  
Derlis Gregor
Keyword(s):  
Water Quality ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Bayesian Optimization ◽  
Computational Time ◽  
Optimization Approach ◽  
Test Scenario ◽  
Sequential Method ◽  
Autonomous Surface Vehicle ◽  
Better Than

Bayesian optimization is a sequential method that can optimize a single and costly objective function based on a surrogate model. In this work, we propose a Bayesian optimization system dedicated to monitoring and estimating multiple water quality parameters simultaneously using a single autonomous surface vehicle. The proposed work combines different strategies and methods for this monitoring task, evaluating two approaches for acquisition function fusion: the coupled and the decoupled techniques. We also consider dynamic parametrization of the maximum measurement distance traveled by the ASV so that the monitoring system balances the total number of measurements and the total distance, which is related to the energy required. To evaluate the proposed approach, the Ypacarai Lake (Paraguay) serves as the test scenario, where multiple maps of water quality parameters, such as pH and dissolved oxygen, need to be obtained efficiently. The proposed system is compared with the predictive entropy search for multi-objective optimization with constraints (PESMOC) algorithm and the genetic algorithm (GA) path planning for the Ypacarai Lake scenario. The obtained results show that the proposed approach is 10.82% better than other optimization methods in terms of R2 score with noiseless measurements and up to 17.23% better when the data are noisy. Additionally, the proposed approach achieves a good average computational time for the whole mission when compared with other methods, 3% better than the GA technique and 46.5% better than the PESMOC approach.

scholarly journals A Bayesian Optimization Approach for Water Resources Monitoring Through an Autonomous Surface Vehicle: The Ypacarai Lake Case Study

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 9163-9179 ◽  
Author(s):  
Federico Peralta Samaniego ◽  
Daniel Gutierrez Reina ◽  
Sergio L. Toral Marin ◽  
Mario Arzamendia ◽  
Derlis O. Gregor
Keyword(s):  
Water Resources ◽  
Bayesian Optimization ◽  
Optimization Approach ◽  
Autonomous Surface Vehicle

Water quality parameter forecast based on grey neural network modeling

2009 ◽  
Vol 29 (6) ◽  
pp. 1529-1531 ◽  
Author(s):  
Wei-ren SHI ◽  
Yan-xia WANG ◽  
Yun-jian TANG ◽  
Min FAN
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Network Modeling ◽  
Quality Parameter ◽  
Water Quality Parameter ◽  
Neural Network Modeling

Spatio-temporal Variations in Water Quality Parameter Trends in River Waters

2018 ◽  
Vol 69 (10) ◽  
pp. 2940-2952 ◽  
Author(s):  
Martina Zelenakova ◽  
Pavol Purcz ◽  
Radu Daniel Pintilii ◽  
Peter Blistan ◽  
Petr Hlustik ◽  
...  
Keyword(s):  
Water Quality ◽  
Chemical Oxygen Demand ◽  
Quality Indicators ◽  
Water Resource Management ◽  
Oxygen Demand ◽  
Temporal Variations ◽  
Water Quality Parameter ◽  
Agricultural Activity ◽  
Water Quality Indicators ◽  
Nitrite Nitrogen

Evaluating trends in water quality indicators is a crucial issue in integrated water resource management in any country. In this study eight chemical and physical water quality indicators were analysed in seven river profiles in the River Laborec in eastern Slovakia. The analysed water quality parameters were biochemical oxygen demand (BOD5), chemical oxygen demand (CODCr), pH, temperature (t), ammonium nitrogen (NH4+-N), nitrite nitrogen (NO2--N), nitrate nitrogen (NO3--N), and total phosphorus (TP). Data from the monitored indicators were provided by the Ko�ice branch of the Slovakian Water Management Company, over a period of 15 years from 1999 to 2013. Mann�Kendall non-parametric statistical test was used for the trend analysis. Biochemical and chemical oxygen demand, ammonium and nitrite nitrogen content exhibit decreasing trends in the River Laborec. Decreasing agricultural activity in the area has had a significant impact on the trends in these parameters. However, NO2--N was the significant parameter of water quality because it mostly exceeds the limit value set in Slovak legislation, Regulation No. 269/2010 Coll. In addition, water temperature revealed an increasing trend which could be caused by global increase in air temperature. These results indicate that human activity significantly impacts the water quality.

scholarly journals Strategies for Improving Optimal Positioning of Quality Sensors in Urban Drainage Systems for Non-Conservative Contaminants

Water ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 934
Author(s):  
Mariacrocetta Sambito ◽  
Gabriele Freni
Keyword(s):  
Treatment Plant ◽  
Optimal Solution ◽  
Monitoring Network ◽  
Computational Effort ◽  
Bayesian Optimization ◽  
Urban Drainage ◽  
Optimization Approach ◽  
Sensor Location ◽  
Contamination Source ◽  
Monitoring Point

In the urban drainage sector, the problem of polluting discharges in sewers may act on the proper functioning of the sewer system, on the wastewater treatment plant reliability and on the receiving water body preservation. Therefore, the implementation of a chemical monitoring network is necessary to promptly detect and contain the event of contamination. Sensor location is usually an optimization exercise that is based on probabilistic or black-box methods and their efficiency is usually dependent on the initial assumption made on possible eligibility of nodes to become a monitoring point. It is a common practice to establish an initial non-informative assumption by considering all network nodes to have equal possibilities to allocate a sensor. In the present study, such a common approach is compared with different initial strategies to pre-screen eligible nodes as a function of topological and hydraulic information, and non-formal 'grey' information on the most probable locations of the contamination source. Such strategies were previously compared for conservative xenobiotic contaminations and now they are compared for a more difficult identification exercise: the detection of nonconservative immanent contaminants. The strategies are applied to a Bayesian optimization approach that demonstrated to be efficient in contamination source location. The case study is the literature network of the Storm Water Management Model (SWMM) manual, Example 8. The results show that the pre-screening and ‘grey’ information are able to reduce the computational effort needed to obtain the optimal solution or, with equal computational effort, to improve location efficiency. The nature of the contamination is highly relevant, affecting monitoring efficiency, sensor location and computational efforts to reach optimality.

