Search Results (241)

The chlorophyll-a (Chl-a) concentration in lakes is a crucial parameter for monitoring water quality and assessing phytoplankton abundance. However, accurately retrieving Chl-a concentrations remains a significant challenge in remote sensing. To address the limitations of existing methods in terms of modeling efficiency and adaptability, this study focuses on Lake Nanyi in Anhui Province. By integrating Sentinel-2 satellite imagery with in situ water quality measurements and employing the AutoML framework AutoGluon, a Chl-a inversion model based on narrow-band spectral features is developed. Feature selection and model ensembling identify bands B6 (740 nm) and B7 (783 nm) as the optimal combination, which are then applied to multi-temporal imagery from October 2022 to generate spatial mean distributions of Chl-a in Lake Nanyi. The results demonstrate that the AutoGluon framework significantly outperforms traditional methods in both model accuracy (R²: 0.94, RMSE: 1.67 $\mathsf{\mu }$g/L) and development efficiency. The retrieval results reveal spatial heterogeneity in Chl-a concentration, with higher concentrations observed in the southern part of the western lake and the western side of the eastern lake, while the central lake area exhibits relatively lower concentrations, ranging from 3.66 to 21.39 $\mathsf{\mu }$g/L. This study presents an efficient and reliable approach for lake ecological monitoring and underscores the potential of AutoML in water color remote sensing applications. Full article

Subtropical plateau lakes, which are distinguished by their elevated altitudes and subtropical climates, display distinct ecological dynamics. Nevertheless, the spatial and seasonal variations in the plankton community structure, as well as their interactions with environmental factors, remain inadequately understood. This study investigated the alterations in the phytoplankton and zooplankton community structure across different geographical regions (southern, central, and northern) and seasonal periods (rainy and dry) in Erhai lake, located in a subtropical plateau in China. The results indicated that the average values of total nitrogen (TN), total phosphorus (TP), chlorophyll-a (Chla), pH, and conductivity are significantly higher during the rainy season in comparison to the dry season. Furthermore, during the rainy season, there were significant differences in the concentrations of TN, TP, and Chla among the three designated water areas. Notable differences were also observed in the distribution of Microcystis, the density of Cladocera and copepods, and the biomass of copepods across the three regions during this season. Conversely, in the dry season, only the biomass of Cladocera exhibited significant variation among the three water areas. The redundancy analysis (RDA) and variance partitioning analysis demonstrated that the distribution of plankton groups (Cyanophyta, Cryptophyta, and Cladocera) is significantly associated with TN, Secchi depth (SD), and Chla during the rainy season, whereas it is significantly correlated with TP and SD during the dry season. These findings underscore the critical influence of environmental factors, shaped by rainfall patterns, in driving these ecological changes. In the context of the early stages of eutrophication in Lake Erhai, it is essential to ascertain the spatial distribution of water quality parameters, as well as phytoplankton and zooplankton density and biomass, during both the rainy and dry seasons. Full article

Ocean ecosystem services provisioning is driven by phytoplankton, which form the base of the ocean food chain in aquatic ecosystems and play a critical role as the Earth‘s carbon sink. Phytoplankton is highly sensitive to temperature, making it vulnerable to the effects of temperature variations. The aim of this research was to develop and test a workflow analysis to monitor the impact of sea surface temperature (SST) on phytoplankton biomass and primary production by combining field and remote sensing data of Chl-a and net primary production (NPP) (as proxies of phytoplankton biomass). The tropical zone was used as a case study to test the procedure. Firstly, machine learning algorithms were applied to the field data of SST, Chl-a and NPP, showing that the Random Forest was the most effective in capturing the dataset’s patterns. Secondly, the Random Forest algorithm was applied to MODIS SST images to build Chl-a and NPP time series. The time series analysis showed a significant increase in SST which corresponded to a significant negative trend in Chl-a concentrations and NPP variation. The recurrence plot of the time series revealed significant disruptions in Chl-a and NPP evolutions, potentially linked to El Niño–Southern Oscillation (ENSO) events. Therefore, the analysis can help to highlight the effects of temperature variation on Chl-a and NPP, such as the long-term evolution of the trend and short perturbation events. The methodology, starting from local studies, can support broader spatial–temporal-scale studies and provide insights into future scenarios. Full article

