Modeling ocean surface chlorophyll-a concentration from ocean color remote sensing reflectance in global waters using machine learning

Global marine phytoplankton dynamics analysis with machine learning and reanalyzed remote sensing

Phytoplankton are the world's largest oxygen producers found in oceans, seas and large water bodies, which play crucial roles in the marine food chain. Unbalanced biogeochemical features like salinity, pH, minerals, etc., can retard their growth. With advancements in better hardware, the usage of Artificial Intelligence techniques is rapidly increasing for creating an intelligent decision-making system. Therefore, we attempt to overcome this gap by using supervised regressions on reanalysis data targeting global phytoplankton levels in global waters. The presented experiment proposes the applications of different supervised machine learning regression techniques such as random forest, extra trees, bagging and histogram-based gradient boosting regressor on reanalysis data obtained from the Copernicus Global Ocean Biogeochemistry Hindcast dataset. Results obtained from the experiment have predicted the phytoplankton levels with a coefficient of determination score (R2) of up to 0.96. After further validation with larger datasets, the model can be deployed in a production environment in an attempt to complement in-situ measurement efforts.

An optical mechanism-based deep learning approach for deriving water trophic state of China's lakes from Landsat images

Widespread eutrophication has been considered as the most serious environment problems in the world. Given the critical roles of lakes in human society and serious negative effects of water eutrophication on lake ecosystems, it is thus fundamentally important to monitor and assess water trophic status of lakes. However, a reliable model for accurately estimating the trophic state index (TSI) of lakes across a large-scale region is still lacking due to their high complexity. Here, we proposed an optical mechanism-based deep learning approach to remotely estimate TSI of lakes based on Landsat images. The approach consists of two steps: (1) determining the optical indicators of TSI and modeling the relationship between them, and (2) developing an approach for remotely deriving the determined optical indicator from Landsat images. With a large number of in situ datasets measured from lakes (2804 samples from 88 lakes) across China with various optical properties, we trained and validated three machine learning methods including deep neural network (DNN), k-nearest neighbors (KNN) and random forest (RF) to model TSI with the optical indicators and TSI and derive the determined optical indicator from Landsat images. The results showed that (1) the total absorption coefficients of optically active constituents at 440 nm (at-w(440)) performs best in characterizing TSI, and (2) DNN outperforms other models in the inversion of both TSI and at-w(440). Overall, our proposed optical mechanism-based deep learning approach demonstrated a robust and satisfactory performance in assessing TSI using Landsat images (root mean squared error (RMSE) = 5.95, mean absolute error (MAE) = 4.81). This highlights its merit as a nationally-adopted method in lake water TSI estimation, enabling the convenience of the acquisition of water eutrophic information in large scale, thereby assisting us in managing lake ecology. Therefore, we assessed water TSI of 961 lakes (>10 km2) across China using the proposed approach. The resulting at-w(440) and TSI ranged from 0.01 m-1 to 31.42 m-1 and from 6 to 96, respectively. Of all these studied lakes, 96 lakes (11.40 %) were oligotrophic, 338 lakes were mesotrophic (40.14 %), 360 lakes were eutrophic (42.76 %), and 48 were hypertrophic (5.70 %) in 2020.

Decision tree ensemble with Bayesian optimization to predict the spatial dynamics of chlorophyll-a concentration: A case study in Bay of Bengal

