Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models
Sea ice motion (SIM) plays a crucial role in setting the distribution of the ice cover in the Arctic. Limited by images’ spatial resolution and tracking algorithms, challenges exist in obtaining coastal sea ice motion (SIM) based on passive microwave satellite sensors. In this study, we developed a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/3/581 |
| _version_ | 1797318244451745792 |
|---|---|
| author | Linxin Zhang Qian Shi Matti Leppäranta Jiping Liu Qinghua Yang |
| author_facet | Linxin Zhang Qian Shi Matti Leppäranta Jiping Liu Qinghua Yang |
| author_sort | Linxin Zhang |
| collection | DOAJ |
| description | Sea ice motion (SIM) plays a crucial role in setting the distribution of the ice cover in the Arctic. Limited by images’ spatial resolution and tracking algorithms, challenges exist in obtaining coastal sea ice motion (SIM) based on passive microwave satellite sensors. In this study, we developed a method based on random forest (RF) models to obtain Arctic SIM in winter by incorporating wind field and coastal geographic location information. These random forest models were trained using Synthetic Aperture Radar (SAR) SIM data. Our results show good consistency with SIM data retrieved from satellite imagery and buoy observations. With respect to the SAR data, compared with SIM estimated with RF model training using reanalysis surface wind, the results by additional coastal information input had a lower root mean square error (RMSE) and a higher correlation coefficient by 31% and 14% relative improvement, respectively. The latter SIM result also showed a better performance for magnitude, especially within 100 km of the coastline in the north of the Canadian Arctic Archipelago. In addition, the influence of coastline on SIM is quantified through variable importance calculation, at 22% and 28% importance of all RF variables for east and north SIM components, respectively. These results indicate the great potential of RF models for estimating SIM over the whole Arctic Ocean in winter. |
| first_indexed | 2024-03-08T03:49:36Z |
| format | Article |
| id | doaj.art-382a70fa468541cf839e7b1d9fdbd81c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T03:49:36Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-382a70fa468541cf839e7b1d9fdbd81c2024-02-09T15:21:33ZengMDPI AGRemote Sensing2072-42922024-02-0116358110.3390/rs16030581Estimating Winter Arctic Sea Ice Motion Based on Random Forest ModelsLinxin Zhang0Qian Shi1Matti Leppäranta2Jiping Liu3Qinghua Yang4School of Atmospheric Sciences, Sun Yat-sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, ChinaSchool of Atmospheric Sciences, Sun Yat-sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, ChinaInstitute for Atmospheric and Earth System Research, University of Helsinki, 00014 Helsinki, FinlandSchool of Atmospheric Sciences, Sun Yat-sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, ChinaSchool of Atmospheric Sciences, Sun Yat-sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, ChinaSea ice motion (SIM) plays a crucial role in setting the distribution of the ice cover in the Arctic. Limited by images’ spatial resolution and tracking algorithms, challenges exist in obtaining coastal sea ice motion (SIM) based on passive microwave satellite sensors. In this study, we developed a method based on random forest (RF) models to obtain Arctic SIM in winter by incorporating wind field and coastal geographic location information. These random forest models were trained using Synthetic Aperture Radar (SAR) SIM data. Our results show good consistency with SIM data retrieved from satellite imagery and buoy observations. With respect to the SAR data, compared with SIM estimated with RF model training using reanalysis surface wind, the results by additional coastal information input had a lower root mean square error (RMSE) and a higher correlation coefficient by 31% and 14% relative improvement, respectively. The latter SIM result also showed a better performance for magnitude, especially within 100 km of the coastline in the north of the Canadian Arctic Archipelago. In addition, the influence of coastline on SIM is quantified through variable importance calculation, at 22% and 28% importance of all RF variables for east and north SIM components, respectively. These results indicate the great potential of RF models for estimating SIM over the whole Arctic Ocean in winter.https://www.mdpi.com/2072-4292/16/3/581sea ice motionrandom forestcryosphere |
| spellingShingle | Linxin Zhang Qian Shi Matti Leppäranta Jiping Liu Qinghua Yang Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models Remote Sensing sea ice motion random forest cryosphere |
| title | Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models |
| title_full | Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models |
| title_fullStr | Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models |
| title_full_unstemmed | Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models |
| title_short | Estimating Winter Arctic Sea Ice Motion Based on Random Forest Models |
| title_sort | estimating winter arctic sea ice motion based on random forest models |
| topic | sea ice motion random forest cryosphere |
| url | https://www.mdpi.com/2072-4292/16/3/581 |
| work_keys_str_mv | AT linxinzhang estimatingwinterarcticseaicemotionbasedonrandomforestmodels AT qianshi estimatingwinterarcticseaicemotionbasedonrandomforestmodels AT mattilepparanta estimatingwinterarcticseaicemotionbasedonrandomforestmodels AT jipingliu estimatingwinterarcticseaicemotionbasedonrandomforestmodels AT qinghuayang estimatingwinterarcticseaicemotionbasedonrandomforestmodels |