Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images
Paddy rice is one of the main foods of the global population. To guarantee paddy rice acreage is essential to ensure food security. Currently, techniques for large-area paddy field mapping rely mainly on complex rule-based machine learning algorithms. But it is difficult for them to achieve an optim...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9987500/ |
| _version_ | 1797976539817574400 |
|---|---|
| author | Hui Wang Bo Zhao Panpan Tang Yuxiang Wang Haoming Wan Shi Bai Ronghao Wei |
| author_facet | Hui Wang Bo Zhao Panpan Tang Yuxiang Wang Haoming Wan Shi Bai Ronghao Wei |
| author_sort | Hui Wang |
| collection | DOAJ |
| description | Paddy rice is one of the main foods of the global population. To guarantee paddy rice acreage is essential to ensure food security. Currently, techniques for large-area paddy field mapping rely mainly on complex rule-based machine learning algorithms. But it is difficult for them to achieve an optimal balance between discriminability and robustness. In this article, we proposed a novel deep learning-based approach for large-scale paddy rice mapping, termed dual-path interactive network (DPIN). An annual time-series Sentinel-2 remote sensing images are used as data source. Taking several areas of interest over the middle and lower Yangtze River plain of China as experimental fields, our model achieves an F1-score of 91.22% on the test dataset, which is 1.09% higher than the existing state-of-the-art predictive model, and its inference speed is 1.18 times faster than it. DPIN-Lite is a lightweight variant of DPIN, and while keeping a competitive mapping accuracy, its inference speed is 1.91 times faster than the compared method (with the best score except for DPIN and DPIN-Lite). |
| first_indexed | 2024-04-11T04:53:35Z |
| format | Article |
| id | doaj.art-b3f2f9afaa9d4596979f4317c6a46255 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T04:53:35Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b3f2f9afaa9d4596979f4317c6a462552022-12-27T00:00:22ZengIEEEIEEE Access2169-35362022-01-011013258413259510.1109/ACCESS.2022.32295899987500Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 ImagesHui Wang0https://orcid.org/0000-0002-5569-2329Bo Zhao1https://orcid.org/0000-0002-6639-7448Panpan Tang2https://orcid.org/0000-0001-7464-1968Yuxiang Wang3Haoming Wan4Shi Bai5Ronghao Wei6Research Center of Big Data Technology, Nanhu Laboratory, Jiaxing, ChinaResearch Center of Big Data Technology, Nanhu Laboratory, Jiaxing, ChinaResearch Center of Big Data Technology, Nanhu Laboratory, Jiaxing, ChinaPIESAT Information Technology Company Ltd., Beijing, ChinaResearch Center of Big Data Technology, Nanhu Laboratory, Jiaxing, ChinaResearch Center of Big Data Technology, Nanhu Laboratory, Jiaxing, ChinaZhejiang Institute of Hydraulics & Estuary, Hangzhou, ChinaPaddy rice is one of the main foods of the global population. To guarantee paddy rice acreage is essential to ensure food security. Currently, techniques for large-area paddy field mapping rely mainly on complex rule-based machine learning algorithms. But it is difficult for them to achieve an optimal balance between discriminability and robustness. In this article, we proposed a novel deep learning-based approach for large-scale paddy rice mapping, termed dual-path interactive network (DPIN). An annual time-series Sentinel-2 remote sensing images are used as data source. Taking several areas of interest over the middle and lower Yangtze River plain of China as experimental fields, our model achieves an F1-score of 91.22% on the test dataset, which is 1.09% higher than the existing state-of-the-art predictive model, and its inference speed is 1.18 times faster than it. DPIN-Lite is a lightweight variant of DPIN, and while keeping a competitive mapping accuracy, its inference speed is 1.91 times faster than the compared method (with the best score except for DPIN and DPIN-Lite).https://ieeexplore.ieee.org/document/9987500/Paddy rice mappingdeep learning spatio-temporalsentinel-2 |
| spellingShingle | Hui Wang Bo Zhao Panpan Tang Yuxiang Wang Haoming Wan Shi Bai Ronghao Wei Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images IEEE Access Paddy rice mapping deep learning spatio-temporal sentinel-2 |
| title | Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images |
| title_full | Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images |
| title_fullStr | Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images |
| title_full_unstemmed | Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images |
| title_short | Paddy Rice Mapping Using a Dual-Path Spatio-Temporal Network Based on Annual Time-Series Sentinel-2 Images |
| title_sort | paddy rice mapping using a dual path spatio temporal network based on annual time series sentinel 2 images |
| topic | Paddy rice mapping deep learning spatio-temporal sentinel-2 |
| url | https://ieeexplore.ieee.org/document/9987500/ |
| work_keys_str_mv | AT huiwang paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT bozhao paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT panpantang paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT yuxiangwang paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT haomingwan paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT shibai paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images AT ronghaowei paddyricemappingusingadualpathspatiotemporalnetworkbasedonannualtimeseriessentinel2images |