Real-Time Chlorophyll-a Forecasting using Machine Learning Framework with Dimension Reduction and Hyperspectral Data.

Since water is an essential resource in various fields, it requires constant monitoring. Chlorophyll-a concentration is a crucial indicator of water quality and can be used to monitor water quality. In this study, we developed methods to forecast chlorophyll-a concentrations in real-time using hyperspectral data on IoT platform and various machine learning algorithms. Compared to regular cameras that record information only in the three broad color bands of red, green, and blue, the hyperspectral images of drinking water sources record the data in dozens or even hundreds of distinct small wavelength bands, providing each pixel in an image with a full spectrum. Different machine learning algorithms have been developed using hyperspectral data and field observations of water quality and weather conditions. Previous studies have predicted chlorophyll concentrations using either partial least squares (PLS), which is a dimensionality reduction method, or machine learning. In contrast, our study employed the PLS technique as a preprocessing step to diminish the dimensionality of the hyperspectral data, followed by the application of the machine learning techniques with optimized hyperparameters to improve the precision of the predictions, thereby introducing a real-time mechanism for chlorophyll-a prediction. Consequently, a machine learning algorithm with R2 values of 0.9 or above and sufficiently small RMSE was developed for real-time chlorophyll-a forecasting. Real-time chlorophyll-a forecasting using LightGBM has the best performance, with a mean R2 of 0.963 and a mean RMSE of 2.679. This paper is expected to have applications in algal bloom early detection on monitoring systems.

Seasonal Effects of Constructed Wetlands on Water Quality Characteristics in Jinshan Lake: A Gate Dam Lake (Zhenjiang City, China).

Urban lakes commonly suffer from nutrient over-enrichment, resulting in water quality deterioration and eutrophication. Constructed wetlands are widely employed for ecological restoration in such lakes but their efficacy in water purification noticeably fluctuates with the seasons. This study takes the constructed wetland of Jinshan Lake as an example. By analyzing the water quality parameters at three depths during both summer and winter, this study explores the influence of the constructed wetland on the water quality of each layer during different seasons and elucidates the potential mechanisms underlying these seasonal effects. The results indicate that the constructed wetland significantly enhances total nitrogen (TN) concentration during summer and exhibits the capacity for nitrate-nitrogen removal in winter. However, its efficacy in removing total phosphorus (TP) is limited, and may even serve as a potential phosphorus (P) source for the lake during winter. Water quality test results of different samples indicated they belong to Class III or IV. Restrictive factors varied across seasons: nitrate-nitrogen and BOD5 jointly affected water quality in winter, whereas TP predominantly constrained water quality in summer. These results could provide a reference for water quality monitoring and management strategies of constructed wetlands in different seasons in Jiangsu Province.

Stabilized chlorophyll-based food colorants from spinach: Kinetics of a tailored enzymatic extraction.

An organic solvent-free method based on limited dosing options (biocatalyst and zinc chloride) for the quick and mild recovery of chlorophyll (Chl) from spinach has been proposed. This tailored, custom-made protocol has been designed to produce stable green natural colorants. The kinetics of pigment extraction turned out to be a very useful tool to identify the proper conditions, in terms of biocatalyst dose (0.10-50 U/g), extraction time (1-48h), and ZnCl2 amount (50-300ppm), both for enhancing the recovery yield and preserving the green color. Considering the extraction kinetics, the recovery yield, and the colorimetric data, the suitable conditions to produce stable green and food-grade colorants are 0.10 U/g of enzyme, 3h, and 150ppm of ZnCl2 at 25°C. The extraction yield of Chl (4863µg/U) was about 51% greater than control, with a higher extraction rate constant (5.43 × 10-4 g/(µg min)). Considering the impact of ZnCl2 amount on Chl, its protective action resulted to be more noticeable toward Chl a: at 150ppm, an increased amount of about 2.5 and 1.5 times was found for Chl a and Chl b, respectively, in comparison to the reference (0ppm ZnCl2). PRACTICAL APPLICATION: This research demonstrates how a suitable kinetic approach helps to provide a tailored protocol, customized for the vegetable matrix, to produce stable green natural colorants from spinach. Lowering enzyme dosage and ZnCl2 amount during the extraction of chlorophyll at low temperature is crucial for its potential use as a colorant in food industry, providing high economic values through saving time and environmental protection.

qPCR-based phytoplankton abundance and chlorophyll a: A multi-year study in twelve large freshwater rivers across the United States.

