Modeling Anthropogenic and Environmental Influences on Freshwater Harmful Algal Bloom Development Detected by MERIS Over the Central United States

Projected response of algal blooms in global lakes to future climatic and land use changes: Machine learning approaches

The eutrophication of lakes and the subsequent algal blooms have become significant environmental issues of global concern in recent years. With ongoing global warming and intensifying human activities, water quality trends in lakes worldwide varied significantly, and the trend of algal blooms in the next few decades is unclear. However, there is a lack of comprehensive quantitative research on the future projection of lake algal blooms globally due to the scarcity of long-term algal blooms observational data and the complex nonlinear relationships between algal blooms and their driving factors. We aimed to develop a global projection model to evaluate the future trend in algal bloom occurrences in large lakes under various socio-economic development scenarios. We focused our research on 161 natural lakes worldwide, each exceeding 500 km2. The results indicated that the Random Forest model performed best (Overall Accuracy: 0.9697, Kappa: 0.8721) among various machine learning models which were applied in this study. The predicted results showed that, by the end of this century, the number of lakes experiencing algal blooms and the intensity of these blooms will worsen under higher forcing scenarios (SSP370 and SSP585) (p < 0.05). In different regions, lakes with increasing algal blooms are mainly distributed in Africa, Asia, and North America, while lakes with decreasing occurrence are primarily found in Europe. Additionally, underdeveloped regions, such as Africa, exhibit greater sensitivity to different SSP scenarios due to high variability in population and economic growth. This study revealed the spatiotemporal distribution of algal blooms in global lakes from 2020 to 2100 and suggested that the intensifying algal blooms due to global warming and human activities may offset the effort of controlling the water quality.

Unlocking the phosphorus circularity potential of corn belt watersheds with biorefinery phosphorus recovery incentives

As global phosphorus (P) stores rapidly decline, P fed algal blooms continue to threaten critical freshwater resources across the globe. In the Midwestern United States (US), particularly the Corn Belt, biorefineries could play a key role in addressing this issue. By recovering P from the byproducts of ethanol production these facilities could reduce the P content of distillers grain feed, thereby reducing P excreted in manures. This process could potentially divert P away from concentrated animal feeding operations (CAFOs) and toward renewable P (rP) fertilizer production utilizing the recovered P. To foster the inclusion of P recovery incentives in state nutrient reduction strategies, this study elucidates the cascading benefits of rP recovery from corn biorefineries in watersheds across six Upper Midwestern states. Incentivizing P recovery in watersheds that contain both biorefineries and CAFOs could foster the production of 107,500 metric tons (MT) rP fertilizer while diverting 26,800 MT P from CAFO wastes each year, nearly double the estimated P reduction potential for municipal wastewater in the analysis region. These estimates can inform nutrient reduction analysts and policymakers in determining P load reduction potential. To further guide incentive strategies, four priority watersheds are highlighted to illustrate P reduction and circularity typologies across the region.

Estimating the temporal and spatial distribution and threats of bisphenol A in temperate lakes using machine learning models

Bisphenol A (BPA) is easily enriched in many human-disturbed watersheds, particularly lakes with poor water mobility, which is posing a threat to aquatic biota. While previous studies have focused on the concentration of BPA in water and its toxicity to aquatic organisms, a small amount of measured data is not enough to reveal the temporal and spatial distribution and threats of BPA, and estimate the ecological risk in watersheds. Therefore, we collected 164 measured BPA data points from Taihu Lake to develop machine learning models using random forest (RF), support vector machine (SVM) and least square regression (LSR) and created month-by-month watershed prediction maps in temperate lakes to estimate the spatiotemporal distribution and threats of BPA. Due to RF's superior robustness to noisy data, the RF model exhibits the best performance among the three algorithms. The RF model showed acceptable predictive performance on the modeling dataset (coefficients of determination and root-mean-square error for the training set were 0.927 and 17.499, respectively, and 0.607, 39.645 for the validation set, respectively). The maps indicated that areas susceptible to anthropogenic activities were more severely polluted by BPA, and rainy climate may favor the migration of BPA to aquatic ecosystems. The model was also applied to predict 42 data points of BPA collected from Dianchi Lake, and the results showed that most predicted data were within a factor of 10 of the measured data, but the prediction accuracy of the model has declined. The ecological risks in the two lakes were evaluated and attention should be paid to the regions with higher risks. Our study provided a novel idea for comprehensive monitoring of an unconventional trace pollutant with endocrine disrupting effects in aquatic ecosystems and analyzing their spatiotemporal distribution, which will contribute to the scientific assessment of the ecological risk of BPA.