This work introduces the use of Bayesian Neural Networks (BNNs) for inferring chlorophyll-a concentration ([CHL-a]) from remotely sensed data. BNNs are probabilistic models that associate a probability distribution to the neural network parameters and rely on Bayes’ rule for training. The performance of the proposed probabilistic model is compared to that of standard ocean color algorithms, namely ocean color 4 (OC4) and ocean color index (OCI). An extensive in situ bio-optical dataset was used to train and validate the ocean color models. In contrast to established methods, the BNN allows for enhanced modeling flexibility, where different variables that affect phytoplankton phenology or describe the state of the ocean can be used as additional input for enhanced performance. Our results suggest that BNNs perform at least as well as established methods, and they could achieve 20–40% lower mean squared errors when additional input variables are included, such as the sea surface temperature and its climatological mean alongside the coordinates of the prediction. The BNNs offer means for uncertainty quantification by estimating the probability distribution of [CHL-a], building confidence in the [CHL-a] predictions through the variance of the predictions. Furthermore, the output probability distribution can be used for risk assessment and decision making through analyzing the quantiles and shape of the predicted distribution. Full article

Harmful algal blooms (HABs), driven by environmental pollution, pose significant threats to water quality, public health, and aquatic ecosystems. This study enhances the prediction of HABs in Lake Erie, part of the Great Lakes system, by utilizing ensemble machine learning (ML) models coupled with explainable artificial intelligence (XAI) for interpretability. Using water quality data from 2013 to 2020, various physical, chemical, and biological parameters were analyzed to predict chlorophyll-a (Chl-a) concentrations, which are a commonly used indicator of phytoplankton biomass and a proxy for algal blooms. This study employed multiple ensemble ML models, including random forest (RF), deep forest (DF), gradient boosting (GB), and XGBoost, and compared their performance against individual models, such as support vector machine (SVM), decision tree (DT), and multi-layer perceptron (MLP). The findings revealed that the ensemble models, particularly XGBoost and deep forest (DF), achieved superior predictive accuracy, with R² values of 0.8517 and 0.8544, respectively. The application of SHapley Additive exPlanations (SHAPs) provided insights into the relative importance of the input features, identifying the particulate organic nitrogen (PON), particulate organic carbon (POC), and total phosphorus (TP) as the critical factors influencing the Chl-a concentrations. This research demonstrates the effectiveness of ensemble ML models for achieving high predictive accuracy, while the integration of XAI enhances model interpretability. The results support the development of proactive water quality management strategies and highlight the potential of advanced ML techniques for environmental monitoring. Full article

Microcystins (MCs), hepatotoxins produced by cyanobacteria, represent a potential threat to aquatic ecosystems and human health. Measuring various environmental and cyanobacterial parameters in water samples can be useful for monitoring water quality and assessing risk but remains a short-term approach. Beyond local risk assessments, estimating global and medium-term levels of freshwater contamination by MC-producing cyanobacteria is challenging in large lakes due to the spatio-temporal variability of their proliferation and the need to multiply sampling dates and locations. In such conditions, a sentinel organism can be valuable for monitoring MCs in situ and providing a time-integrated picture of contamination levels at various stations. We previously assessed the ability of the freshwater bivalves Anodonta anatina and Dreissena polymorpha to act as biointegrators of MCs, even under low exposure levels to cyanobacteria. In this study, through a two-season investigation in several French lakes experiencing moderate cyanobacterial blooms, we evaluated the relevance of various parameters (cyanobacterial density and biovolume, chlorophyll-a, and phycocyanin) as well as the use of bivalves as indicators of medium-term freshwater contamination by MC-producing cyanobacteria. MC concentrations in cyanobacterial biomass (intracellular MCs) and in bivalves (free MCs, being unbound, and total free and protein-bound accumulated MCs) were measured alongside the characterization of phytoplankton communities. Both mussels integrated and highlighted the presence of intracellular MCs in the environment over the period between two successive water samplings, even at low contamination levels, demonstrating their suitability for in situ biomonitoring of MC-producing cyanobacteria. The results are discussed in terms of the strengths and limitations of different parameters for assessing MC contamination levels in waters depending on the objective (managing, preventing, or global evaluation) and the monitoring strategies used. Full article

This paper analyzes phytoplankton communities in the Eastern Tropical Pacific Ocean off Mexico (ETPOM) and the Southern Gulf of California (SGC) during the strong El Niño event of 2023/24. A multidisciplinary research cruise was conducted in the winter of 2024, during which high-resolution hydrographic data and water samples for phytoplankton cell determinations were collected at 33 sites. Additionally, satellite data were obtained to evaluate sea surface temperature and chlorophyll-a levels. A total of 269 phytoplankton species were identified, comprising one hundred and fifty diatoms, one hundred and twelve dinoflagellates, five silicoflagellates, one ciliate and one cyanobacteria. The dominant species included the diatom Pseudo-nitzschia pseudodelicatissima, the dinoflagellate Gyrodinium fusiforme, the silicoflagellate Octactis octonaria, and the ciliate Mesodinium rubrum. The cyanobacterium Trichodesmium hildebrandtii was also identified. In terms of total abundances, diatoms were the most prevalent, with 224,900 cells L⁻¹, followed by dinoflagellates at 104,520 cells L⁻¹, ciliates at 20,980 cells L⁻¹, cyanobacteria at 1760 cells L⁻¹, and silicoflagellates at 1500 cells L⁻¹. Notably, interesting differences emerged in species richness and abundance when comparing both regions. These results enhance our understanding of phytoplankton dynamics associated with strong El Niño events. The ETPOM remains a region that requires further monitoring through in situ observations. Full article

