Remote Sensing of Water Quality Parameters over Lake Balaton by Using Sentinel-3 OLCI

Abstract

The Ocean and Land Color Instrument (OLCI) onboard Sentinel 3A satellite was launched in February 2016. Level 2 (L2) products have been available for the public since July 2017. OLCI provides the possibility to monitor aquatic environments on 300 m spatial resolution on 9 spectral bands, which allows to retrieve detailed information about the water quality of various type of waters. It has only been a short time since L2 data became accessible, therefore validation of these products from different aquatic environments are required. In this work we study the possibility to use S3 OLCI L2 products to monitor an optically highly complex shallow lake. We test S3 OLCI-derived Chlorophyll-a (Chl-a), Colored Dissolved Organic Matter (CDOM) and Total Suspended Matter (TSM) for complex waters against in situ measurements over Lake Balaton in 2017. In addition, we tested the machine learning Gaussian process regression model, trained locally as a potential candidate to retrieve water quality parameters. We applied the automatic model selection algorithm to select the combination and number of spectral bands for the given water quality parameter to train the Gaussian Process Regression model. Lake Balaton represents different types of aquatic environments (eutrophic, mesotrophic and oligotrophic), hence being able to establish a model to monitor water quality by using S3 OLCI products might allow the generalization of the methodology.

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

“…This is retrieved by using a Neural Network (NN) algorithm [24,25]. Although this might provide an alternative solution which is able to estimate Chl-a concentration in complex waters, validation experiments have shown that the approach is sensitive to TSM, and often results in erroneous Chl-a estimates [26].…”

“…In the work [26], the Automatic Model Selection Algorithm (AMSA) was applied, which was introduced in [40] to a complexity-diverse aquatic environment. AMSA combines feature ranking and selection with ML regression methods to determine the number and combination of spectral bands and/or features needed to obtain the strongest performance for a given aquatic environment.…”

“…Hence, applying the approach to an aquatic environment representing a wide range of optical complexities, might allow determination of a model, which can be generalized and optimized to complex high northern latitude waters. The ML GPR model was established on Lake Balaton, and was shown to improve Chl-a retrieval from S3 OLCI Rrs data [26] in the lake. The ML GPR Balaton model takes as input only three Rrs values, measured on bands centered at 442.5, 665, and 681.25 nm as input to estimate Chl-a concentration.…”

“…The regression power of the method decreases, when additional OLCI Rrs bands are added. Using all the available OLCI bands in the ML GPR Balaton model resulted in a Normalized Root Mean Squared Error (NRMSE) of 0.11, a bias of 2.25 and Pearson correlation coefficient of 0.79, whereas using only the three selected bands as inputs resulted in a NRMSE of 0.10, a bias of 2.12 and a Pearson correlation coefficient of 0.83) [26]. This suggests that using only these bands in complexity-diverse waters might provide sufficient spectral information to estimate Chl-a concentration.…”

Innovative Water Quality and Ecology Monitoring Using Underwater Unmanned Vehicles: Field Applications, Challenges and Feedback from Water Managers

“…While there has been a rapid development of unmanned tools and sensors for environmental monitoring and inspections in recent years [26][27][28][29][30], it is not yet clear if the use of these methods by water managers in their daily practice, and the extent to which they can replace or complement existing techniques, should be further explored. There still seems to be technical, social, legislative and operational limitations and barriers for the large-scale use of this technology.…”