Developing a New Machine-Learning Algorithm for Estimating Chlorophyll-a Concentration in Optically Complex Waters: A Case Study for High Northern Latitude Waters by Using Sentinel 3 OLCI

Machine learning methods for assessing photosynthetic activity: environmental monitoring applications

Monitoring of the photosynthetic activity of natural and artificial biocenoses is of crucial importance. Photosynthesis is the basis for the existence of life on Earth, and a decrease in primary photosynthetic production due to anthropogenic influences can have catastrophic consequences. Currently, great efforts are being made to create technologies that allow continuous monitoring of the state of the photosynthetic apparatus of terrestrial plants and microalgae. There are several sources of information suitable for assessing photosynthetic activity, including gas exchange and optical (reflectance and fluorescence) measurements. The advent of inexpensive optical sensors makes it possible to collect data locally (manually or using autonomous sea and land stations) and globally (using aircraft and satellite imaging). In this review, we consider machine learning methods proposed for determining the functional parameters of photosynthesis based on local and remote optical measurements (hyperspectral imaging, solar-induced chlorophyll fluorescence, local chlorophyll fluorescence imaging, and various techniques of fast and delayed chlorophyll fluorescence induction). These include classical and novel (such as Partial Least Squares) regression methods, unsupervised cluster analysis techniques, various classification methods (support vector machine, random forest, etc.) and artificial neural networks (multilayer perceptron, long short-term memory, etc.). Special aspects of time-series analysis are considered. Applicability of particular information sources and mathematical methods for assessment of water quality and prediction of algal blooms, for estimation of primary productivity of biocenoses, stress tolerance of agricultural plants, etc. is discussed.

Toward Atmospheric Correction Algorithms for Sentinel-3/OLCI Images of Productive Waters

Atmospheric correction of remote sensing imagery over optically complex waters is still a challenging task. Even algorithms showing a good accuracy for moderate and extremely turbid waters need to be tested when being used for eutrophic inland basins. Such a test was carried out in this study on the example of a Sentinel-3/OLCI image of the productive waters of the Gorky Reservoir during the period of intense blue-green algal bloom using data on the concentration of chlorophyll a and remote sensing reflectance measured from the motorboat at many points of the reservoir. The accuracy of four common atmospheric correction (AC) algorithms was examined. All of them showed unsatisfactory accuracy due to incorrect determination of atmospheric aerosol parameters and aerosol radiance. The calculated aerosol optical depth (AOD) spectra varied widely (AOD(865) = 0.005 − 0.692) even over a small area (up to 10 × 10 km) and correlated with the measured chlorophyll a. As a result, a part of the high water-leaving signal caused by phytoplankton bloom was taken as an atmosphere signal. A significant overestimation of atmospheric aerosol parameters, as a consequence, led to a strong underestimation of the remote sensing reflectance and low accuracy of the considered AC algorithms. To solve this problem, an algorithm with a fixed AOD was proposed. The fixed AOD spectrum was determined in the area with relatively “clean” water as 5 percentiles of AOD in all water pixels. The proposed algorithm made it possible to obtain the remote sensing reflectance with high accuracy. The slopes of linear regression are close to 1 and the intercepts tend to zero in almost all spectral bands. The determination coefficients are more than 0.9; the bias, mean absolute percentage error, and root-mean-square error are notably lower than for other AC algorithms.

Comparing the performance of machine learning algorithms for remote and in situ estimations of chlorophyll-a content: A case study in the Tri An Reservoir, Vietnam

