A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter
High-quality leaf area index (LAI) data is essential for regional and global ecology, climate and environment research. However, there are still many quality problems in the continuity of current LAI time series products. Here we developed a new comprehensive three-step reconstruction method (GANSG)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243421003408 |
| _version_ | 1818549826790359040 |
|---|---|
| author | Anqi Huang Runping Shen Wenli Di Huimin Han |
| author_facet | Anqi Huang Runping Shen Wenli Di Huimin Han |
| author_sort | Anqi Huang |
| collection | DOAJ |
| description | High-quality leaf area index (LAI) data is essential for regional and global ecology, climate and environment research. However, there are still many quality problems in the continuity of current LAI time series products. Here we developed a new comprehensive three-step reconstruction method (GANSG) for satellite-retrieved LAI time series data based on generative adversarial network, improving the Savitzky-Golay (S-G) filter and median absolute deviation filter. We applied GANSG to the reconstruction of MODIS LAI data in China from 2001 to 2019. The reconstruction results show that the new method based on the unsupervised deep learning framework has an advantage in interpolating low-quality LAI with high precision. The new method can better retain high-quality pixel information to smoothen the interpolated LAI time series by improving the traditional S-G filter. Compared with the five other methods, including the adaptive S-G filter, double logistic, asymmetric Gaussian, modified temporal spatial filter and spatial temporal S-G filter, qualitative analysis showed the new method has a more resilient ability to handle the continuous loss of high-quality pixels and identify the phenological features of biomes. Quantitative analysis based on station observation showed that the new method performs best among the other three methods, with the optimal correlation coefficient of 0.84 relative to station observation and the lowest root mean square error of 0.71 m2/m2. |
| first_indexed | 2024-12-12T08:38:20Z |
| format | Article |
| id | doaj.art-0638a68aa0c24d95884b4b601b133c88 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-12-12T08:38:20Z |
| publishDate | 2021-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-0638a68aa0c24d95884b4b601b133c882022-12-22T00:30:51ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322021-12-01105102633A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filterAnqi Huang0Runping Shen1Wenli Di2Huimin Han3School of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCorresponding author at: School of Geographical Sciences, Nanjing University of Information Science and Technology, NO.219 Ningliu Road, Nanjing 210044, China.; School of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Geographical Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaHigh-quality leaf area index (LAI) data is essential for regional and global ecology, climate and environment research. However, there are still many quality problems in the continuity of current LAI time series products. Here we developed a new comprehensive three-step reconstruction method (GANSG) for satellite-retrieved LAI time series data based on generative adversarial network, improving the Savitzky-Golay (S-G) filter and median absolute deviation filter. We applied GANSG to the reconstruction of MODIS LAI data in China from 2001 to 2019. The reconstruction results show that the new method based on the unsupervised deep learning framework has an advantage in interpolating low-quality LAI with high precision. The new method can better retain high-quality pixel information to smoothen the interpolated LAI time series by improving the traditional S-G filter. Compared with the five other methods, including the adaptive S-G filter, double logistic, asymmetric Gaussian, modified temporal spatial filter and spatial temporal S-G filter, qualitative analysis showed the new method has a more resilient ability to handle the continuous loss of high-quality pixels and identify the phenological features of biomes. Quantitative analysis based on station observation showed that the new method performs best among the other three methods, with the optimal correlation coefficient of 0.84 relative to station observation and the lowest root mean square error of 0.71 m2/m2.http://www.sciencedirect.com/science/article/pii/S0303243421003408Remote sensingLeaf area indexTime seriesData reconstructionGenerative adversarial network |
| spellingShingle | Anqi Huang Runping Shen Wenli Di Huimin Han A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter International Journal of Applied Earth Observations and Geoinformation Remote sensing Leaf area index Time series Data reconstruction Generative adversarial network |
| title | A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter |
| title_full | A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter |
| title_fullStr | A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter |
| title_full_unstemmed | A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter |
| title_short | A methodology to reconstruct LAI time series data based on generative adversarial network and improved Savitzky-Golay filter |
| title_sort | methodology to reconstruct lai time series data based on generative adversarial network and improved savitzky golay filter |
| topic | Remote sensing Leaf area index Time series Data reconstruction Generative adversarial network |
| url | http://www.sciencedirect.com/science/article/pii/S0303243421003408 |
| work_keys_str_mv | AT anqihuang amethodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT runpingshen amethodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT wenlidi amethodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT huiminhan amethodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT anqihuang methodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT runpingshen methodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT wenlidi methodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter AT huiminhan methodologytoreconstructlaitimeseriesdatabasedongenerativeadversarialnetworkandimprovedsavitzkygolayfilter |