Using Machine Learning to Model Dead Zones in Lakes – UConn Today

Using Machine Learning to Model Dead Zones in Lakes - UConn Today  University of Connecticut

Using Machine Learning to Model Dead Zones in Lakes – UConn Today

Sustainable Development Goals and Aquatic Ecosystems

Aquatic ecosystems are complex environments that can be affected by many variables, including weather, the biological activities of the organisms living within them, and anthropogenic nutrient pollution. The influence these variables may have on aquatic ecosystems can also depend on the characteristics of the water body, such as temperature and depth. These interconnected processes can be tipped out of balance with devastating consequences.

Research on Lake Water Quality

To help anticipate these consequences, a group of UConn researchers have developed a versatile computer modeling method using machine learning to enhance existing efforts to monitor and predict lake water quality. The method was recently published in Environmental Modeling & Software.

Collaboration and Focus

Department of Civil & Environmental Engineering and Head of the Atmospheric and Air Quality Modeling Group Associate Professor Marina Astitha explains the research was five years in the making and is a collaboration with a former student, Christina Feng Chang ‘22 Ph.D. as part of her dissertation, and Department of Marine Sciences and Head of the Environmental Chemistry and Geochemistry research group, Professor Penny Vlahos.

Eutrophication and Algal Blooms

Aquatic environments are susceptible to eutrophication, a process triggered by excess nutrients, most prominently tied to fertilizer runoff from agricultural activities, that make their way to water ecosystems and lead to algae blooms. The increase in growth and eventual decomposition of these plant-like materials consume much or all of the available oxygen, to the detriment of other organisms in the environment.

  • Oxygen-deprived or hypoxic areas are dubbed “dead zones”
  • Can lead to fish mortality, water quality issues, and other harmful environmental and economic impacts

Modeling for Monitoring and Prediction

The researchers focused their study on Lake Erie’s central basin, which has experienced seasonal algal blooms and eutrophication events for decades. The lake’s proximity to large agricultural areas and metropolitan centers presents a unique set of challenges that the team aimed to study.

  1. Millions of people rely on Lake Erie for their water
  2. Modeling instrumental in monitoring water quality

Machine Learning Models

No single model can account for all the variables that impact water quality. To address this, the researchers started building machine learning models to integrate data from different sources and train machine learning algorithms with observations in the lake.

  • First publication focused on modeling of chlorophyll a
  • Second paper looked at nutrient pollution from rivers and streams

Understanding Eutrophication Processes

The model was designed to predict dissolved oxygen (DO) and apparent oxygen utilization (AOU) in Lake Erie’s central basin to understand the dynamic processes involved in eutrophication events. The results accurately predicted observed conditions.

  1. Thermal stratification identified as most impactful variable driving eutrophication
  2. Model successfully predicted DO and AOU conditions

Future Research and Climate Change

Models like this will become increasingly important for water quality monitoring as climate change continues. Future research includes applying the methodology to other ecosystems and investigating the impact of climate change scenarios on water quality.

  • Climate change expected to intensify stratification and nutrient input into lakes
  • Models crucial for supporting decision-making in changing environmental conditions

Astitha says, “In the era of machine learning and artificial intelligence, we are trying to bring that piece in and see how helpful it is, which motivated me to start and continue this work.”

## Sustainable Development Goals (SDGs) Addressed in the Article

### SDG 6: Clean Water and Sanitation
The article addresses the issue of monitoring and predicting lake water quality, specifically focusing on Lake Erie, which is a vital water source for millions of people. The research aims to understand and mitigate the impacts of eutrophication events on aquatic ecosystems.

### SDG 14: Life Below Water
The article discusses the detrimental effects of eutrophication on aquatic environments, leading to dead zones, fish mortality, and water quality issues. The research aims to develop models to monitor and predict these events in bodies of water like Lake Erie.

## Specific Targets and Indicators

### Target 6.3: Improve water quality by reducing pollution, eliminating dumping, and minimizing release of hazardous chemicals
The research focuses on understanding the impact of anthropogenic nutrient pollution on aquatic ecosystems, particularly in Lake Erie, due to fertilizer runoff from agricultural activities.

### Indicator 14.1.1: Index of coastal eutrophication and floating plastic debris density
The study of eutrophication events in Lake Erie, caused by excess nutrients leading to algae blooms, serves as an indicator of the environmental degradation affecting aquatic ecosystems.

## Table of SDGs, Targets, and Indicators

| SDGs | Targets | Indicators |
|—————————|——————————————————————————————-|—————————————————————————————————–|
| SDG 6: Clean Water and Sanitation | Target 6.3: Improve water quality by reducing pollution, eliminating dumping, and minimizing release of hazardous chemicals | Indicator 14.1.1: Index of coastal eutrophication and floating plastic debris density |
| SDG 14: Life Below Water | Target 6.3: Improve water quality by reducing pollution, eliminating dumping, and minimizing release of hazardous chemicals | Indicator 14.1.1: Index of coastal eutrophication and floating plastic debris density |

Copyright: Dive into this article, curated with care by SDG Investors Inc. Our advanced AI technology searches through vast amounts of data to spotlight how we are all moving forward with the Sustainable Development Goals. While we own the rights to this content, we invite you to share it to help spread knowledge and spark action on the SDGs.

Fuente: today.uconn.edu

 

Join us, as fellow seekers of change, on a transformative journey at https://sdgtalks.ai/welcome, where you can become a member and actively contribute to shaping a brighter future.