Forecasting freshwater cyanobacterial harmful algal blooms for Sentinel-3 satellite resolved U.S. lakes and reservoirs

This forecasting approach may be useful for water managers and associated public health managers to predict near-term future high-risk cyanobacterial harmful algal blooms (cyanoHAB) occurrence. Freshwater cyanoHABs may grow to excessive concentrations and cause human, animal, and environmental health concerns in lakes and reservoirs. Knowledge of the timing and location of cyanoHAB events is important for water quality management of recreational and drinking water systems. No quantitative tool exists to forecast cyanoHABs across broad geographic scales and at regular intervals. Publicly available satellite monitoring has proven effective in detecting cyanobacteria biomass near-real time within the United States. Weekly cyanobacteria abundance was quantified from the Ocean and Land Colour Instrument (OLCI) onboard the Sentinel-3 satellite as the response variable. An Integrated Nested Laplace Approximation (INLA) hierarchical Bayesian spatiotemporal model was applied to forecast World Health Organization (WHO) recreation Alert Level 1 exceedance >12 μg L-1 chlorophyll-a with cyanobacteria dominance for 2192 satellite resolved lakes in the United States across nine climate zones. The INLA model was compared against support vector classifier and random forest machine learning models; and Dense Neural Network, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Gneural Network (GNU) neural network models. Predictors were limited to data sources relevant to cyanobacterial growth, readily available on a weekly basis, and at the national scale for operational forecasting. Relevant predictors included water surface temperature, precipitation, and lake geomorphology. Overall, the INLA model outperformed the machine learning and neural network models with prediction accuracy of 90% with 88% sensitivity, 91% specificity, and 49% precision as demonstrated by training the model with data from 2017 through 2020 and independently assessing predictions with data from the 2021 calendar year. The probability of true positive responses was greater than false positive responses and the probability of true negative responses was less than false negative responses. This indicated the model correctly assigned lower probabilities of events when they didn't exceed the WHO Alert Level 1 threshold and assigned higher probabilities when events did exceed the threshold. The INLA model was robust to missing data and unbalanced sampling between waterbodies.

Recent changes in cyanobacteria algal bloom magnitude in large lakes across the contiguous United States

Cyanobacterial blooms in inland lakes produce large quantities of biomass that impact drinking water systems, recreation, and tourism and may produce toxins that can adversely affect public health. This study analyzed nine years of satellite-derived bloom records and compared how the bloom magnitude has changed from 2008-2011 to 2016-2020 in 1881 of the largest lakes across the contiguous United States (CONUS). We determined bloom magnitude each year as the spatio-temporal mean cyanobacteria biomass from May to October and in concentrations of chlorophyll-a. We found that bloom magnitude decreased in 465 (25 %) lakes in the 2016-2020 period. Conversely, there was an increase in bloom magnitude in only 81 lakes (4 %). Bloom magnitude either didn't change, or the observed change was in the uncertainty range in the majority of the lakes (n = 1335, 71 %). Above-normal wetness and normal or below-normal maximum temperature over the warm season may have caused the decrease in bloom magnitude in the eastern part of the CONUS in recent years. On the other hand, a hotter and dryer warm season in the western CONUS may have created an environment for increased algal biomass. While more lakes saw a decrease in bloom magnitude, the pattern was not monotonic over the CONUS. The variations in temporal changes in bloom magnitude within and across climatic regions depend on the interactions between land use land cover (LULC) and physical factors such as temperature and precipitation. Despite expectations suggested by recent global studies, bloom magnitude has not increased in larger US lakes over this time period.

Modeling National Embedded Phosphorus Flows of Corn Ethanol Distillers' Grains to Elucidate Nutrient Reduction Opportunities

Freshwater quality and ecosystem impairment associated with excess phosphorus (P) loadings have led to federally mandated P reduction for certain organic waste streams. Phosphorus reduction from livestock and poultry feeds such as corn ethanol distillers' grains (DGs) presents a centralized strategy for reducing P loss from animal manurein agriculturally intensive states, but little is known about the actual distribution and geospatial P contributions of DGs as animal feed. Here, a county-level flow network for corn ethanol DGs was simulated in the United States to elucidate opportunities for P reduction and the potential for nutrient trading between centralized sources. Overall, the estimated P in DGs that was transferred to US animal feeding operations was nearly twice that present in all human waste prior to treatment. Simulation results suggest that Midwestern states account for an estimated 63% of domestic DG usage, with 72% utilized within the state of production. County-level data were also used to highlight the potential of using nutrient trading markets to incentivize P recovery from DGs at biorefineries within an agriculturally intensive watershed region in Iowa. In summary, corn ethanol biorefineries represent a key leverage point for sustainable P management at the national and local scales.