Phytoplanktonic overgrowth, which characterizes the eutrophication or trophic status of surface water bodies, threatens ecosystems and public health. Quantitative polymerase chain reaction (qPCR) is promising for assessing the abundance and community composition of phytoplankton. However, applications of qPCR to indicate eutrophication and trophic status, especially in lotic systems, have yet to be comprehensively evaluated. For the first time, this study correlates qPCR-based phytoplankton abundance with chlorophyll a (the most widely used indicator of eutrophication and trophic status) in multiple freshwater rivers. From early summer to late fall in 2017, 2018, and 2019, we evaluated phytoplankton, chlorophyll a, pheophytin a, and the Trophic Level Index (TLI) in twelve large freshwater rivers in three regions (western, midcontinent, and eastern) in the United States. Chlorophyll a concentration had positive allometric correlations with qPCR-based phytoplankton abundance (adjusted R2 = 0.5437, p-value <0.001), pheophytin a concentration (adjusted R2 = 0.3378, p-value <0.001), and TLI (adjusted R2 = 0.4789, p-value <0.001). Thus, a greater phytoplankton abundance suggests a higher trophic status. This work also presents the numerical values of qPCR-based phytoplankton abundance defining the boundaries among trophic statuses (e.g., oligotrophic, mesotrophic, and eutrophic) of freshwater rivers. The sampling sites in the midcontinent rivers were more eutrophic because they had significantly higher chlorophyll a concentrations, pheophytin a concentrations, and TLI values than in the western and eastern rivers. The higher phytoplankton abundance at the midcontinent sites confirmed their higher trophic status. By linking qPCR-based phytoplankton abundance to chlorophyll a, this study demonstrates that qPCR is a promising avenue to investigate the population dynamics of phytoplankton and the trophic status (or eutrophication) of freshwater rivers.

Long-term trend forecast of chlorophyll-a concentration over eutrophic lakes based on time series decomposition and deep learning algorithm.

Long-term trend forecast of chlorophyll-a concentration (Chla) holds significant implications for eutrophication management and pollution control planning on lakes, especially under the background of climate change. However, it is a challenging task due to the mixture of trend, seasonal and residual components in time series and the nonlinear relationships between Chla and the hydro-environmental factors. Here we developed a hybrid approach for long-term trend forecast of Chla in lakes, taking the Lake Taihu as an instantiation case, by the integration of Seasonal and Trend decomposition using Loess (STL), wavelet coherence, and Convolutional Neural Network with Bidirectional Long Short-Term Memory (CNN-BiLSTM). The results showed that long-term trends of Chla and the hydro-environmental factors could be effectively separated from the seasonal and residual terms by STL method, thereby enhancing the characterization of long-term variation. The resonance pattern and time lag between Chla and the hydro-environmental factors in the time-frequency domain were accurately identified by wavelet coherence. Chla responded quickly to variations in TP, but showed a time lag response to variations in WT in Lake Taihu. The forecasting method using multivariate and CNN-BiLSTM largely outperformed the other methods for Lake Taihu with regards to R2, RMSE, IOA and peak capture capability, owning to the combination of CNN for extracting local features and the integration of bidirectional propagation mechanism for the acquisition of higher-level features. The proposed hybrid deep learning approach offers an effective solution for the long-term trend forecast of algal blooms in eutrophic lakes and is capable of addressing the complex attributes of hydro-environmental data.

Enhanced forecasting of chlorophyll-a concentration in coastal waters through integration of Fourier analysis and Transformer networks.

The accurate prediction of chlorophyll-a (chl-a) concentration in coastal waters is essential to coastal economies and ecosystems as it serves as the key indicator of harmful algal blooms. Although powerful machine learning methods have made strides in forecasting chl-a concentrations, there remains a gap in effectively modeling the dynamic temporal patterns and dealing with data noise and unreliability. To wiggle out of quagmires, we introduce an innovative deep learning prediction model (termed ChloroFormer) by integrating Transformer networks with Fourier analysis within a decomposition architecture, utilizing coastal in-situ data from two distinct study areas. Our proposed model exhibits superior capabilities in capturing both short-term and middle-term dependency patterns in chl-a concentrations, surpassing the performance of six other deep learning models in multistep-ahead predictive accuracy. Particularly in scenarios involving extreme and frequent blooms, our proposed model shows exceptional predictive performance, especially in accurately forecasting peak chl-a concentrations. Further validation through Kolmogorov-Smirnov tests attests that our model not only replicates the actual dynamics of chl-a concentrations but also preserves the distribution of observation data, showcasing its robustness and reliability. The presented deep learning model addresses the critical need for accurate prediction on chl-a concentrations, facilitating the exploration of marine observations with complex dynamic temporal patterns, thereby supporting marine conservation and policy-making in coastal areas.

