Seamless retrievals of chlorophyll-a from Sentinel-2 (MSI) and Sentinel-3 (OLCI) in inland and coastal waters: A machine-learning approach

Pahlevan, Nima; Smith, Brandon; Schalles, John F.; Binding, Caren; Cao, Zhigang; Ma, Ronghua; Alikas, Krista; Kangro, Kersti; Gurlin, Daniela; Ha, Nguyen Thi Thu; Matsushita, Bunkei; Moses, Wesley J.; Greb, Steven R.; Lehmann, Moritz K.; Ondrusek, Michael; Oppelt, Natascha; Stumpf, Richard P.

doi:10.1016/j.rse.2019.111604

Cited by 327 publications

(225 citation statements)

References 97 publications

Supporting

Mentioning

165

Contrasting

Unclassified

Order By: Relevance

“…Another neural network algorithm known as mixture density network (MDN) was also used to retrieve chl-a concentration using Multispectral Instrument and Ocean and Land Color Instrument (OLCI) imagery in different water types. The result confirmed that the MDN method exhibits better performance than the empirical models [27]. Other machine learning methods have been found to be successful in the study of water quality parameter inversion, including hidden Markov models, self-organizing decision trees, and Gaussian process regression [2,15,[28][29][30][31][32][33][34].…”

Section: Introductionsupporting

confidence: 59%

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

Chen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionsupporting

confidence: 59%

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

Chen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The coefficients 0.2412, −2.0546, 1.1776, −0.5538, −0.4570 are, respectively, used for a 0 to a 4 (https://oceancolor.gsfc.nasa.gov/atbd/chlor_a/). The performance evaluation of Chl-a retrievals using Sentinel-2 data and OCx algorithms based on Acolite was found within the root mean squared logarithmic error (RMSLE) of 1.2-1.3 [39]. In another study, by employing OC3 algorithm for Indonesian seas, the RMSE of in situ vs. satellite Chl-a was found within the range of 0.04-0.05 [40], suggesting superior performance of satellite retrievals of Chl-a in aquatic systems.…”

Section: Chlorophyll-a Retrievalmentioning

confidence: 92%

Did the COVID-19 Lockdown-Induced Hydrological Residence Time Intensify the Primary Productivity in Lakes? Observational Results Based on Satellite Remote Sensing

Avtar

Kumar

Supe

et al. 2020

Water

View full text Add to dashboard Cite

The novel coronavirus pandemic (COVID-19) has brought countries around the world to a standstill in the early part of 2020. Several nations and territories around the world insisted their population stay indoors for practicing social distance in order to avoid infecting the disease. Consequently, industrial activities, businesses, and all modes of traveling have halted. On the other hand, the pollution level decreased ‘temporarily’ in our living environment. As fewer pollutants are supplied in to the hydrosphere, and human recreational activities are stopped completely during the lockdown period, we hypothesize that the hydrological residence time (HRT) has increased in the semi-enclosed or closed lake bodies, which can in turn increase the primary productivity. To validate our hypothesis, and to understand the effect of lockdown on primary productivity in aquatic systems, we quantitatively estimated the chlorophyll-a (Chl-a) concentrations in different lake bodies using established Chl-a retrieval algorithm. The Chl-a monitored using Landsat-8 and Sentinel-2 sensor in the lake bodies of Wuhan, China, showed an elevated concentration of Chl-a. In contrast, no significant changes in Chl-a are observed for Vembanad Lake in India. Further analysis of different geo-environments is necessary to validate the hypothesis.

show abstract

“…The largest errors are attributed to OLI-derived TSS products, owing to the absence of spectral information within the 700-800 nm region for approximating spectral b bp (Section 4.1.1). In essence, the overall performance of the MDN model in estimating b bp at each individual band is better when more relevant spectral features are supplied (Pahlevan et al, 2020), i.e., more accurate b bp is possible via MSI or MODIS than that through OLI (analysis not shown here). A secondary factor that may contribute to the reduced performance of the OLI model is that OLI's red channel, in contrast to other missions, does not fully capture Chla absorption peak at6 70 nm (Table 3).…”

Section: Extension To Other Satellite Missionsmentioning

confidence: 97%

“…Here, for Type II waters, using the synthetic data described in Section 2.1, we train a machine learning model termed the Mixture Density Network (MDN) for b bp retrievals (Section 3 and Table 1). This model has recently shown promise in retrieving Chla from multispectral images (Pahlevan et al, 2020). MDNs are a class of neural networks for modeling a mixture of Gaussian functions (Bishop, 1994).…”

Section: Machine Learning Approach: Mixture Density Networkmentioning

confidence: 99%

Robust algorithm for estimating total suspended solids (TSS) in inland and nearshore coastal waters

Balasubramanian

Pahlevan

Smith

et al. 2020

Remote Sensing of Environment

Self Cite

161

View full text Add to dashboard Cite

One of the challenging tasks in modern aquatic remote sensing is the retrieval of near-surface concentrations of Total Suspended Solids (TSS). This study aims to present a Statistical, inherent Optical property (IOP)-based, and muLti-conditional Inversion proceDure (SOLID) for enhanced retrievals of satellite-derived TSS under a wide range of in-water bio-optical conditions in rivers, lakes, estuaries, and coastal waters. In this study, using a large in situ database (N > 3500), the SOLID model is devised using a three-step procedure: (a) water-type classification of the input remote sensing reflectance (R rs), (b) retrieval of particulate backscattering (b bp) in the red or near-infrared (NIR) regions using semi-analytical, machine-learning, and empirical models, and (c) estimation of TSS from b bp via water-type-specific empirical models. Using an independent subset of our in situ data (N = 2729) with TSS ranging from 0.1 to 2626.8 [g/m 3 ], the SOLID model is thoroughly examined and compared against several state-of-the-art algorithms (Miller and McKee, 2004; Nechad et al., 2010; Novoa et al., 2017; Ondrusek et al., 2012; Petus et al., 2010). We show that SOLID outperforms all the other models to varying degrees, i.e.,from 10 to > 100%, depending on the statistical attributes (e.g., global versus water-type-specific metrics). For demonstration purposes, the model is implemented for images acquired by the MultiSpectral Imager aboard Sentinel-2A/B over the Chesapeake Bay, San-Francisco-Bay-Delta Estuary, Lake Okeechobee, and Lake Taihu. To enable generating consistent, multimission TSS products, its performance is further extended to, and evaluated for, other missions, such as the Ocean and Land Color Instrument (OLCI), Moderate Resolution Imaging Spectroradiometer (MODIS), Visible Infrared Imaging Radiometer Suite (VIIRS), and Operational Land Imager (OLI). Sensitivity analyses on uncertainties induced by the atmospheric correction indicate that 10% uncertainty in R rs leads to < 20% uncertainty in TSS retrievals from SOLID. While this study suggests that SOLID

show abstract

Seamless retrievals of chlorophyll-a from Sentinel-2 (MSI) and Sentinel-3 (OLCI) in inland and coastal waters: A machine-learning approach

Cited by 327 publications

References 97 publications

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

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

Did the COVID-19 Lockdown-Induced Hydrological Residence Time Intensify the Primary Productivity in Lakes? Observational Results Based on Satellite Remote Sensing

Robust algorithm for estimating total suspended solids (TSS) in inland and nearshore coastal waters

Contact Info

Product

Resources

About