Lake Taihu has highly turbid inland waters with complex optical properties. Due to the bottom effect of submerged aquatic plants in optically shallow waters, currently available phytoplankton chlorophyll-a retrieval algorithms tend to overestimate chlorophyll-a concentrations in the eastern part of Lake Taihu. This overestimation can distort the eutrophication evaluation of the entire lake. This paper identifies submerged and emergent plants, determines the retrieval models for the upwelling (K_u) and downwelling (K_d) irradiance attenuation coefficients, and proposes a phytoplankton chlorophyll-a retrieval model using a water depth optimization-based method to remove the bottom effect. The results show the following: (1) The normalized difference vegetation index (NDVI) method can distinguish the bottom mud (NDVI < −0.46) and submerged aquatic plants (−0.46 ≤ NDVI < 0.52) from the emergent plants (NDVI ≥ 0.52) with 90% accuracy. (2) The downwelling and upwelling irradiance attenuation coefficients are highly correlated with the suspended sediments, and retrieval models for these coefficients in three visible bands with high accuracy are presented. (3) Compared to traditional algorithms without bottom effect removal, the proposed chlorophyll-a concentration estimation algorithm based on the water depth-optimized bottom effect removal method efficiently reduces the bottom effect of the submerged aquatic plants. The root mean square error (RMSE) for the obtained chlorophyll-a concentrations decreases from 45.61 ${\mathsf{\mu }\mathrm{g}·\mathrm{L}}^{-1}$ to 8.69 ${\mathsf{\mu }\mathrm{g}·\mathrm{L}}^{-1}$, and the mean absolute percentage error (MAPE) is reduced from 245.12% to 19.58%. In the validation step, the obtained RMSE of 10.89 ${\mathsf{\mu }\mathrm{g}·\mathrm{L}}^{-1}$ and MAPE of 17.52% are consistent with the proposed algorithm. This research provides a good reference for the determination of chlorophyll-a concentrations in phytoplankton in complex inland water bodies. The findings are potentially useful for the operational monitoring of harmful algal blooms in the future. Full article

Phytoplankton comprise the base of the food web in estuaries and their biomass and rates of growth (productivity) exert a bottom-up control in pelagic ecosystems. Reliable means to quantify biomass and productivity are crucial for managing estuarine ecosystems. In many estuaries, direct productivity measurements are rare and instead are estimated with biomass-based models. A seminal example of this is a light utilization model (LUM) used to predict productivity in the San Francisco Estuary and Delta (SFED) from long timeseries data using an efficiency factor, ψ. Applications of the LUM in the SFED, Chesapeake Bay, and the Dutch Scheldt Estuary highlight significant interannual and regional variability, indicating the model must be recalibrated often. The objectives of this study are to revisit the LUM approach in the SFED and assess a chlorophyll-a to carbon model (CCM) that produces a tuning parameter, Ω. To assess the estimates of primary productivity resulting from the models, productivity was directly measured with a ¹³C-tracer at nine locations during 22 surveys using field-derived phytoplankton incubations between March and November of 2023. For this study, ψ was determined to be 0.42 ± 0.02 (r² = 0.89, p < 0.001, CI₉₅ = 319). Modeling productivity using an alternative CCM approach (Ω = 3.47 × 10⁴ ± 1.7 × 10³, r² = 0.84, p < 0.001, CI₉₅ = 375) compared well to the LUM approach, expanding the toolbox for estuarine researchers to cross-examine productivity models. One practical application of this study is that it confirms an observed decline in ψ, suggesting a decline in light utilization by phytoplankton in the SFED. This highlights the importance of occasionally recalibrating productivity models in estuaries and leveraging multiple modeling approaches to validate estimations before application in ecological management decision making. Full article

