Identifying Key Factors Affecting Harmful Algal Blooms in Western Lake Erie from the Perspective of Machine Learning

Author(s):  
Jimmy Nguyen ◽  
Zesheng Chen ◽  
Veronika Meyer ◽  
Dong Chen
2019 ◽  
Vol 45 (3) ◽  
pp. 587-595 ◽  
Author(s):  
Nathan F. Manning ◽  
Yu-Chen Wang ◽  
Colleen M. Long ◽  
Isabella Bertani ◽  
Michael J. Sayers ◽  
...  

2014 ◽  
Vol 71 (11) ◽  
pp. 1642-1654 ◽  
Author(s):  
David F. Millie ◽  
Gary R. Weckman ◽  
Gary L. Fahnenstiel ◽  
Hunter J. Carrick ◽  
Ehsan Ardjmand ◽  
...  

Cyanobacterial harmful algal blooms (CyanoHABs), mainly composed of the genus Microcystis, occur frequently throughout the Laurentian Great Lakes. We used artificial neural networks (ANNs) involving 31 hydrological and meteorological predictors to model total phytoplankton (as chlorophyll a) and Microcystis biomass from 2009 to 2011 in western Lake Erie. Continuous ANNs provided modeled-measured correspondences (and modeling efficiencies) ranging from 0.87 to 0.97 (0.75 to 0.94) and 0.71 to 0.90 (0.45 to 0.88) for training–cross-validation and test data subsets of chlorophyll a concentrations and Microcystis biovolumes, respectively. Classification ANNs correctly assigned up to 94% of instances for Microcystis presence–absence. The influences of select predictors on phytoplankton and CyanoHAB niches were visualized using biplots and three-dimensional response surfaces. These then were used to generate mathematical expressions for the relationships between modeled CyanoHAB outcomes and the direct and interactive influences of environmental factors. Based on identified conditions (∼40 to 50 μg total phosphorus (TP)·L−1, 22 to 26 °C, and prolonged wind speeds less than ∼19 km·h−1) underlying the likelihood of occurrence and accumulation of phytoplankton and Microcystis, a “target” concentration of 30 μg TP·L−1 appears appropriate for alleviating blooms. ANNs generated robust ecological niche models for Microcystis, providing a predictive framework for quantitative visualization of nonlinear CyanoHAB–environmental interactions.


2017 ◽  
Vol 19 (3) ◽  
pp. 1149-1162 ◽  
Author(s):  
Michelle A. Berry ◽  
Timothy W. Davis ◽  
Rose M. Cory ◽  
Melissa B. Duhaime ◽  
Thomas H. Johengen ◽  
...  

PLoS ONE ◽  
2017 ◽  
Vol 12 (6) ◽  
pp. e0179622 ◽  
Author(s):  
Di Tian ◽  
Gengxin Xie ◽  
Jing Tian ◽  
Kuo-Hsin Tseng ◽  
C. K. Shum ◽  
...  

2020 ◽  
Vol 46 (2) ◽  
pp. 289-301 ◽  
Author(s):  
Dilrukshika S.W. Palagama ◽  
David Baliu-Rodriguez ◽  
Brenda K. Snyder ◽  
Jennifer A. Thornburg ◽  
Thomas B. Bridgeman ◽  
...  

2017 ◽  
Vol 1 (1) ◽  
pp. 1-8 ◽  
Author(s):  
Ramiro Berardo ◽  
Francesca Formica ◽  
Jeffrey Reutter ◽  
Ajay Singh

One of the focal events motivating the passage of the Clean Water Act in 1972 was the decline of water quality in Lake Erie, which was originally linked to insufficient treatment of wastewater in some of the biggest adjacent urban centers. The passing of the CWA and the adoption of the Great Lakes Water Quality Agreement in the early 1970s contributed to the quick improvement of water quality in the two ensuing decades, but the 1990s saw the return of water quality problems, indicated by the return of algal blooms to Western Lake Erie. Algal blooms typically occur when excess nutrients are produced by mixture of agricultural and urban practices, and they may threaten ecological stability and public health for millions dependent on the lake for drinking water, tourism, and fisheries. In this case study, we explore the relationship between human behavior and water quality impairments that lead to harmful algal blooms (HABs) in the Western Lake Erie Basin (WLEB), and in particular, the Maumee River Watershed. The case is designed to be taught in eight class meetings to an audience of upper-level undergraduate students, and has been tested in the classroom in consecutive semesters starting in the fall of 2015.