scholarly journals Nutrient, pH, Alkalinity, and Ionic Property Levels in Runoff Containment Basins in Alabama, Louisiana, Maryland, Mississippi, and Virginia Ornamental Plant Nurseries

HortScience ◽  
2017 ◽  
Vol 52 (4) ◽  
pp. 641-648 ◽  
Author(s):  
Warren E. Copes ◽  
Haibo Zhang ◽  
Patricia A. Richardson ◽  
Bruk E. Belayneh ◽  
Andrew Ristvey ◽  
...  
Keyword(s):  
Water Quality ◽  
Ammonium Nitrogen ◽  
Quality Parameter ◽  
Ornamental Plant ◽  
Total Alkalinity ◽  
Water Quality Parameter ◽  
Runoff Water ◽  
Manganese Zinc ◽  
Water Ph ◽  
Parameter Values

Nine runoff containment basins (RCBs), used directly or indirectly for irrigating plants in ornamental plant nurseries, and one adjacent stream were sampled for water quality between Feb. and July 2013 in Maryland (MD), Mississippi (MS), and Virginia (VA). Triplicate water samples were taken monthly. Analysis was done for 18 water quality variables including nitrate-nitrogen (NO3−-N) and ammonium-nitrogen (NH4+-N), orthophosphate-phosphorus (PO4-P) and total-phosphorus (T-P), potassium, calcium, magnesium, sulfur, aluminum, boron (B), copper (Cu), iron (Fe), manganese, zinc (Zn), pH, total alkalinity (T-Alk), electrical conductivity (EC), and sodium. Additionally, 15 RCBs from 10 nurseries in Alabama (AL), Louisiana (LA), and MS were sampled in 2014 and 2016. Most prevalent correlations (P = 0.01) were between macronutrients, EC, B, Fe, and Zn, but none were prevalent across a majority of RCBs. Water quality parameter values were mostly present at low to preferred levels in all 25 waterways. Macronutrient levels were highest for a RCB that receives fertility from fertigation derived runoff. Water pH ranged from acidic to alkaline (>8). Results of this study show water quality in RCBs can be suitable for promoting plant health in ornamental plant nurseries, but also shows levels will vary between individual RCBs, therefore demonstrates need to verify water quality from individual water sources.

Water-Quality Assessment of Lv-Tang River in Zhanjiang, China

2013 ◽  
Vol 295-298 ◽  
pp. 755-758 ◽  
Author(s):  
Ya Yun Liu ◽  
Zhi Hong Li ◽  
Xiao Jian Liang ◽  
Yan Peng Lin ◽  
Rong Hao Wu ◽  
...  
Keyword(s):  
Water Quality ◽  
Water Quality Index ◽  
Quality Index ◽  
Oxygen Demand ◽  
Pollution Index ◽  
Ammonia Nitrogen ◽  
Single Parameter ◽  
Water Quality Parameter ◽  
National Quality

Based on the water quality investigation data of December in 2010, the water environment quality of Lv-tang River in Zhanjiang national urban wetland park was assessed using single water quality parameter model and integrated water quality index model. The results show that the water quality of Lv-tang River is worse than the national quality standards for Grade V. The water is polluted seriously. The main pollutants are total nitrogen (TN), ammonia nitrogen (NH3-N) and chemical oxygen demand CODCr with their average concentrations of 60.49 mg/L, 30.57 mg/L and 227.38mg/L, respectively. The averages of their single parameter pollution index are 30.25 , 19.79 and 8.74. The average of single parameter pollution index of the river is 8.23 which indicated that the river belongs to heavy pollution zone. The integrated water quality index was 22.5 showing that the river belongs to serious pollution zone.

scholarly journals Optimal Water Quality Sensor Placement by Accounting for Possible Contamination Events in Water Distribution Networks

Water ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 1999
Author(s):  
Malvin S. Marlim ◽  
Doosun Kang
Keyword(s):  
Water Quality ◽  
Water Distribution ◽  
Sensor Placement ◽  
Pso Algorithm ◽  
Distribution Networks ◽  
Fair Value ◽  
Water Distribution Networks ◽  
Optimization Approach ◽  
Protection Measure ◽  
Contamination Events

Contamination in water distribution networks (WDNs) can occur at any time and location. One protection measure in WDNs is the placement of water quality sensors (WQSs) to detect contamination and provide information for locating the potential contamination source. The placement of WQSs in WDNs must be optimally planned. Therefore, a robust sensor-placement strategy (SPS) is vital. The SPS should have clear objectives regarding what needs to be achieved by the sensor configuration. Here, the objectives of the SPS were set to cover the contamination event stages of detection, consumption, and source localization. As contamination events occur in any form of intrusion, at any location and time, the objectives had to be tested against many possible scenarios, and they needed to reach a fair value considering all scenarios. In this study, the particle swarm optimization (PSO) algorithm was selected as the optimizer. The SPS was further reinforced using a databasing method to improve its computational efficiency. The performance of the proposed method was examined by comparing it with a benchmark SPS example and applying it to DMA-sized, real WDNs. The proposed optimization approach improved the overall fitness of the configuration by 23.1% and showed a stable placement behavior with the increase in sensors.

Sign in / Sign up

Export Citation Format

Share Document