Submerged macrophytes can profoundly influence interactions between aquatic predators and their prey due to changes in foraging efficiencies, pursuit time and swimming behaviors of predator–prey participants. Water hyacinth, Eichhornia crassipes (Mart.) Solms-Laub. (Pontederiaceae), is the most widely distributed of the aquatic invasive weeds in South Africa. This invasive weed contributes to changes in physicochemical (turbidity, temperature and water column stratification) and biological (total chlorophyll-a (Chl-a) concentrations and species composition and distribution of vertebrates and invertebrates) variables within freshwater systems of the region. The current study assessed the influence of varying levels of water hyacinth cover (0, 25, 50 and 100% treatments) on the total Chl-a concentration, size structure of the phytoplankton community and the strength of the interaction between a predatory notonectid, Enithares sobria, and zooplankton using a short-term 10-day long mesocosm study. There were no significant differences in selected physicochemical (temperature, dissolved oxygen, total nitrogen and total phosphate) variables in these different treatments over the duration of this study (ANOVA; p > 0.05 in all cases). Results of this study indicate that treatment had a significant effect on total Chl-a concentrations and total zooplankton abundances. The increased surface cover of water hyacinth contributed to a significant reduction in total Chl-a concentrations and a significant increase in total zooplankton abundances (ANCOVA; p < 0.05 in both cases). The increased habitat complexity conferred by the water hyacinth root system provided refugia for zooplankton. The decline in total Chl-a concentration and the size structure of the phytoplankton community under elevated levels of water hyacinth cover can therefore probably be related to both the unfavorable light environment conferred by the plant cover and the increased grazing activity of zooplankton. The presence of the water hyacinth thus suppressed a predator–prey cascade at the base of the food web. Water hyacinth may, therefore, have important implications for the plankton food web dynamics of freshwater systems by reducing food availability (Chl-a), changing energy flow and alternating the strength of interactions between predators and their prey. Full article

Harmful algal blooms (HABs) have emerged as a significant environmental challenge, impacting aquatic ecosystems, drinking water supply systems, and human health due to the combined effects of human activities and climate change. This study investigates the performance of deep learning models, particularly the Transformer model, as there are limited studies exploring its effectiveness in HAB prediction. The chlorophyll-a (Chl-a) concentration, a commonly used indicator of phytoplankton biomass and a proxy for HAB occurrences, is used as the target variable. We consider multiple influencing parameters—including physical, chemical, and biological water quality monitoring data from multiple stations located west of Lake Erie—and employ SHapley Additive exPlanations (SHAP) values as an explainable artificial intelligence (XAI) tool to identify key input features affecting HABs. Our findings highlight the superiority of deep learning models, especially the Transformer, in capturing the complex dynamics of water quality parameters and providing actionable insights for ecological management. The SHAP analysis identifies Particulate Organic Carbon, Particulate Organic Nitrogen, and total phosphorus as critical factors influencing HAB predictions. This study contributes to the development of advanced predictive models for HABs, aiding in early detection and proactive management strategies. Full article

Benthic–pelagic coupling is a key approach to studying the structure and energy dynamics of shallow marine food webs. The movement and foraging patterns of consumers are major drivers of nutrient and energy distribution in ecosystems and are critical for maintaining ecosystem stability. To better understand the energy coupling of consumers between coastal marine habitats, this study employed a Bayesian mixture model using SC and SI data. By classifying functional groups based on taxonomy, morphological traits, and feeding ecology similarities, we constructed a trophic network and analyzed the changes in fish feeding patterns and the dynamics of benthic–pelagic coupling across environmental gradients. The results show that the primary carbon sources in the Beibu Gulf are phytoplankton, particulate organic matter (POM), and sediment organic matter (SOM), with phytoplankton contributing the most. Pelagic food subsidies dominate the food web. Small sized, abundant planktivorous and benthivorous fish act both as predators and important prey, transferring carbon and energy derived from both benthic and pelagic zones to higher trophic-levels. Larger, higher-trophic-level piscivorous fish serve as key energy couplers, preying on organisms from various habitats. Depth and chlorophyll–a (Chl–a) are the two key variables influencing the trophic structure of fish, with opposite gradient patterns observed for each. Along the depth gradient, fish exhibit clear adaptive foraging strategies. As water depth increases, fish tend to forage more within their specific habitat (either benthic or pelagic), with prey types continually changing, leading to a gradual reduction in the strength of benthic–pelagic trophic coupling. This study reveals the spatial resource utilization patterns and adaptive foraging strategies of fish in the Beibu Gulf, providing deeper insights into the structure and spatial variation of food webs. It also enhances our understanding of ecosystem responses to human pressures and global changes, offering valuable perspectives for predicting these responses. Full article