Smartphone as an alternative to measure chlorophyll-a concentration in small waterbodies.

Monitoring chlorophyll-a concentrations (Chl-a, µg·L-1) in aquatic ecosystems has attracted much attention due to its direct link to harmful algal blooms. However, there has been a lack of a cost-effective method for measuring Chl-a in small waterbodies. Inspired by the increase of smartphone photography, a Smartphone-based convolutional neural networks (CNN) framework (SCCA) was developed to estimate Chl-a in Aquatic ecosystem. To evaluate the performance of SCCA, 238 paired records (a smartphone image with a 12-color background and a measured Chl-a value) were collected from diverse aquatic ecosystems (e.g., rivers, lakes and ponds) across China in 2023. Our performance-evaluation results revealed a NS and R2 value of 0.90 and 0.94 in Chl-a estimation, demonstrating a satisfactory (NS = 0.84, R2 = 0.86) model fit in lower Chl-a (<30 µg L-1) conditions. SCCA had involved a realtime-update method with hyperparameter optimization technology. In comparison with the existing methods of measuring Chl-a, SCCA provides a useful screening tool for cost-effective measurement of Chl-a and has the potential for being an algal bloom screening means in small waterbodies, using Huajin River as a case study, especially under limited resources for water measurement. Overall, we highlight that the SCCA can be potentially integrated into a smartphone application in the future to diverse waterbodies in environmental management.

The impact of marine heatwaves on surface phytoplankton chlorophyll-a in the South China Sea.

According to previous studies, marine heatwaves (MHWs) significantly suppress the phytoplankton chlorophyll-a concentration (Chl a) in tropical oceans. However, pre-MHW Chl a has rarely been considered as a reference value. In this study, the Chl a for the periods preceding and during MHWs events was used to explore the impact of MHWs on Chl a from 1998 to 2022 in the South China Sea (SCS). The Chl a response to MHWs in different regions was further discussed based on the Chl a variation characteristics. The results showed that the Chl a response to MHWs exhibited regional variability. Interestingly, there was a large proportion of positive Chl a anomalies (∼0.55) in the estuary and offshore regions during MHWs; however, Chl a anomalies were mostly negative in the upwelling regions. These different response patterns are related to background conditions, including nutrient concentrations, wind-driven dynamics, and light availability. In upwelling regions, negative Chl a anomalies were primarily due to the weakening of wind speeds, Ekman pumping velocities, and upwelling intensities. In estuarine regions, positive Chl a anomalies were caused by enhanced light availability, whereas in offshore regions, there were attributed to the increased atmospheric wet deposition. These results have improved our understanding of the impact of MHWs on marine ecosystems.

Foliar Spraying with ZnSO4 or ZnO of Vitis vinifera cv. Syrah Increases the Synthesis of Photoassimilates and Favors Winemaking.

Zinc enrichment of edible food products, through the soil and/or foliar application of fertilizers, is a strategy that can increase the contents of some nutrients, namely Zn. In this context, a workflow for agronomic enrichment with zinc was carried out on irrigated Vitis vinifera cv. Syrah, aiming to evaluate the mobilization of photoassimilates to the winegrapes and the consequences of this for winemaking. During three productive cycles, foliar applications were performed with ZnSO4 or ZnO, at concentrations ranging between 150 and 1350 g.ha-1. The normal vegetation index as well as some photosynthetic parameters indicated that the threshold of Zn toxicity was not reached; it is even worth noting that with ZnSO4, a significant increase in several cases was observed in net photosynthesis (Pn). At harvest, Zn biofortification reached a 1.2 to 2.3-fold increase with ZnSO4 and ZnO, respectively (being significant relative to the control, in two consecutive years, with ZnO at a concentration of 1350 g.ha-1). Total soluble sugars revealed higher values with grapes submitted to ZnSO4 and ZnO foliar applications, which can be advantageous for winemaking. It was concluded that foliar spraying was efficient with ZnO and ZnSO4, showing potential benefits for wine quality without evidencing negative impacts.