1975 ◽  
Vol 32 (10) ◽  
pp. 1733-1743 ◽  
Author(s):  
Wolf-Dieter N. Busch ◽  
Russell L. Scholl ◽  
Wilbur L. Hartman

Commercial production of walleyes (Stizostedion vitreum vitreum) from western Lake Erie declined from 5.9 million pounds in 1956 to 140,000 pounds by 1969. Since 1956, marked irregularity in year-class success has developed. Only four year-classes were considered good during 1959–70. The rate and regularity of water warming during the spring spawning and incubation periods in 1960–70 had a positive effect on the density of egg deposits and the resulting year-class strength. Rates of warming were not themselves detrimental, but rather the extended length of the incubation period in cool springs increased the exposure of eggs to such negative influences as dislodgment from the spawning reefs by strong current action generated by spring storms, or siltation and low oxygen tensions. The annual brood stock size had much less influence on year-class strength than did water temperature. Reproductive success was unrelated to fluctuations in size of suitable reef spawning area caused by changes in water level. Apparently the usable spawning area at any water level is more than adequate to serve the limited walleye brood stocks.


Author(s):  
Sharon Levy

In August 2014, the water supply for the city of Toledo, Ohio, was poisoned. Officials issued an order to the half- million residents connected to the municipal water supply: Don’t drink, cook, or brush your teeth with the water. Do not use it to bathe your children, and don’t give it to your pets. Stores ran out of bottled water, and residents had to wait in long lines or travel to neighboring towns to find more. The culprit was a bright green plume of Microcystis, a cyanobacterium that thrives in warm water tainted with heavy loads of phosphorus and nitrogen. Every spring, rains wash a pulse of nutrients off fertilized fields and send it down the Maumee and Sandusky rivers and into western Lake Erie. Every summer, as water temperatures rise, Microcystis forms an iridescent mat over parts of the lake’s surface. In early August 2014, strong winds blew a lawn of cyanobacteria over Toledo’s water intake, which lies just outside the Maumee’s mouth. Tests showed that the city’s water contained dangerous levels of microcystin, a liver toxin produced by the bloom. The drinking water crisis was a dramatic signal of Lake Erie’s descent back into eutrophication. In the 1980s, after sewage plants in the watershed were upgraded and phosphate detergents banned, Lake Erie experienced a revival. Algal blooms faded, and populations of walleye rebounded. The lake grew a thriving tourist industry based on sport fishing. Then, in 1995, researchers recorded the lake’s first wide­spread bloom of Microcystis. Eruptions of Microcystis have since become a predictable event striking the western Lake Erie basin every summer. The most widespread and long- lasting blooms hit in 2011 and 2015, after intense spring rains dumped heavy loads of nutrients into the lake. Climate models forecast warmer summer temperatures and heavier spring rains for the Great Lakes region. Those conditions are a recipe for more and larger algal blooms, and are likely to favor Microcystis in particular. The regulatory efforts of the 1970s and 1980s made great progress in cleaning up discharges from industries and sewage treatment plants, but failed to address nonpoint source pollution flowing from farm fields and city streets.


2020 ◽  
Vol 86 (22) ◽  
Author(s):  
Katelyn M. McKindles ◽  
Makayla A. Manes ◽  
Jonathan R. DeMarco ◽  
Andrew McClure ◽  
R. Michael McKay ◽  
...  

ABSTRACT Western Lake Erie (Laurentian Great Lakes) is prone to annual cyanobacterial harmful algal blooms (cHABs) dominated by Microcystis spp. that often yield microcystin toxin concentrations exceeding the federal EPA recreational contact advisory of 8 μg liter−1. In August 2014, microcystin levels were detected in finished drinking water above the World Health Organization 1.0 μg liter−1 threshold for consumption, leading to a 2-day disruption in the supply of drinking water for >400,000 residents of Toledo, Ohio (USA). Subsequent metatranscriptomic analysis of the 2014 bloom event provided evidence that release of toxin into the water supply was likely caused by cyanophage lysis that transformed a portion of the intracellular microcystin pool into the dissolved fraction, rendering it more difficult to eliminate during treatment. In August 2019, a similar increase in dissolved microcystins at the Toledo water intake was coincident with a viral lytic event caused by a phage consortium different in composition from what was detected following the 2014 Toledo water crisis. The most abundant viral sequence in metagenomic data sets was a scaffold from a putative member of the Siphoviridae, distinct from the Ma-LMM01-like Myoviridae that are typically documented to occur in western Lake Erie. This study provides further evidence that viral activity in western Lake Erie plays a significant role in transformation of microcystins from the particulate to the dissolved fraction and therefore requires monitoring efforts from local water treatment plants. Additionally, identification of multiple lytic cyanophages will enable the development of a quantitative PCR toolbox to assess viral activity during cHABs. IMPORTANCE Viral attack on cHABs may contribute to changes in community composition during blooms, as well as bloom decline, yet loss of bloom biomass does not eliminate the threat of cHAB toxicity. Rather, it may increase risks to the public by delivering a pool of dissolved toxin directly into water treatment utilities when the dominating Microcystis spp. are capable of producing microcystins. Detecting, characterizing, and quantifying the major cyanophages involved in lytic events will assist water treatment plant operators in making rapid decisions regarding the pool of microcystins entering the plant and the corresponding best practices to neutralize the toxin.


Sign in / Sign up

Export Citation Format

Share Document