Related Experiment Video
Updated: Sep 20, 2025
12:44
Watershed Planning within a Quantitative Scenario Analysis Framework
Published on: July 24, 2016
8.1K
A catchment-scale model of river water quality by Machine Learning
Maria Grazia Zanoni1, Bruno Majone1, Alberto Bellin1
1Department of Civil, Environmental and Mechanical Engineering, University of Trento, via Mesiano 77, I-38123 Trento, Italy.
The Science of the Total Environment
|June 6, 2022
Summary
Machine learning models accurately predict river water quality parameters like temperature and pollutants. Deep feed-forward neural networks proved most effective, outperforming linear regression for complex environmental data analysis.
Area of Science:
- Environmental Science
- Water Resource Management
- Data Science
Background:
- River water quality is a global concern, impacted by pollutants affecting freshwater ecosystems.
- Understanding driver-parameter relationships at regional scales is crucial for pollution control.
- Developing accurate regional water quality models is challenging due to complex, non-linear relationships.
Purpose of the Study:
- To develop and compare regional water quality models using Machine Learning (ML) algorithms.
- To assess the performance of Random Forest and Deep feed-forward Neural Networks against Linear Regression.
- To model key water quality variables: temperature, dissolved oxygen, arsenic, sulfate, chloride, and electrical conductivity.
Main Methods:
- Utilized two ML algorithms: Random Forest and Deep feed-forward Neural Network.
- Developed regional models for multiple water quality parameters.
- Compared ML model performance against a standard Linear Regression model.
Main Results:
- ML algorithms significantly outperformed Linear Regression in accuracy for all tested variables.
- Deep feed-forward Neural Network demonstrated superior performance, effectively capturing non-linear relationships and driver importance.
- Temporal variables (Julian day, year) effectively substituted air temperature for modeling water temperature and dissolved oxygen.
Conclusions:
- ML, particularly Deep feed-forward Neural Networks, offers a powerful approach for regional water quality modeling.
- The study highlights the complex interplay of geogenic and anthropogenic sources for pollutants like arsenic, sulfate, and chloride.
- Findings suggest a non-uniform, spatial geogenic origin for arsenic, influenced by dilution effects.
Related Concept Videos
01:30Typical Model Studies
448
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
448
01:19Quality of Water
200
In concrete preparation, the quality of water is paramount as it affects the strength and durability of the concrete. Potable water is usually preferred; however, it must not have excessive sodium or potassium to prevent compromising the concrete's integrity. Water quality is typically evaluated based on impurities such as dissolved solids, chlorides, and sulfates, and its pH value is ideally between 6 and 8. Even slightly acidic natural water may be acceptable unless it contains harmful...
200
01:14Testing Water Quality
192
When the quality of water for concrete preparation is uncertain, its impact on the setting time of cement and compressive strength of mortar is assessed by comparison with de-ionized or distilled water benchmarks. American Society for Testing and Materials (ASTM) C1602 requires the setting times to be within 90 minutes of the control, British Standard (BS) 3146:1980 allows a 30-minute variance in the initial setting, while British Standards European Norm (BS EN) 1008 specifies initial setting...
192
01:12Modeling and Similitude
350
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
350
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
341
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
341
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
109
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
109