Structural and spectroscopic insights into fucoxanthin chlorophyll a/c-binding proteins of diatoms in diverse oligomeric states.

Diatoms, a group of prevalent marine algae, significantly contribute to global primary productivity. Their substantial biomass is linked to enhanced absorption of blue-green light underwater, facilitated by fucoxanthin chlorophyll a/c-binding proteins (FCPs), exhibiting oligomeric diversity across diatom species. Utilizing mild CN-PAGE analysis on solubilized thylakoid membranes, we displayed monomeric, dimeric, trimeric, tetrameric and pentameric FCPs in diatoms. Mass spectrometry analysis revealed each oligomeric FCP has specific protein compositions, constituting a large Lhcf family of FCP antennas. In addition, we resolved the structures of Thalassiosira pseudonana FCP (Tp-FCP) homotrimer and Chaetoceros gracilis FCP (Cg-FCP) pentamer by cryo-electron microscopy at 2.73 Å and 2.65 Å resolutions, respectively. The distinct pigment composition and organization in various oligomeric FCPs change their blue-green light-harvesting, excitation energy transfer pathways. In comparison to dimeric and trimeric FCPs, Cg-FCP tetramer and Cg-FCP pentamer exhibit stronger absorption by Chls c, red-shifted and broader Chl a fluorescence emission, as well as more robust circular dichroism signals originating from Chl a-carotenoid dimers. These spectroscopic characteristics indicate that Chl a molecules in Cg-FCP tetramer and Cg-FCP pentamer are more heterogeneous than in both dimers and Tp-FCP trimer. The structural and spectroscopic insights provided by this study contribute to a better understanding of the mechanisms that empower diatoms to adapt to fluctuating light environments.

The sound of lichens: ultrasonic acoustic emissions during desiccation question cavitation events in the hyphae.

Lichens are a mutualistic symbiosis between a fungus and one or more photosynthetic partners. They are photosynthetically active during desiccation until relative water contents (RWC) as low as 30% (on dry mass). Experimental evidence suggests that during desiccation, the photobionts have a higher hydration level than the surrounding fungal pseudo-tissues. Explosive cavitation events in the hyphae might cause water movements towards the photobionts. This hypothesis was tested in two foliose lichens by measurements of ultrasonic acoustic emissions (UAE), a method commonly used in vascular plants but never in lichens, and by measurements of photosystem II efficiency, water potential and RWC. Thallus structural changes were characterised by low-temperature scanning electron microscopy. The thalli were silent between 380% and 30% RWCs, i.e. when explosive cavitation events should cause movements of liquid water. Nevertheless, the thalli emitted UAE at approximately 5% RWC. Accordingly, the medullary hyphae were partially shrunk at about 15% RWC, whereas they were completely shrunk below 5% RWC. These results do not support the hypothesis of hyphal cavitation and suggest that the UAE originate from structural changes at hyphal level. The shrinking of hyphae is proposed as an adaptation to avoid cell damage at very low RWCs.

Phytoplankton Assemblage over a 14-Year Period in the Adriatic Sea: Patterns and Trends.

Considering the role of phytoplankton in the functioning and health of marine systems, it is important to characterize its responses to a changing environment. The central Adriatic Sea, as a generally oligotrophic area, is a suitable environment to distinguish between regular fluctuations in phytoplankton and those caused by anthropogenic or climatic influences. This study provides a long-term perspective of phytoplankton assemblage in the central eastern Adriatic Sea, with 14 years of continuous time series data collected at two coastal and two offshore stations. The predominant phytoplankton groups were diatoms and phytoflagellates, but their proportion varied depending on the vicinity of the coast, as evidenced also by the distribution of chlorophyll a. In the coastal environment, the phytoplankton biomass was substantially higher, with a higher proportion of microphytoplankton, while small phytoplankton accounted for the majority of biomass in the offshore area. In addition, a decreasing trend in diatom abundance was observed in the coastal waters, while such trend was not so evident in the offshore area. Using a neural gas algorithm, five clusters were defined based on the contribution of the major groups. The observed increase in diversity, especially in dinoflagellates, which outnumber diatom taxa, could be a possible adaptation of dinoflagellates to the increased natural solar radiation in summer and the increased sea surface temperature.

