Microcystin concentrations and congener composition in relation to environmental variables across 440 north-temperate and boreal lakes

MacKeigan, Paul W.; Zastepa, Arthur; Taranu, Zofia E.; Westrick, Judy A.; Liang, Anqi; Pick, Frances R.; Beisner, Beatrix E.; Gregory‐Eaves, Irene

doi:10.1016/j.scitotenv.2023.163811

Cited by 10 publications

(11 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, we found that NTL was extremely important to both MICX presence (ranked first) and MICX concentration (ranked second) (Figure ), this aligned with previous findings that MICX is better explained by NTL than PTL at the national scale . Our findings also highlighted the importance of pH to both MICX presence and concentration, which aligned with observations from large-scale studies as well . However, we cannot establish the causal links between pH and MICX based on this.…”

Section: Discussionsupporting

confidence: 88%

“…For example, previous studies found that trophic status often successfully predicts MICX concentrations across large numbers of lakes. 84,85 Not surprisingly, the most important drivers we identified for MICX presence (NTL and CHLA) and concentrations (TURB and NTL) were all related to the trophic status. Moreover, we found that NTL was extremely important to both MICX presence (ranked first) and MICX concentration (ranked second) (Figure 3), this aligned with previous findings that MICX is better explained by NTL than PTL at the national scale.…”

Section: Discussionmentioning

confidence: 84%

“…Our results showed that the MICX tends to be lower at the earlier stage and gradually increases toward the end of the growing season. This is also likely to be associated with the change of dominating phytoplankton as pointed out by some studies, 84,87 and the seasonal climatic factors such as temperature can play a role as well. 87 The percentage of wetlands turned out to be one of the most important factors for MICX concentration (ranked fifth), with higher percentages of wetlands associated with higher MICX concentrations.…”

Section: Discussionmentioning

confidence: 89%

“…86 Our findings also highlighted the importance of pH to both MICX presence and concentration, which aligned with observations from large-scale studies as well. 84 However, we cannot establish the causal links between pH and MICX based on this. The underlying process can be that phytoplankton photosynthesis affects both pH and MICX-production, 84 meaning the relationship between pH and MICX was observed as a result of confounding; or it could also be that pH directly affects the growth of MICX-producing phytoplankton species and their metabolism process associated with MICX.…”

Section: Discussionmentioning

confidence: 93%

See 3 more Smart Citations

A Two-Stage Interpretable Machine Learning Framework for Accurate Prediction of Trace Pollutants: With an Application to Microcystin

Wu,

Liang,

Qiu

2023

ACS EST Water

View full text Add to dashboard Cite

Trace pollutants are widely observed in aquatic ecosystems and can significantly impact human health and the environment. Accurate prediction of trace pollutants and understanding their response to environmental drivers are key to environmental management, yet these tasks remain challenging. An important reason for this challenge is that monitoring data for trace pollutants are often left-censored, leading to biased estimation and inaccurate response-driver relationships. Here we propose a novel two-stage interpretable machine learning framework applicable to left-censored trace pollutant data. The two stages include (1) a classifier to predict the presence of the pollutant and (2) a regressor to predict the pollutant concentration if present. The two stages were followed by a model interpretation to understand the contribution of drivers to the presence and concentration of the pollutant accordingly. We take the prediction of microcystin (MICX) in lakes across the United States as a case study. Applying this framework to MICX consistently improved prediction accuracy, including prediction of its occurrence and concentration regardless of the algorithms and performance metrics used. The best-performing algorithm using the two-stage framework, compared with the baseline model, improves classification performance by 48% to 290% and the regression performance by 11% to 33%, depending on the metric used to evaluate the performance. The interpretable machine learning model also successfully revealed the impacts of the most important drivers on the presence of MICX and its concentration. Our results showed the advantages of this framework, including its interpretability to understand the driver-response relationship, ability to handle nonlinearity, better prediction performance, differentiation between the underlying processes, and potential to be generalized to other pollutants. As such, we anticipate that the framework we propose will be a starting point for using state-of-the-art interpretable machine learning models for predicting trace pollutants.

show abstract

Section: Discussionsupporting

confidence: 88%

Section: Discussionmentioning

confidence: 84%

Section: Discussionmentioning

confidence: 89%

Section: Discussionmentioning

confidence: 93%

See 2 more Smart Citations

A Two-Stage Interpretable Machine Learning Framework for Accurate Prediction of Trace Pollutants: With an Application to Microcystin

Wu,

Liang,

Qiu

2023

ACS EST Water

View full text Add to dashboard Cite

show abstract

“…Rigosi et al (2014) explored the interactions between nutrients and climate change among lakes with different trophic states and found that the pre-existing trophic state influenced lake responses. In this study, present-day total phosphorus concentrations suggest enriched conditions (i.e., meso-hypereutrophic; Table S1.1), a quintessential feature of lakes located within the Canadian prairies (MacKeigan et al, 2023). Rigosi et al (2014) found that climate warming had a more significant influence on enriched waterbodies, and our paleolimnological investigation further supports this finding.…”

Section: Discussionsupporting

confidence: 75%

Climate change amplifies the risk of potentially toxigenic cyanobacteria

Erratt

Creed

Lobb

et al. 2023

Global Change Biology

View full text Add to dashboard Cite

Cyanobacterial blooms pose a significant threat to water security, with anthropogenic forcing being implicated as a key driver behind the recent upsurge and global expansion of cyanobacteria in modern times. The potential effects of land‐use alterations and climate change can lead to complicated, less‐predictable scenarios in cyanobacterial management, especially when forecasting cyanobacterial toxin risks. There is a growing need for further investigations into the specific stressors that stimulate cyanobacterial toxins, as well as resolving the uncertainty surrounding the historical or contemporary nature of cyanobacterial‐associated risks. To address this gap, we employed a paleolimnological approach to reconstruct cyanobacterial abundance and microcystin‐producing potential in temperate lakes situated along a human impact gradient. We identified breakpoints (i.e., points of abrupt change) in these time series and examined the impact of landscape and climatic properties on their occurrence. Our findings indicate that lakes subject to greater human influence exhibited an earlier onset of cyanobacterial biomass by 40 years compared to less‐impacted lakes, with land‐use change emerging as the dominant predictor. Moreover, microcystin‐producing potential increased in both high‐ and low‐impact lakes around the 1980s, with climate warming being the primary driver. Our findings chronicle the importance of climate change in increasing the risk of toxigenic cyanobacteria in freshwater resources.

show abstract