Chlorophyll-a (Chl-a) is one of the most important indicators of the trophic status of inland waters, and its continued monitoring is essential. Recently, the operated Sentinel-2 MSI satellite offers high spatial resolution images for remote water quality monitoring. In this study, we tested the performance of the three well-known machine learning (ML) (random forest [RF], support vector machine [SVM], and Gaussian process [GP]) and the two novel ML (extreme gradient boost (XGB) and CatBoost [CB]) models for estimation a wide range of Chl-a concentration (10.1-798.7 μg/L) using the Sentinel-2 MSI data and in situ water quality measurement in the Tri An Reservoir (TAR), Vietnam. GP indicated the most reliable model for predicting Chl-a from water quality parameters (R²  = 0.85, root-mean-square error [RMSE] = 56.65 μg/L, Akaike's information criterion [AIC] = 575.10, and Bayesian information criterion [BIC] = 595.24). Regarding input model as water surface reflectance, CB was the superior model for Chl-a retrieval (R²  = 0.84, RMSE = 46.28 μg/L, AIC = 229.18, and BIC = 238.50). Our results indicated that GP and CB are the two best models for the prediction of Chl-a in TAR. Overall, the Sentinel-2 MSI coupled with ML algorithms is a reliable, inexpensive, and accurate instrument for monitoring Chl-a in inland waters. PRACTITIONER POINTS: Machine learning algorithms were used for both remote sensing data and in situ water quality measurements. The performance of five well-known machine learning models was tested Gaussian process was the most reliable model for predicting Chl-a from water quality parameters CatBoost was the best model for Chl-a retrieval from water surface reflectance.

Comparison of In-Situ Chlorophyll-a Time Series and Sentinel-3 Ocean and Land Color Instrument Data in Slovenian National Waters (Gulf of Trieste, Adriatic Sea)

While satellite remote sensing of ocean color is a viable tool for estimating large-scale patterns of chlorophyll-a (Chl-a) and global ocean primary production, its application in coastal waters is limited by the complex optical properties. An exploratory study was conducted in the Gulf of Trieste (Adriatic Sea) to assess the usefulness of Sentinel-3 satellite data in the Slovenian national waters. OLCI (Ocean and Land Colour Instrument) Chl-a level 2 products (OC4Me and NN) were compared to monthly Chl-a in-situ measurements at fixed sites from 2017 to 2019. In addition, eight other methods for estimating Chl-a concentration based on reflectance in different spectral bands were tested (OC3M, OC4E, MedOC4, ADOC4, AD4, 3B-OLCI, 2B-OLCI and G2B). For some of these methods, calibration was performed on in-situ data to achieve a better agreement. Finally, L1-regularized regression and random forest were trained on the available dataset to test the capabilities of the machine learning approach. The results show rather poor performance of the two originally available products. The same is true for the other eight methods and the fits to the measured values also show only marginal improvement. The best results are obtained with the blue-green methods (OC3, OC4 and AD4), especially the AD4SI (a designated fit of AD4) with R = 0.56 and RMSE = 0.4 mg/m³, while the near infrared (NIR) methods show underwhelming performance. The machine learning approach can only explain 30% of the variability and the RMSE is of the same order as for the blue-green methods. We conclude that due to the low Chl-a concentration and the moderate turbidity of the seawater, the reflectance provided by the Sentinel-3 OLCI spectrometer carries little information about Chl-a in the Slovenian national waters within the Gulf of Trieste and is therefore of limited use for our purposes. This requires that we continue to improve satellite products for use in those marine waters that have not yet proven suitable. In this way, satellite data could be effectively integrated into a comprehensive network that would allow a reliable assessment of ecological status, taking into account environmental regulations.

Estimating Coastal Chlorophyll-A Concentration from Time-Series OLCI Data Based on Machine Learning

Chlorophyll-a (chl-a) is an important parameter of water quality and its concentration can be directly retrieved from satellite observations. The Ocean and Land Color Instrument (OLCI), a new-generation water-color sensor onboard Sentinel-3A and Sentinel-3B, is an excellent tool for marine environmental monitoring. In this study, we introduce a new machine learning model, Light Gradient Boosting Machine (LightGBM), for estimating time-series chl-a concentration in Fujian’s coastal waters using multitemporal OLCI data and in situ data. We applied the Case 2 Regional CoastColour (C2RCC) processor to obtain OLCI band reflectance and constructed four spectral indices based on OLCI feature bands as supplementary input features. We also used root-mean-square error (RMSE), mean absolute error (MAE), median absolute percentage error (MAPE), and R2 as performance indicators. The results indicate that the addition of spectral indices can easily improve the prediction accuracy of the model, and normalized fluorescence height index (NFHI) has the best performance, with an RMSE of 0.38 µg/L, MAE of 0.22 µg/L, MAPE of 28.33%, and R2 of 0.785. Moreover, we used the well-known band ratio and three-band methods for chl-a estimation validation, and another two OLCI chl-a products were adopted for comparison (OC4Me chl-a and Inverse Modelling Technique (IMT) Neural Net chl-a). The results confirmed that the LightGBM model outperforms the traditional methods and OLCI chl-a products. This study provides an effective remote sensing technique for coastal chl-a concentration estimation and promotes the advantage of OLCI data in ocean color remote sensing.