Spatiotemporal variability of lake surface water temperature and water quality parameters and its interrelationship with water hyacinth biomass in Lake Tana, Ethiopia.

Urbanization, agriculture, and climate change affect water quality and water hyacinth growth in lakes. This study examines the spatiotemporal variability of lake surface water temperature, turbidity, and chlorophyll-a (Chl-a) and their association with water hyacinth biomass in Lake Tana. MODIS Land/ Lake surface water temperature (LSWT), Sentinel 2 MSI Imagery, and in-situ water quality data were used. Validation results revealed strong positive correlations between MODIS LSWT and on-site measured water temperature (R = 0.90), in-situ turbidity and normalized difference turbidity index (NDTI) (R = 0.92), and in-situ Chl-a and normalized difference chlorophyll index (NDCI) (R = 0.84). LSWT trends varied across the lake, with increasing trends in the northeastern, northwestern, and southwestern regions and decreasing trends in the western, southern, and central areas (2001-2022). The spatial average LSWT trend decreased significantly in pre-rainy (0.01 ℃/year), rainy (0.02 ℃/year), and post-rainy seasons (0.01℃/year) but increased non-significantly in the dry season (0.00 ℃/year) (2001-2022, P < 0.05). Spatial average turbidity decreased significantly in all seasons, except in the pre-rainy season (2016-2022). Likewise, spatial average Chl-a decreased significantly in pre-rainy and rainy seasons, whereas it showed a non-significant increasing trend in the dry and post-rainy seasons (2016-2022). Water hyacinth biomass was positively correlated with LSWT (R = 0.18) but negatively with turbidity (R = -0.33) and Chl-a (R = -0.35). High spatiotemporal variability was observed in LSWT, turbidity, and Chl-a, along with overall decreasing trends. The findings suggest integrated management strategies to balance water hyacinth eradication and its role in water purification. The results will be vital in decision support systems and preparing strategic plans for sustainable water resource management, environmental protection, and pollution prevention.

Examining chlorophyll-a concentrations in tropical reservoirs under various land use changes using Sentinel - 2 and Google Earth engine - Bhadra and Tungabhadra, India.

The understanding of spatio-temporal variation in land use and land cover (LULC) patterns is crucial for managing catchment land use planning, as it directly influences of tropical reservoir water quality and the subsequent Nutrient Contamination (NC) of unmonitored water bodies. The current research attempts to accurately measure the influence of LULC and its associated determinants on the quantities of NC loads by using Chl-a as a proxy, within tropical reservoirs, i.e. Bhadra and Tungabhadra, located in same river catchment. This Chl-a spread calculated by the Maximum Chlorophyll Index (MCI) derived from Sentinel 2 satellite data products covering the period from July 2016 to June 2021 were done using Google Earth Engine (GEE) platform. The validation analysis confirms the robustness of the methodology with a strong correlation between MCI-calculated values and EOMAP (Earth Observation and Environmental Services Mapping) Chl-a (µg/L) data points for both reservoirs, Bhadra (R2 = 0.64) and Tungabhadra (R2 = 0.68). The findings reveal that, Tungabhadra reservoir consistently exhibits an excessive spatial distribution of Chl-a spread area (17 km2 to 335 km2), reflecting nutrient-rich water inflows, particularly evident during the post-monsoon period. This notable rise could be linked to harvesting the Kharif crop, resulting in elevated nutrient concentrations. In contrast Bhadra reservoir, dominated by forested areas, maintains relatively lower Chl-a spread areas (<20 km2), highlighting its pivotal role in maintaining water cleanliness and serves as a riparian boundary. In addition, the changes in LULC classes show a strong relationship with variation in Chl-a during the studied period, for the Bhadra Reservoir R2 = 0.51 (F- statistics = 3.983, p = 0.021), and the Tungabhadra Reservoir R2 = 0.802 (F- statistics = 7.489, p = 0.0143). This highlights how changes in land use significantly shape contamination dynamics, deepening our understanding of nutrient inputs and contamination drivers in tropical reservoirs.

