Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning
Seawater pH is a direct proxy of ocean acidification, and monitoring the global pH distribution and long-term series changes is critical to understanding the changes and responses of the marine ecology and environment under climate change. Owing to the lack of sufficient global-scale pH data and the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/10/2366 |
| _version_ | 1797495948992053248 |
|---|---|
| author | Zhiting Jiang Zigeng Song Yan Bai Xianqiang He Shujie Yu Siqi Zhang Fang Gong |
| author_facet | Zhiting Jiang Zigeng Song Yan Bai Xianqiang He Shujie Yu Siqi Zhang Fang Gong |
| author_sort | Zhiting Jiang |
| collection | DOAJ |
| description | Seawater pH is a direct proxy of ocean acidification, and monitoring the global pH distribution and long-term series changes is critical to understanding the changes and responses of the marine ecology and environment under climate change. Owing to the lack of sufficient global-scale pH data and the complex relationship between seawater pH and related environmental variables, generating time-series products of satellite-derived global sea surface pH poses a great challenge. In this study, we solved the problem of the lack of sufficient data for pH algorithm development by using the massive underway sea surface carbon dioxide partial pressure (<i>p</i>CO<sub>2</sub>) dataset to structure a large data volume of near <i>in situ</i> pH based on carbonate calculation between underway <i>p</i>CO<sub>2</sub> and calculated total alkalinity from sea surface salinity and relevant parameters. The remote sensing inversion model of pH was then constructed through this massive pH training dataset and machine learning methods. After several tests of machine learning methods and groups of input parameters, we chose the random forest model with longitude, latitude, sea surface temperature (SST), chlorophyll a (Chla), and Mixed layer depth (MLD) as model inputs with the best performance of correlation coefficient (R<sup>2</sup> = 0.96) and root mean squared error (RMSE = 0.008) in the training set and R<sup>2</sup> = 0.83 (RMSE = 0.017) in the testing set. The sensitivity analysis of the error variation induced by the uncertainty of SST and Chla (SST ≤ ±0.5 °C and Chla ≤ ±20%; RMSE<sub>SST</sub> ≤ 0.011 and RMSE<sub>Chla</sub> ≤ 0.009) indicated that our sea surface pH model had good robustness. Monthly average global sea surface pH products from 2004 to 2019 with a spatial resolution of 0.25° × 0.25° were produced based on the satellite-derived SST and Chla products and modeled MLD dataset. The pH model and products were validated using another independent station-measured pH dataset from the Global Ocean Data Analysis Project (GLODAP), showing good performance. With the time-series pH products, refined interannual variability and seasonal variability were presented, and trends of pH decline were found globally. Our study provides a new method of directly using remote sensing to invert pH instead of indirect calculation based on the construction of massive underway calculated pH data, which would be made useful by comparing it with satellite-derived <i>p</i>CO<sub>2</sub> products to understand the carbonate system change and the ocean ecological environments responding to the global change. |
| first_indexed | 2024-03-10T01:56:48Z |
| format | Article |
| id | doaj.art-54207f813c2545f4a727f630aa275ac4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:56:48Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-54207f813c2545f4a727f630aa275ac42023-11-23T12:55:03ZengMDPI AGRemote Sensing2072-42922022-05-011410236610.3390/rs14102366Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine LearningZhiting Jiang0Zigeng Song1Yan Bai2Xianqiang He3Shujie Yu4Siqi Zhang5Fang Gong6School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaSchool of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, ChinaSchool of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, ChinaSeawater pH is a direct proxy of ocean acidification, and monitoring the global pH distribution and long-term series changes is critical to understanding the changes and responses of the marine ecology and environment under climate change. Owing to the lack of sufficient global-scale pH data and the complex relationship between seawater pH and related environmental variables, generating time-series products of satellite-derived global sea surface pH poses a great challenge. In this study, we solved the problem of the lack of sufficient data for pH algorithm development by using the massive underway sea surface carbon dioxide partial pressure (<i>p</i>CO<sub>2</sub>) dataset to structure a large data volume of near <i>in situ</i> pH based on carbonate calculation between underway <i>p</i>CO<sub>2</sub> and calculated total alkalinity from sea surface salinity and relevant parameters. The remote sensing inversion model of pH was then constructed through this massive pH training dataset and machine learning methods. After several tests of machine learning methods and groups of input parameters, we chose the random forest model with longitude, latitude, sea surface temperature (SST), chlorophyll a (Chla), and Mixed layer depth (MLD) as model inputs with the best performance of correlation coefficient (R<sup>2</sup> = 0.96) and root mean squared error (RMSE = 0.008) in the training set and R<sup>2</sup> = 0.83 (RMSE = 0.017) in the testing set. The sensitivity analysis of the error variation induced by the uncertainty of SST and Chla (SST ≤ ±0.5 °C and Chla ≤ ±20%; RMSE<sub>SST</sub> ≤ 0.011 and RMSE<sub>Chla</sub> ≤ 0.009) indicated that our sea surface pH model had good robustness. Monthly average global sea surface pH products from 2004 to 2019 with a spatial resolution of 0.25° × 0.25° were produced based on the satellite-derived SST and Chla products and modeled MLD dataset. The pH model and products were validated using another independent station-measured pH dataset from the Global Ocean Data Analysis Project (GLODAP), showing good performance. With the time-series pH products, refined interannual variability and seasonal variability were presented, and trends of pH decline were found globally. Our study provides a new method of directly using remote sensing to invert pH instead of indirect calculation based on the construction of massive underway calculated pH data, which would be made useful by comparing it with satellite-derived <i>p</i>CO<sub>2</sub> products to understand the carbonate system change and the ocean ecological environments responding to the global change.https://www.mdpi.com/2072-4292/14/10/2366random forest modelglobal sea surface pHremote sensing inversiontotal alkalinitycarbonate system |
| spellingShingle | Zhiting Jiang Zigeng Song Yan Bai Xianqiang He Shujie Yu Siqi Zhang Fang Gong Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning Remote Sensing random forest model global sea surface pH remote sensing inversion total alkalinity carbonate system |
| title | Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning |
| title_full | Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning |
| title_fullStr | Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning |
| title_full_unstemmed | Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning |
| title_short | Remote Sensing of Global Sea Surface pH Based on Massive Underway Data and Machine Learning |
| title_sort | remote sensing of global sea surface ph based on massive underway data and machine learning |
| topic | random forest model global sea surface pH remote sensing inversion total alkalinity carbonate system |
| url | https://www.mdpi.com/2072-4292/14/10/2366 |
| work_keys_str_mv | AT zhitingjiang remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT zigengsong remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT yanbai remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT xianqianghe remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT shujieyu remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT siqizhang remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning AT fanggong remotesensingofglobalseasurfacephbasedonmassiveunderwaydataandmachinelearning |