First monitoring of cyanobacteria and cyanotoxins in freshwater from fish farms in Rondônia state, Brazil

The main aimed of this study was to evaluate the physicochemical parameters, abundance and density of cyanobacteria, determine their blooms and the ecotoxicological risk of their cyanotoxins in fish ponds water. This study was conducted out in 20 fish farms in Rondônia state (Brazilian Amazon), samplings were carried out in the rainy and dry seasons. The experiment was developed in a completely randomized factorial design 20 × 3 x 3 (20 fish farms, 3 ponds and 3 replications). Regarding the composition of qualitative samples, horizontal and vertical hauls were carried out on the water surface, quantitative samples was obtained using a plankton net (50 μm mesh opening). Meanwhile, with the use of a multiparametric probe, physicochemical analyzes in fish ponds water were carried out. Furthermore, the cyanobacteria found were classified taxonomically and its blooms were recorded. Finally, blood was collected from 60 Colossoma macropomum. Concerning the higher averages in the rainy season 6.13 mg L^⁻1 of dissolved oxygen, 40.02 cm of transparency, 0.35 NO₃^1⁻ of nitrate, 0.15 NO₂^1⁻ of nitrite, 44.55 mg L^⁻1 CaCO₃ of alkalinity and 50.10 mg L^⁻1 CaCO₃ of hardness, while higher averages of pH, phosphate and phosphorus were found in the dry season. A total of 15 families and 29 species of cyanobacteria were identified in the different seasons. The families that showed the highest densities (rainy and dry seasons) were Microcystaceae (356 and 760 cells mL^⁻1), Leptolyngbyaceae (126 and 287 cells mL^⁻1) and Microcoleaceae (111 and 405 cells mL^⁻1). The species that showed the highest densities were Microcystis aeruginosa (356 and 697 cells mL^⁻1), Planktolyngbya limnetica (98 and 257 cells mL^⁻1) and Planktothrix sp. (111 and 239 cells mL^⁻1). There were significant Pearson's correlations (r > 0.85; p < 0.05) between family abundances and cyanotoxin volume between physicochemical water variables and seasonality. A total of 20 cyanobacteria blooms were recorded, all of which in the dry season showed an ecotoxicological risk. Concerning the assessment mutagenicity in fish blood cells, a total of 78 abnormalities per slide were observed. In the dry season, the expected volume of cyanotoxins in the ponds from fish farms F1 and F4 were above the quantification limit (>QL). Abundance and density of cyanobacteria and their blooms and cyanotoxins can be used as bioindicators of eutrophication and/or water quality and ecotoxicological risk in fish ponds.

Identifying lakes at risk of toxic cyanobacterial blooms using satellite imagery and field surveys across the United States

Harmful algal blooms caused by cyanobacteria are a threat to global water resources and human health. Satellite remote sensing has vastly expanded spatial and temporal data on lake cyanobacteria, yet there is still acute need for tools that identify which waterbodies are at-risk for toxic cyanobacterial blooms. Algal toxins cannot be directly detected through imagery but monitoring toxins associated with cyanobacterial blooms is critical for assessing risk to the environment, animals, and people. The objective of this study is to address this need by developing an approach relating satellite imagery on cyanobacteria with field surveys to model the risk of toxic blooms among lakes. The Medium Resolution Imaging Spectrometer (MERIS) and United States (US) National Lakes Assessments are leveraged to model the probability among lakes of exceeding lower and higher demonstration thresholds for microcystin toxin, cyanobacteria, and chlorophyll a. By leveraging the large spatial variation among lakes using two national-scale data sources, rather than focusing on temporal variability, this approach avoids many of the previous challenges in relating satellite imagery to cyanotoxins. For every satellite-derived lake-level Cyanobacteria Index (CI_cyano) increase of 0.01 CI_cyano/km2, the odds of exceeding six bloom thresholds increased by 23-54 %. When the models were applied to the 2192 satellite monitored lakes in the US, the number of lakes identified with ≥75 % probability of exceeding the thresholds included as many as 335 lakes for the lower thresholds and 70 lakes for the higher thresholds, respectively. For microcystin, the models identified 162 and 70 lakes with ≥75 % probability of exceeding the lower (0.2 μg/L) and higher (1.0 μg/L) thresholds, respectively. This approach represents a critical advancement in using satellite imagery and field data to identify lakes at risk for developing toxic cyanobacteria blooms. Such models can help translate satellite data to aid water quality monitoring and management.

