An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea
ABSTRACTThis paper presents a novel approach for predicting the water quality indicator – Secchi disk depth (ZSD). ZSD indirectly reflects water clarity and serves as a proxy for other quality parameters. This study utilizes Deep Neural Network (DNN) trained on satellite remote sensing and measured...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-01-01
|
| Series: | Big Earth Data |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/20964471.2023.2273058 |
| _version_ | 1827307486526308352 |
|---|---|
| author | Antonia Ivanda Ljiljana Šerić Dušan Žagar Krištof Oštir |
| author_facet | Antonia Ivanda Ljiljana Šerić Dušan Žagar Krištof Oštir |
| author_sort | Antonia Ivanda |
| collection | DOAJ |
| description | ABSTRACTThis paper presents a novel approach for predicting the water quality indicator – Secchi disk depth (ZSD). ZSD indirectly reflects water clarity and serves as a proxy for other quality parameters. This study utilizes Deep Neural Network (DNN) trained on satellite remote sensing and measured data from three sources: two datasets obtained from official agencies in Croatia and Slovenia, and one citizen science data source, all covering the northern coastal region of the Adriatic Sea. The proposed model uses 1D Convolutional Neural Network (CNN) in the spectral dimension to predict ZSD. The model’s performance indicates a strong fit to the observed data, proving capability of 1D-CNN to capture changes in water transparency. On the test dataset, the model achieved a high R-squared value of 0.890, a low root mean squared error (RMSE) of 0.023 and mean absolute error (MAE) of 0.014. These results demonstrate that employing a 1D-CNN in the spectral dimension of Sentinel-3 OLCI data is an effective approach for predicting water quality. These findings have significant implications for monitoring ZSD in coastal areas. By integrating diverse data sources and leveraging advanced machine learning algorithms, a more accurate and comprehensive assessment of water quality can be achieved. |
| first_indexed | 2024-04-24T18:40:56Z |
| format | Article |
| id | doaj.art-6061434f944a424ea106c3df5c053e46 |
| institution | Directory Open Access Journal |
| issn | 2096-4471 2574-5417 |
| language | English |
| last_indexed | 2024-04-24T18:40:56Z |
| publishDate | 2024-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Big Earth Data |
| spelling | doaj.art-6061434f944a424ea106c3df5c053e462024-03-27T13:07:26ZengTaylor & Francis GroupBig Earth Data2096-44712574-54172024-01-01818211410.1080/20964471.2023.2273058An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic SeaAntonia Ivanda0Ljiljana Šerić1Dušan Žagar2Krištof Oštir3Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, Split, CroatiaFaculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, Split, CroatiaFaculty of Civil and Geodetic Engineering, University of Ljubljana, Ljubljana, SloveniaFaculty of Civil and Geodetic Engineering, University of Ljubljana, Ljubljana, SloveniaABSTRACTThis paper presents a novel approach for predicting the water quality indicator – Secchi disk depth (ZSD). ZSD indirectly reflects water clarity and serves as a proxy for other quality parameters. This study utilizes Deep Neural Network (DNN) trained on satellite remote sensing and measured data from three sources: two datasets obtained from official agencies in Croatia and Slovenia, and one citizen science data source, all covering the northern coastal region of the Adriatic Sea. The proposed model uses 1D Convolutional Neural Network (CNN) in the spectral dimension to predict ZSD. The model’s performance indicates a strong fit to the observed data, proving capability of 1D-CNN to capture changes in water transparency. On the test dataset, the model achieved a high R-squared value of 0.890, a low root mean squared error (RMSE) of 0.023 and mean absolute error (MAE) of 0.014. These results demonstrate that employing a 1D-CNN in the spectral dimension of Sentinel-3 OLCI data is an effective approach for predicting water quality. These findings have significant implications for monitoring ZSD in coastal areas. By integrating diverse data sources and leveraging advanced machine learning algorithms, a more accurate and comprehensive assessment of water quality can be achieved.https://www.tandfonline.com/doi/10.1080/20964471.2023.2273058SecchiSentinel-3OLCI1D-CNNAdriatic sea |
| spellingShingle | Antonia Ivanda Ljiljana Šerić Dušan Žagar Krištof Oštir An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea Big Earth Data Secchi Sentinel-3 OLCI 1D-CNN Adriatic sea |
| title | An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea |
| title_full | An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea |
| title_fullStr | An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea |
| title_full_unstemmed | An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea |
| title_short | An application of 1D convolution and deep learning to remote sensing modelling of Secchi depth in the northern Adriatic Sea |
| title_sort | application of 1d convolution and deep learning to remote sensing modelling of secchi depth in the northern adriatic sea |
| topic | Secchi Sentinel-3 OLCI 1D-CNN Adriatic sea |
| url | https://www.tandfonline.com/doi/10.1080/20964471.2023.2273058 |
| work_keys_str_mv | AT antoniaivanda anapplicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT ljiljanaseric anapplicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT dusanzagar anapplicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT kristofostir anapplicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT antoniaivanda applicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT ljiljanaseric applicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT dusanzagar applicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea AT kristofostir applicationof1dconvolutionanddeeplearningtoremotesensingmodellingofsecchidepthinthenorthernadriaticsea |