An accurate prediction of the spatial distribution of phytoplankton biomass, as represented by Chlorophyll-a (CHL-a) concentrations, is important for assessing ecological conditions in the marine environment. This study developed a hyperparameter-optimized decision tree-based machine learning (ML) models to predict the geographical distribution of marine phytoplankton CHL-a in the Bay of Bengal. To predict CHL-a over a large spatial extent, satellite-derived remotely sensed data of ocean color features (CHL-a, colored dissolved organic matter, photosynthetically active radiation, particulate organic carbon) and climatic factors (nighttime sea surface temperature, surface absorbed longwave radiation, sea level pressure) from 2003 to 2022 are used to train and test the models. Results obtained from this study have shown the highest concentrations of CHL-a occurred near the Bay's coastal belts and river estuaries. Analysis revealed that aside from photosynthetically active radiation, organic components exhibited a stronger positive relationship with CHL-a than climatic features, which are correlated negatively. Results showed the chosen decision tree methods to all possess higher R2 and lower root mean square error (RMSE) errors. Furthermore, XGBoost outperforms all other models in predicting the geographic distribution of CHL-a. To assess the model efficacy on seasonal basis, a best performing XGBoost model was validated in the Bay of Bengal region which has shown a good performance in predicting the spatial distribution of Chl-a as well as the pixel values during the summer, winter and monsoon seasons. This study provides the best ML model to researchers for predicting CHL-a in the Bay of Bengal. Further it helps to improve our knowledge of CHL-a spatial dynamics and assist in monitoring marine resources in the Bay of Bengal. It worth noting that the water quality in the Indian Ocean is very dynamic in nature, therefore, additional efforts are needed to test the efficacy of this study model over different seasons and spatial gradients.

Monitor water quality through retrieving water quality parameters from hyperspectral images using graph convolution network with superposition of multi-point effect: A case study in Maozhou River

Quantitative prediction by unmanned aerial vehicle (UAV) remote sensing on water quality parameters (WQPs) including phosphorus, nitrogen, chemical oxygen demand (COD), biochemical oxygen demand (BOD), and chlorophyll a (Chl-a), total suspended solids (TSS), and turbidity provides a flexible and effective approach to monitor the variation in water quality. In this study, a deep learning-based method integrating graph convolution network (GCN), gravity model variant, and dual feedback machine involving parametric probability analysis and spatial distribution pattern analysis, named Graph Convolution Network with Superposition of Multi-point Effect (SMPE-GCN) has been developed to calculate concentrations of WQPs through UAV hyperspectral reflectance data on large scale efficiently. With an end-to-end structure, our proposed method has been applied to assisting environmental protection department to trace potential pollution sources in real time. The proposed method is trained on a real-world dataset and its effectiveness is validated on an equal amount of testing dataset with respect to three evaluation metrics including root of mean squared error (RMSE), mean absolute percent error (MAPE), and coefficient of determination (R²). The experimental results demonstrate that our proposed model achieves better performance in comparison with state-of-the-art baseline models in terms of RMSE, MAPE, and R². The proposed method is applicable for quantifying seven various WQPs and has achieved good performance for each WQP. The resulting MAPE ranges from 7.16% to 10.96% and R² ranges from 0.80 to 0.94 for all WQPs. This approach brings a novel and systematic insight into real-time quantitative water quality monitoring of urban rivers, and provides a unified framework for in-situ data acquisition, feature engineering, data conversion, and data modeling for further research. It provides fundamental support to assist environmental managers to efficiently monitor water quality of urban rivers.

Incorporating marine particulate carbon into machine learning for accurate estimation of coastal chlorophyll-a

Accurate predictions of coastal ocean chlorophyll-a (Chl-a) concentrations are necessary for dynamic water quality monitoring, with eutrophication as a critical factor. Prior studies that used the driven-data method have typically overlooked the relationship between Chl-a and marine particulate carbon. To address this gap, marine particulate carbon was incorporated into machine learning (ML) and deep learning (DL) models to estimate Chl-a concentrations in the Yang Jiang coastal ocean of China. Incorporating particulate organic carbon (POC) and particulate inorganic carbon (PIC) as predictors can lead to successful Chl-a estimation. The Gaussian process regression (GPR) model significantly outperforming the DL model in terms of stability and robustness. A lower POC/Chl-a ratio was observed in coastal areas, in contrast to the higher ratios detected in the southern regions of the study area. This study highlights the efficacy of the GPR model for estimating Chl-a and the importance of considering POC in modeling Chl-a concentrations.