Improving denitrification estimation by joint inclusion of suspended particles and chlorophyll a in aquaculture ponds.

The denitrification process in aquaculture systems plays a crucial role in nitrogen (N) cycle and N budget estimation. Reliable models are needed to rapidly quantify denitrification rates and assess nitrogen losses. This study conducted a comparative analysis of denitrification rates in fish, crabs, and natural ponds in the Taihu region from March to November 2021, covering a complete aquaculture cycle. The results revealed that aquaculture ponds exhibited higher denitrification rates compared to natural ponds. Key variables influencing denitrification rates were Nitrate nitrogen (NO3--N), Suspended particles (SPS), and chlorophyll a (Chla). There was a significant positive correlation between SPS concentration and denitrification rates. However, we observed that the denitrification rate initially rose with increasing Chla concentration, followed by a subsequent decline. To develop parsimonious models for denitrification rates in aquaculture ponds, we constructed five different statistical models to predict denitrification rates, among which the improved quadratic polynomial regression model (SQPR) that incorporated the three key parameters accounted for 80.7% of the variability in denitrification rates. Additionally, a remote sensing model (RSM) utilizing SPS and Chla explained 43.8% of the variability. The RSM model is particularly valuable for rapid estimation in large regions where remote sensing data are the only available source. This study enhances the understanding of denitrification processes in aquaculture systems, introduces a new model for estimating denitrification in aquaculture ponds, and offers valuable insights for environmental management.

Expanding the Application of Sentinel-2 Chlorophyll Monitoring across United States Lakes.

Eutrophication of inland lakes poses various societal and ecological threats, making water quality monitoring crucial. Satellites provide a comprehensive and cost-effective supplement to traditional in situ sampling. The Sentinel-2 MultiSpectral Instrument (S2 MSI) offers unique spectral bands positioned to quantify chlorophyll a, a water-quality and trophic-state indicator, along with fine spatial resolution, enabling the monitoring of small waterbodies. In this study, two algorithms-the Maximum Chlorophyll Index (MCI) and the Normalized Difference Chlorophyll Index (NDCI)-were applied to S2 MSI data. They were calibrated and validated using in situ chlorophyll a measurements for 103 lakes across the contiguous U.S. Both algorithms were tested using top-of-atmosphere reflectances (ρ t), Rayleigh-corrected reflectances (ρ s), and remote sensing reflectances (R rs ). MCI slightly outperformed NDCI across all reflectance products. MCI using ρ t showed the best overall performance, with a mean absolute error factor of 2.08 and a mean bias factor of 1.15. Conversion of derived chlorophyll a to trophic state improved the potential for management applications, with 82% accuracy using a binary classification. We report algorithm-to-chlorophyll-a conversions that show potential for application across the U.S., demonstrating that S2 can serve as a monitoring tool for inland lakes across broad spatial scales.

Photosynthetic Performance and Yield Losses of Winter Rapeseed (Brassica napus L. var. napus) Caused by Simulated Hail.

Winter oilseed rape (Brassica napus L.), Europe's foremost oilseed crop, is significantly impacted by hailstorms, leading to substantial yield reductions that are difficult to predict and measure using conventional methods. This research aimed to assess the effectiveness of photosynthetic efficiency analysis for predicting yield loss in winter rapeseed subjected to hail exposure. The aim was to pinpoint the chlorophyll fluorescence parameters most affected by hail stress and identify those that could act as non-invasive biomarkers of yield loss. The study was conducted in partially controlled conditions (greenhouse). Stress was induced in the plants by firing plastic balls with a 6 mm diameter at them using a pneumatic device, which launched the projectiles at speeds of several tens of meters per second. Measurements of both continuous-excitation and pulse-modulated-amplitude chlorophyll fluorescence were engaged to highlight the sensitivity of the induction curve and related parameters to hail stress. Our research uncovered that some parameters such as Fs, Fm', ΦPSII, ETR, Fo, Fv/Fm, and Fv/Fo measured eight days after the application of stress had a strong correlation with final yield, thus laying the groundwork for the creation of new practical protocols in agriculture and the insurance industry to accurately forecast damage to rapeseed crops due to hail stress.

Inversion Method for Chlorophyll-a Concentration in High-Salinity Water Based on Hyperspectral Remote Sensing Data.