The urban water environment, an integral component of the terrestrial hydrosphere, is closely linked to human activities and serves as a fundamental resource for industrial and agricultural development. Sedimentary organic matter in water bodies contains rich biological, physical, and chemical information, playing a central role in nutrient cycling and serving as a primary reservoir for nutrient accumulation. This study assesses the water quality, chemical indicators, and sediment productivity of four typical urban water bodies (Canal, Pond, Lake, and River) in Shaoxing City, eastern China. The results show that artificial water bodies, particularly canals, have higher dissolved oxygen (DO) compared to natural water bodies. Stationary water bodies, such as lakes and ponds, generally have higher total dissolved solids (TDS) and electrical conductivity (EC) than flowing water bodies like rivers and canals. All four urban water body types slightly exceed China’s Class-V water quality standard for total nitrogen (TN), with canals, lakes, ponds, and rivers averaging 1.29, 1.22, 1.23, and 1.23 times the standard, respectively. Ponds exhibit the highest total dissolved nitrogen (TDN) content, while ammonium (NH₄⁺–N) and nitrate (NO₃⁻–N) levels are relatively consistent across the bodies, except for lower NO₃⁻–N in lakes. Higher organic matter in canals and lakes, indicated by chlorophyll-a (Chl-a) and permanganate index (COD_Mn), suggests greater eutrophication compared to ponds and rivers. Sediment total organic nitrogen (TON) content is relatively uniform across all water bodies, with slightly higher values in lakes and rivers. Total organic carbon (TOC) content is highest in lake sediments, 1.51 times that of canals. Carbon/nitrogen (C/N) ratios vary, with ponds and lakes showing the highest averages. Source quantification using isotopic analysis (δ¹³C and δ¹⁵N values) indicates that phytoplankton is the primary sedimentary organic matter source in rivers and canals, while terrestrial sources are significant in lakes and ponds. Sewage notably contributes to rivers and canals. These findings highlight the need for targeted pollution control strategies, focusing on phytoplankton and sewage as key sedimentary organic matter sources to mitigate eutrophication and enhance water quality in urban environments. Full article

One year of monthly sampling in some lagoons of the Po Delta and a pond in the Comacchio Valleys helped fill a gap in the knowledge of the primary producers of these degraded environments, focusing on the competition between macrophytes and phytoplankton. Key water column and surface sediment parameters showed a strong association with the different primary producers, explaining the main factors influencing the dominance of one group over the other. Phytoplankton, recorded as Chlorophyll-a and Phaeophytin-a, and Chlorophyceae among the macrophytes, dominated in conditions of high water turbidity and elevated nutrient concentrations. In contrast, macrophytes, particularly Rhodophyceae, their abundance, total biomass, and number of taxa. prevailed in clear, oxygenated waters. Under optimal conditions, sensitive macroalgae and aquatic angiosperms were also present. Additionally, the current list of macroalgal taxa has been updated, highlighting the dominance of some nonindigenous species (NIS) that had not been recorded before the 2000s. Specifically, Gracilaria vermiculophylla and Ulva australis, native to the North West Pacific (Japan, Korea, China, and Vietnam) and to South Australia, as well as the Indo-West Pacific (India, South Africa, Japan, and Korea), respectively, are now the most frequent and abundant taxa in these lagoons. Full article

Rivers play a crucial role in nutrient cycling, yet are increasingly affected by eutrophication due to anthropogenic activities. This study focuses on the Barato River in Hokkaido, Japan, employing an integrated approach of field measurements and Sentinel-2 satellite remote sensing to monitor eutrophication as the river experiencing huge sewage effluents. Key parameters such as chlorophyll-a (Chla), dissolved inorganic nitrogen (DIN), dissolved inorganic phosphorus (DIP), and Secchi Disk Depth (SDD) were analyzed. The developed empirical models showed a strong predictive capability for water quality, particularly for Chla (R² = 0.87), DIP (R² = 0.61), and SDD (R² = 0.82). Seasonal analysis indicated peak Chla concentrations in October, reaching up to 92.4 μg/L, alongside significant decreases in DIN and DIP, suggesting high phytoplankton activity. Advanced machine learning models, specifically back propagation neural networks, improved the prediction accuracy with R² values up to 0.90 for Chla and 0.83 for DIN. Temporal analyses from 2018 to 2022 consistently revealed the Barato River’s eutrophic state, with severe eutrophication occurring for 33% of the year and moderate for over 50%, emphasizing the ongoing nutrient imbalance. The strong correlation between DIP and Chla highlights phosphorus as the main driver of eutrophication. These findings demonstrate the efficacy of integrating remote sensing and machine learning for dynamic monitoring of river eutrophication, providing critical insights for nutrient management and water quality improvement. Full article