A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images
This article addresses the scarcity of labeled data in multitemporal remote sensing image analysis, and especially in the context of Chlorophyll-a (Chl-a) estimation for inland water quality assessment. We propose a multitask CNN architecture that can exploit unlabeled satellite imagery and that can...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/18 |
| _version_ | 1797497782888562688 |
|---|---|
| author | Melike Ilteralp Sema Ariman Erchan Aptoula |
| author_facet | Melike Ilteralp Sema Ariman Erchan Aptoula |
| author_sort | Melike Ilteralp |
| collection | DOAJ |
| description | This article addresses the scarcity of labeled data in multitemporal remote sensing image analysis, and especially in the context of Chlorophyll-a (Chl-a) estimation for inland water quality assessment. We propose a multitask CNN architecture that can exploit unlabeled satellite imagery and that can be generalized to other multitemporal remote sensing image analysis contexts where the target parameter exhibits seasonal fluctuations. Specifically, Chl-a estimation is set as the main task, and an unlabeled sample’s month classification is set as an auxiliary network task. The proposed approach is validated with multitemporal/spectral Sentinel-2 images of Lake Balik in Turkey using in situ measurements acquired during 2017–2019. We show that harnessing unlabeled data through multitask learning improves water quality estimation performance. |
| first_indexed | 2024-03-10T03:24:11Z |
| format | Article |
| id | doaj.art-900fc63ee2554ead8d77910dbffd95ef |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:24:11Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-900fc63ee2554ead8d77910dbffd95ef2023-11-23T12:11:51ZengMDPI AGRemote Sensing2072-42922021-12-011411810.3390/rs14010018A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing ImagesMelike Ilteralp0Sema Ariman1Erchan Aptoula2Department of Computer Engineering, Gebze Technical University, Kocaeli 41400, TurkeyDepartment of Meteorological Engineering, Samsun University, Samsun 55070, TurkeyInstitute of Information Technologies, Gebze Technical University, Kocaeli 41400, TurkeyThis article addresses the scarcity of labeled data in multitemporal remote sensing image analysis, and especially in the context of Chlorophyll-a (Chl-a) estimation for inland water quality assessment. We propose a multitask CNN architecture that can exploit unlabeled satellite imagery and that can be generalized to other multitemporal remote sensing image analysis contexts where the target parameter exhibits seasonal fluctuations. Specifically, Chl-a estimation is set as the main task, and an unlabeled sample’s month classification is set as an auxiliary network task. The proposed approach is validated with multitemporal/spectral Sentinel-2 images of Lake Balik in Turkey using in situ measurements acquired during 2017–2019. We show that harnessing unlabeled data through multitask learning improves water quality estimation performance.https://www.mdpi.com/2072-4292/14/1/18time series analysiswater qualityconvolutional neural networkregressionsemisupervised learning |
| spellingShingle | Melike Ilteralp Sema Ariman Erchan Aptoula A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images Remote Sensing time series analysis water quality convolutional neural network regression semisupervised learning |
| title | A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images |
| title_full | A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images |
| title_fullStr | A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images |
| title_full_unstemmed | A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images |
| title_short | A Deep Multitask Semisupervised Learning Approach for Chlorophyll-a Retrieval from Remote Sensing Images |
| title_sort | deep multitask semisupervised learning approach for chlorophyll a retrieval from remote sensing images |
| topic | time series analysis water quality convolutional neural network regression semisupervised learning |
| url | https://www.mdpi.com/2072-4292/14/1/18 |
| work_keys_str_mv | AT melikeilteralp adeepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages AT semaariman adeepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages AT erchanaptoula adeepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages AT melikeilteralp deepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages AT semaariman deepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages AT erchanaptoula deepmultitasksemisupervisedlearningapproachforchlorophyllaretrievalfromremotesensingimages |