Drone-borne sensing of major and accessory pigments in algae using deep learning modeling
Intensive algal blooms increasingly degrade the inland water quality. Hence, this study aimed to analyze the algal phenomena quantitatively and qualitatively using synoptic monitoring, algal pigment analysis, and a deep learning model. Water surface reflectance was measured using field monitoring an...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2022.2027120 |
| _version_ | 1797679029772353536 |
|---|---|
| author | JongCheol Pyo Seok Min Hong Jiyi Jang Sanghun Park Jongkwan Park Jae Hoon Noh Kyung Hwa Cho |
| author_facet | JongCheol Pyo Seok Min Hong Jiyi Jang Sanghun Park Jongkwan Park Jae Hoon Noh Kyung Hwa Cho |
| author_sort | JongCheol Pyo |
| collection | DOAJ |
| description | Intensive algal blooms increasingly degrade the inland water quality. Hence, this study aimed to analyze the algal phenomena quantitatively and qualitatively using synoptic monitoring, algal pigment analysis, and a deep learning model. Water surface reflectance was measured using field monitoring and drone hyperspectral image sensing. The algal experiment conducted on the water samples provided data on major pigments including chlorophyll-a and phycocyanin, accessory pigments including lutein, fucoxanthin, and zeaxanthin, and absorption coefficients. Based on the reflectance and absorption coefficient spectral inputs, a one-dimensional convolutional neural network (1D-CNN) was developed to estimate the concentrations of the major and minor pigments. The 1D-CNN could model periodic trends of chlorophyll-a, phycocyanin, lutein, fucoxanthin, and zeaxanthin compared to the observed ones, with R2 values of 0.87, 0.71, 0.76, 0.78, and 0.74, respectively. In addition, major and secondary pigment maps developed by applying the trained 1D-CNN model to the processed drone hyperspectral image inputs successfully provided spatial information regarding the spots of interest. The model provided explicit algal biomass information using the estimated major pigments and implicit taxonomical information using accessory pigments such as green algae, diatoms, and cyanobacteria. Therefore, we provide strong evidence of the extendibility of deep learning models for analyzing various algal pigments to gain a better understanding of algal blooms. |
| first_indexed | 2024-03-11T23:08:28Z |
| format | Article |
| id | doaj.art-7ad78e1fd90b43b9903cfe9449b6969a |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:08:28Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-7ad78e1fd90b43b9903cfe9449b6969a2023-09-21T12:43:08ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262022-12-0159131033210.1080/15481603.2022.20271202027120Drone-borne sensing of major and accessory pigments in algae using deep learning modelingJongCheol Pyo0Seok Min Hong1Jiyi Jang2Sanghun Park3Jongkwan Park4Jae Hoon Noh5Kyung Hwa Cho6Korea Environment InstituteUlsan National Institute of Science and TechnologyUlsan National Institute of Science and TechnologyUlsan National Institute of Science and TechnologyChangwon National UniversityKorea Institute of Ocean Science and TechnologyUlsan National Institute of Science and TechnologyIntensive algal blooms increasingly degrade the inland water quality. Hence, this study aimed to analyze the algal phenomena quantitatively and qualitatively using synoptic monitoring, algal pigment analysis, and a deep learning model. Water surface reflectance was measured using field monitoring and drone hyperspectral image sensing. The algal experiment conducted on the water samples provided data on major pigments including chlorophyll-a and phycocyanin, accessory pigments including lutein, fucoxanthin, and zeaxanthin, and absorption coefficients. Based on the reflectance and absorption coefficient spectral inputs, a one-dimensional convolutional neural network (1D-CNN) was developed to estimate the concentrations of the major and minor pigments. The 1D-CNN could model periodic trends of chlorophyll-a, phycocyanin, lutein, fucoxanthin, and zeaxanthin compared to the observed ones, with R2 values of 0.87, 0.71, 0.76, 0.78, and 0.74, respectively. In addition, major and secondary pigment maps developed by applying the trained 1D-CNN model to the processed drone hyperspectral image inputs successfully provided spatial information regarding the spots of interest. The model provided explicit algal biomass information using the estimated major pigments and implicit taxonomical information using accessory pigments such as green algae, diatoms, and cyanobacteria. Therefore, we provide strong evidence of the extendibility of deep learning models for analyzing various algal pigments to gain a better understanding of algal blooms.http://dx.doi.org/10.1080/15481603.2022.2027120algal bloomconvolutional neural networkdrone-borne sensinghyperspectral imagesaccessory pigments |
| spellingShingle | JongCheol Pyo Seok Min Hong Jiyi Jang Sanghun Park Jongkwan Park Jae Hoon Noh Kyung Hwa Cho Drone-borne sensing of major and accessory pigments in algae using deep learning modeling GIScience & Remote Sensing algal bloom convolutional neural network drone-borne sensing hyperspectral images accessory pigments |
| title | Drone-borne sensing of major and accessory pigments in algae using deep learning modeling |
| title_full | Drone-borne sensing of major and accessory pigments in algae using deep learning modeling |
| title_fullStr | Drone-borne sensing of major and accessory pigments in algae using deep learning modeling |
| title_full_unstemmed | Drone-borne sensing of major and accessory pigments in algae using deep learning modeling |
| title_short | Drone-borne sensing of major and accessory pigments in algae using deep learning modeling |
| title_sort | drone borne sensing of major and accessory pigments in algae using deep learning modeling |
| topic | algal bloom convolutional neural network drone-borne sensing hyperspectral images accessory pigments |
| url | http://dx.doi.org/10.1080/15481603.2022.2027120 |
| work_keys_str_mv | AT jongcheolpyo dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT seokminhong dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT jiyijang dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT sanghunpark dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT jongkwanpark dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT jaehoonnoh dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling AT kyunghwacho dronebornesensingofmajorandaccessorypigmentsinalgaeusingdeeplearningmodeling |