2019
DOI: 10.1080/22797254.2019.1625726
|View full text |Cite
|
Sign up to set email alerts
|

Multispectral data by the new generation of high-resolution satellite sensors for mapping phytoplankton blooms in the Mar Piccolo of Taranto (Ionian Sea, southern Italy)

Abstract: The HR (High-Resolution) EO (Earth Observation) satellite systems Landsat 8 OLI and Sentinel 2 were tested for mapping the frequent phytoplankton blooms and Chl a distributions in the sea basin of the Mar Piccolo of Taranto (Ionian Sea, southern Italy), using the sea truth calibration data acquired in 2013. The data were atmospherically corrected for accounting of the aerosol load on optically complexes waters (case II). Various blue-green and additional spectral indices ratios, were then satisfyingly tested f… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 9 publications
(9 citation statements)
references
References 32 publications
0
9
0
Order By: Relevance
“…The upper section of sediment in the 2 nd basin has slightly (but significantly) less negative values, suggesting a relatively higher contribution of phytoplankton and/or macroalgae to the buried OC than the upper sections of sediments in the 1 st basin. Indeed, the satellite mapping invariably shows a higher concentration of phytoplankton during summer blooms (Borfecchia et al 2019 ) and denser green macroalgae coverage (Cibic et al 2016 ) in the 2 nd basin.…”
Section: Resultsmentioning
confidence: 99%
“…The upper section of sediment in the 2 nd basin has slightly (but significantly) less negative values, suggesting a relatively higher contribution of phytoplankton and/or macroalgae to the buried OC than the upper sections of sediments in the 1 st basin. Indeed, the satellite mapping invariably shows a higher concentration of phytoplankton during summer blooms (Borfecchia et al 2019 ) and denser green macroalgae coverage (Cibic et al 2016 ) in the 2 nd basin.…”
Section: Resultsmentioning
confidence: 99%
“…In our study, we conducted a comprehensive comparative analysis of various supervised machine learning techniques to assess their model performance (Figure 6a). The techniques examined include LR [29][30][31][32][33][34][35][36]45,46,51,65,75,, PLSR [22,27,[185][186][187][188][189], GPR [33,35,46,171,[190][191][192][193][194], GP [45,158,175,192,[195][196][197][198][199], SVM [22,25,26,[29][30][31][33][34][35]40,…”
Section: Machine or Deep Learning Model Choicementioning
confidence: 99%
“…SVMs, in particular, prove to be highly suitable for satellite-based water quality monitoring due to their exceptional capability to handle large datasets characterized by a high number of features. GP [158,[195][196][197][198][199], GPR [33,35,[190][191][192][193][194], and PLSR [22,27,[185][186][187][188][189] algorithms have received relatively less attention from researchers. Nonetheless, it is important to highlight that these methods have exhibited comparable and modest model performance relative to other algorithms commonly employed in the field of satellite-based water quality monitoring.…”
Section: Machine or Deep Learning Model Choicementioning
confidence: 99%
“…These RS techniques are recognized as effective tools for determining species diversity and distribution, for quantifying biomass and primary production, as obtained from the photosynthetically available radiation (PAR) and leaf area index (LAI), and for monitoring their changes over space and time in shallow waters [36,[38][39][40][41][42][43]. In any case, they must be combined with in situ measurements [44] of biophysical parameters of interest in order to support the proper calibration/validation of the EO data.…”
Section: Introductionmentioning
confidence: 99%