Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks
Algal blooms are a common problem in inland waters, which raise growing awareness on monitoring lakes’ conditions. The on site monitoring is expensive and requires large human resources efforts. This work proposes remote monitoring techniques using satellite images and machine learning al...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10436679/ |
| _version_ | 1797293323328684032 |
|---|---|
| author | Dalia Grendaite Linas Petkevicius |
| author_facet | Dalia Grendaite Linas Petkevicius |
| author_sort | Dalia Grendaite |
| collection | DOAJ |
| description | Algal blooms are a common problem in inland waters, which raise growing awareness on monitoring lakes’ conditions. The on site monitoring is expensive and requires large human resources efforts. This work proposes remote monitoring techniques using satellite images and machine learning algorithms to predict chlorophyll <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> concentration in water bodies and identify algal blooms. The training and test dataset used in this study includes diverse range of lakes in Baltic countries. The lake spectral features obtained from Sentinel-2 satellite images are used as predictors for proposed deep neural network models. The prediction of chlorophyll <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> concentration with MAE 7.97 mg/<inline-formula> <tex-math notation="LaTeX">$\text{m}^{3}$ </tex-math></inline-formula> and bloom vs. non-bloom classification with 71.6 % accuracy was achieved. The use of Bèzier curves for smoothing the point-wise prediction is proposed for identification of algal bloom characteristics: the bloom start date, end date, and duration. The results showed lake type impact on the blooming time. The experimental data and code are released with paper. |
| first_indexed | 2024-03-07T20:11:10Z |
| format | Article |
| id | doaj.art-b672a38ddd724c92bf485c3e0da0b837 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T20:11:10Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b672a38ddd724c92bf485c3e0da0b8372024-02-28T00:00:59ZengIEEEIEEE Access2169-35362024-01-0112279732798810.1109/ACCESS.2024.336649110436679Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural NetworksDalia Grendaite0https://orcid.org/0000-0002-9611-5421Linas Petkevicius1https://orcid.org/0000-0003-2416-0431Institute of Geosciences, Vilnius University, Vilnius, LithuaniaInstitute of Computer Science, Vilnius University, Vilnius, LithuaniaAlgal blooms are a common problem in inland waters, which raise growing awareness on monitoring lakes’ conditions. The on site monitoring is expensive and requires large human resources efforts. This work proposes remote monitoring techniques using satellite images and machine learning algorithms to predict chlorophyll <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> concentration in water bodies and identify algal blooms. The training and test dataset used in this study includes diverse range of lakes in Baltic countries. The lake spectral features obtained from Sentinel-2 satellite images are used as predictors for proposed deep neural network models. The prediction of chlorophyll <inline-formula> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> concentration with MAE 7.97 mg/<inline-formula> <tex-math notation="LaTeX">$\text{m}^{3}$ </tex-math></inline-formula> and bloom vs. non-bloom classification with 71.6 % accuracy was achieved. The use of Bèzier curves for smoothing the point-wise prediction is proposed for identification of algal bloom characteristics: the bloom start date, end date, and duration. The results showed lake type impact on the blooming time. The experimental data and code are released with paper.https://ieeexplore.ieee.org/document/10436679/Satellite image processingchlorophyll α predictiondeep neural networksremote sensingBèzier curves |
| spellingShingle | Dalia Grendaite Linas Petkevicius Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks IEEE Access Satellite image processing chlorophyll α prediction deep neural networks remote sensing Bèzier curves |
| title | Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks |
| title_full | Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks |
| title_fullStr | Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks |
| title_full_unstemmed | Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks |
| title_short | Identification of Algal Blooms in Lakes in the Baltic States Using Sentinel-2 Data and Artificial Neural Networks |
| title_sort | identification of algal blooms in lakes in the baltic states using sentinel 2 data and artificial neural networks |
| topic | Satellite image processing chlorophyll α prediction deep neural networks remote sensing Bèzier curves |
| url | https://ieeexplore.ieee.org/document/10436679/ |
| work_keys_str_mv | AT daliagrendaite identificationofalgalbloomsinlakesinthebalticstatesusingsentinel2dataandartificialneuralnetworks AT linaspetkevicius identificationofalgalbloomsinlakesinthebalticstatesusingsentinel2dataandartificialneuralnetworks |