Combining Artificial Neural Networks with Causal Inference for Total Phosphorus Concentration Estimation and Sensitive Spectral Bands Exploration Using MODIS

The total phosphorus (TP) concentration is a key water quality parameter for water monitoring and a major indicator of the state of eutrophication in inland lakes. Using remote-sensing to estimate TP concentration is useful, as it provides a synoptic view of the entire water region; however, the weak optical characteristics of TP lead to difficulty in accurately estimating TP concentration. The differences in water characteristics and components between lakes mean that most TP estimation methods are not applicable to all lakes. An artificial neural network (ANN) model was created to represent the correlation between TP concentration and the spectral bands of Moderate Resolution Imaging Spectroradiometer (MODIS) images in different research areas. We investigated the causal inference under the potential outcome framework to analyze the sensitivity of each band with regard to the TP concentration of different lakes for the research of water characteristics. Our results show that the accuracy of the ANN-based TP concentration estimation, with R2 > 0.73, root mean squared error (RMSE) < 0.037 mg/L in Lake Okeechobee and R2 > 0.73, RMSE < 4.1 μg/L in Lake Erie, respectively, is much higher than traditional empirical methods, e.g., linear regression. We found that the sensitive bands of TP concentration in Lake Erie are blue bands, whereas the sensitive bands in Lake Okeechobee are green bands. Various TP concentration maps were drawn to indicate the distribution of TP concentration and its tendency to change. The maps show that the distribution of TP concentration closely corresponds to the shore land-use, and a high TP concentration corresponds to the latest algal blooms breakout. Our proposed approach shows good potential for the remote-sensing estimation of TP concentration for inland lakes. Identifying the sensitive bands not only help characterize the lakes, but will also help the researchers to further observe the TP concentration of specific lakes in an efficient way.

Mapping Water Quality Parameters in Urban Rivers from Hyperspectral Images Using a New Self-Adapting Selection of Multiple Artificial Neural Networks

Protection of water environments is an important part of overall environmental protection; hence, many people devote their efforts to monitoring and improving water quality. In this study, a self-adapting selection method of multiple artificial neural networks (ANNs) using hyperspectral remote sensing and ground-measured water quality data is proposed to quantitatively predict water quality parameters, including phosphorus, nitrogen, biochemical oxygen demand (BOD), chemical oxygen demand (COD), and chlorophyll a. Seventy-nine ground measured data samples are used as training data in the establishment of the proposed model, and 30 samples are used as testing data. The proposed method based on traditional ANNs of numerical prediction involves feature selection of bands, self-adapting selection based on multiple selection criteria, stepwise backtracking, and combined weighted correlation. Water quality parameters are estimated with coefficient of determination R 2 ranging from 0.93 (phosphorus) to 0.98 (nitrogen), which is higher than the value (0.7 to 0.8) obtained by traditional ANNs. MPAE (mean percent of absolute error) values ranging from 5% to 11% are used rather than root mean square error to evaluate the predicting precision of the proposed model because the magnitude of each water quality parameter considerably differs, thereby providing reasonable and interpretable results. Compared with other ANNs with backpropagation, this study proposes an auto-adapting method assisted by the above-mentioned methods to select the best model with all settings, such as the number of hidden layers, number of neurons in each hidden layer, choice of optimizer, and activation function. Different settings for ANNS with backpropagation are important to improve precision and compatibility for different data. Furthermore, the proposed method is applied to hyperspectral remote sensing images collected using an unmanned aerial vehicle for monitoring the water quality in the Shiqi River, Zhongshan City, Guangdong Province, China. Obtained results indicate the locations of pollution sources.