Uncovering the influence of hydrological and climate variables in chlorophyll-A concentration in tropical reservoirs with machine learning

Climate variability and change, associated with increasing water demands, can have significant implications for water availability. In the Brazilian semi-arid, eutrophication in reservoirs raises the risk of water scarcity. The reservoirs have also a high seasonal and annual variability of water level and volume, which can have important effects on chlorophyll-a concentration (Chla). Assessing the influence of climate and hydrological variability on phytoplankton growth can be important to find strategies to achieve water security in tropical regions with similar problems. This study explores the potential of machine learning models to predict Chla in reservoirs and to understand their relationship with hydrological and climate variables. The model is based mainly on satellite data, which makes the methodology useful for data-scarce regions. Tree-based ensemble methods had the best performances among six machine learning methods and one parametric model. This performance can be considered satisfactory as classical empirical relationships between Chla and phosphorus may not hold for tropical reservoirs. Water volume and the mix-layer depth are inversely related to Chla, while mean surface temperature, water level, and surface solar radiation have direct relationships with Chla. These findings provide insights on how seasonal climate prediction and reservoir operation might influence water quality in regions supplied by superficial reservoirs.

Satellites quantify the spatial extent of cyanobacterial blooms across the United States at multiple scales

Previous studies indicate that cyanobacterial harmful algal bloom (cyanoHAB) frequency, extent, and magnitude have increased globally over the past few decades. However, little quantitative capability is available to assess these metrics of cyanoHABs across broad geographic scales and at regular intervals. Here, the spatial extent was quantified from a cyanobacteria algorithm applied to two European Space Agency satellite platforms-the MEdium Resolution Imaging Spectrometer (MERIS) onboard Envisat and the Ocean and Land Colour Instrument (OLCI) onboard Sentinel-3. CyanoHAB spatial extent was defined for each geographic area as the percentage of valid satellite pixels that exhibited cyanobacteria above the detection limit of the satellite sensor. This study quantified cyanoHAB spatial extent for over 2,000 large lakes and reservoirs across the contiguous United States (CONUS) during two time periods: 2008-2011 via MERIS and 2017-2020 via OLCI when cloud-, ice-, and snow-free imagery was available. Approximately 56% of resolvable lakes were glaciated, 13% were headwater, isolated, or terminal lakes, and the rest were primarily drainage lakes. Results were summarized at national-, regional-, state-, and lake-scales, where regions were defined as nine climate regions which represent climatically consistent states. As measured by satellite, changes in national cyanoHAB extent did have a strong increase of 6.9% from 2017 to 2020 (|Kendall's tau (τ)| = 0.56; gamma (γ) = 2.87 years), but had negligible change (|τ| = 0.03) from 2008 to 2011. Two of the nine regions had moderate (0.3 ≤ |τ| < 0.5) increases in spatial extent from 2017 to 2020, and eight of nine regions had negligible (|τ| < 0.2) change from 2008 to 2011. Twelve states had a strong or moderate increase from 2017 to 2020 (|τ| ≥ 0.3), while only one state had a moderate increase and two states had a moderate decrease from 2008 to 2011. A decrease, or no change, in cyanoHAB spatial extent did not indicate a lack of issues related to cyanoHABs. Sensitivity results of randomly omitted daily CONUS scenes confirm that even with reduced data availability during a short four-year temporal assessment, the direction and strength of the changes in spatial extent remained consistent. We present the first set of national maps of lake cyanoHAB spatial extent across CONUS and demonstrate an approach for quantifying past and future changes at multiple spatial scales. Results presented here provide water quality managers information regarding current cyanoHAB spatial extent and quantify rates of change.

Mapping Benthic Algae and Cyanobacteria in River Channels from Aerial Photographs and Satellite Images: A Proof-of-Concept Investigation on the Buffalo National River, AR, USA

Although rivers are of immense practical, aesthetic, and recreational value, these aquatic habitats are particularly sensitive to environmental changes. Increasingly, changes in streamflow and water quality are resulting in blooms of bottom-attached (benthic) algae, also known as periphyton, which have become widespread in many water bodies of US national parks. Because these blooms degrade visitor experiences and threaten human and ecosystem health, improved methods of characterizing benthic algae are needed. This study evaluated the potential utility of remote sensing techniques for mapping variations in algal density in shallow, clear-flowing rivers. As part of an initial proof-of-concept investigation, field measurements of water depth and percent cover of benthic algae were collected from two reaches of the Buffalo National River along with aerial photographs and multispectral satellite images. Applying a band ratio algorithm to these data yielded reliable depth estimates, although a shallow bias and moderate level of precision were observed. Spectral distinctions among algal percent cover values ranging from 0 to 100% were subtle and became only slightly more pronounced when the data were aggregated to four ordinal levels. A bagged trees machine learning model trained using the original spectral bands and image-derived depth estimates as predictor variables was used to produce classified maps of algal density. The spatial and temporal patterns depicted in these maps were reasonable but overall classification accuracies were modest, up to 64.6%, due to a lack of spectral detail. To further advance remote sensing of benthic algae and other periphyton, future studies could adopt hyperspectral approaches and more quantitative, continuous metrics such as biomass.