As one of the important lakes in the "One Lake and Two Seas" of the Inner Mongolia Autonomous Region, the monitoring of water quality in Lake Daihai has attracted increasing attention, and the concentration of chlorophyll-a directly affects the water quality, making the monitoring of chlorophyll-a concentration in Lake Daihai particularly crucial. Traditional methods of monitoring chlorophyll-a concentration are not only inefficient but also require significant human and material resources. Remote sensing technology has the advantages of wide coverage and short update cycles. For lakes such as Daihai with a high salinity content, salinity is considered a key factor when inverting the concentration of chlorophyll-a. In this study, machine learning models, including model stacking from ensemble learning, a ridge regression model, and a random forest model, were constructed. After comparing the training accuracy of the three models on Zhuhai-1 satellite data, the random forest model, which had the highest accuracy, was selected as the final training model. By comparing the accuracy changes before and after adding salinity factors to the random forest model, a high-precision model for inverting chlorophyll-a concentration in hypersaline lakes was obtained. The research results show that, without considering the salinity factor, the root mean square error (RMSE) of the model was 0.056, and the coefficient of determination (R2) was 0.64, indicating moderate model performance. After adding the salinity factor, the model accuracy significantly improved: the RMSE decreased to 0.047, and the R2 increased to 0.92. This study provides a solid basis for the application of remote sensing technology in hypersaline aquatic environments, confirming the importance of considering salinity when estimating chlorophyll-a concentration in hypersaline waters. This research helps us gain a deeper understanding of the water quality and ecosystem evolution in Daihai Lake.

Primary production in the bays of the novaya zemlya archipelago (Kara Sea) in the contrasting glacial and non-glacial environmental conditions.

Ongoing warming is leading to the accelerated shrinkage of glaciers located on Arctic islands. Consequently, the influence of glacial meltwater on phytoplankton primary production in Arctic bays becomes critically important in an era of warming. This work studies the spatiotemporal variation of primary production and chlorophyll a concentration in the bays along the eastern coast of the Novaya Zemlya archipelago. Data were collected during nine cruises performed from July to October (2013-2022). The effect of underwater photosynthetically available radiation (PAR) and nutrients on primary production was assessed separately for bays influenced by glacial meltwater (glacial bays) and those without such influence (non-glacial bays). The median value of water column-integrated primary production (IPP) for all bays was 38 mgC m-2 d-1, characterizing them as oligotrophic areas. IPP in non-glacial bays was found to be 2.3-fold and 1.4-fold higher than that in glacial bays during summer and autumn, respectively. Underwater PAR was the main abiotic factor determining IPP during the ice-free period. In the entire bays nutrient concentrations were high, exceeding the limiting values for growth and photosynthesis of phytoplankton. It was concluded that the high turbidity from glacial meltwater runoff leads to decreased underwater PAR and, consequently, to a decline in IPP. This study demonstrates that rapid warming could have a negative impact on the productivity of high Arctic bays and their adjacent areas.

Change in water column total chlorophyll-a in the Mediterranean revealed by satellite observation.

Chlorophyll-a (Chl-a) is a crucial pigment in algae and macrophytes, which makes the concentration of total Chl-a in the water column (total Chl-a) an essential indicator for estimating the primary productivity and carbon cycle of the ocean. Integrating the Chl-a concentration at different depths (Chl-a profile) is an important way to obtain the total Chl-a. However, due to limited cost and technology, it is difficult to measure Chl-a profiles directly in a spatially continuous and high-resolution way. In this study, we proposed an integrated strategy model that combines three different machine learning methods (PSO-BP, random forest and gradient boosting) to predict the Chl-a profile in the Mediterranean by using several sea surface variables (photosynthetically active radiation, spectral irradiance, sea surface temperature, wind speed, euphotic depth and KD490) and subsurface variables (mixed layer depth) observed by or estimated from satellite and BGC-Argo float observations. After accuracy estimation, the integrated model was utilized to generate the time series total Chl-a in the Mediterranean from 2003 to 2021. By analysing the time series results, it was found that seasonal fluctuation contributed the most to the variation in total Chl-a. In addition, there was an overall decreasing trend in the Mediterranean phytoplankton biomass, with the total Chl- decreasing at a rate of 0.048 mg/m2 per year, which was inferred to be related to global warming and precipitation reduction based on comprehensive analysis with sea surface temperature and precipitation data.