Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping
Crop mapping is vital in ensuring food production security and informing governmental decision-making. The satellite-normalized difference vegetation index (NDVI) obtained during periods of vigorous crop growth is important for crop species identification. Sentinel-2 images with spatial resolutions...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/16/2/235 |
_version_ | 1797342642313363456 |
---|---|
author | Wenfang Zhan Feng Luo Heng Luo Junli Li Yongchuang Wu Zhixiang Yin Yanlan Wu Penghai Wu |
author_facet | Wenfang Zhan Feng Luo Heng Luo Junli Li Yongchuang Wu Zhixiang Yin Yanlan Wu Penghai Wu |
author_sort | Wenfang Zhan |
collection | DOAJ |
description | Crop mapping is vital in ensuring food production security and informing governmental decision-making. The satellite-normalized difference vegetation index (NDVI) obtained during periods of vigorous crop growth is important for crop species identification. Sentinel-2 images with spatial resolutions of 10, 20, and 60 m are widely used in crop mapping. However, the images obtained during periods of vigorous crop growth are often covered by clouds. In contrast, time-series moderate-resolution imaging spectrometer (MODIS) images can usually capture crop phenology but with coarse resolution. Therefore, a time-series-based spatiotemporal fusion network (TSSTFN) was designed to generate TSSTFN-NDVI during critical phenological periods for finer-scale crop mapping. This network leverages multi-temporal MODIS-Sentinel-2 NDVI pairs from previous years as a reference to enhance the precision of crop mapping. The long short-term memory module was used to acquire data about the time-series change pattern to achieve this. The UNet structure was employed to manage the spatial mapping relationship between MODIS and Sentinel-2 images. The time distribution of the image sequences in different years was inconsistent, and time alignment strategies were used to process the reference data. The results demonstrate that incorporating the predicted critical phenological period NDVI consistently yields better crop classification performance. Moreover, the predicted NDVI trained with time-consistent data achieved a higher classification accuracy than the predicted NDVI trained with the original NDVI. |
first_indexed | 2024-03-08T10:36:13Z |
format | Article |
id | doaj.art-3b88d1e74922470b9d506a8cdf11b1c4 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-08T10:36:13Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-3b88d1e74922470b9d506a8cdf11b1c42024-01-26T18:16:05ZengMDPI AGRemote Sensing2072-42922024-01-0116223510.3390/rs16020235Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type MappingWenfang Zhan0Feng Luo1Heng Luo2Junli Li3Yongchuang Wu4Zhixiang Yin5Yanlan Wu6Penghai Wu7School of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaCCCC Second Highway Consultants Co., Ltd., Wuhan 430056, ChinaGuangxi Zhuang Automomous Region Institute of Natural Resources Remote Sensing, Nanning 530023, ChinaSchool of Resources and Environment, Anhui Agricultural University, Hefei 230036, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaInformation Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601, ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei 230601, ChinaCrop mapping is vital in ensuring food production security and informing governmental decision-making. The satellite-normalized difference vegetation index (NDVI) obtained during periods of vigorous crop growth is important for crop species identification. Sentinel-2 images with spatial resolutions of 10, 20, and 60 m are widely used in crop mapping. However, the images obtained during periods of vigorous crop growth are often covered by clouds. In contrast, time-series moderate-resolution imaging spectrometer (MODIS) images can usually capture crop phenology but with coarse resolution. Therefore, a time-series-based spatiotemporal fusion network (TSSTFN) was designed to generate TSSTFN-NDVI during critical phenological periods for finer-scale crop mapping. This network leverages multi-temporal MODIS-Sentinel-2 NDVI pairs from previous years as a reference to enhance the precision of crop mapping. The long short-term memory module was used to acquire data about the time-series change pattern to achieve this. The UNet structure was employed to manage the spatial mapping relationship between MODIS and Sentinel-2 images. The time distribution of the image sequences in different years was inconsistent, and time alignment strategies were used to process the reference data. The results demonstrate that incorporating the predicted critical phenological period NDVI consistently yields better crop classification performance. Moreover, the predicted NDVI trained with time-consistent data achieved a higher classification accuracy than the predicted NDVI trained with the original NDVI.https://www.mdpi.com/2072-4292/16/2/235crop mappingSentinel-2 NDVIMODIS NDVIdeep learningspatiotemporal fusion |
spellingShingle | Wenfang Zhan Feng Luo Heng Luo Junli Li Yongchuang Wu Zhixiang Yin Yanlan Wu Penghai Wu Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping Remote Sensing crop mapping Sentinel-2 NDVI MODIS NDVI deep learning spatiotemporal fusion |
title | Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping |
title_full | Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping |
title_fullStr | Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping |
title_full_unstemmed | Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping |
title_short | Time-Series-Based Spatiotemporal Fusion Network for Improving Crop Type Mapping |
title_sort | time series based spatiotemporal fusion network for improving crop type mapping |
topic | crop mapping Sentinel-2 NDVI MODIS NDVI deep learning spatiotemporal fusion |
url | https://www.mdpi.com/2072-4292/16/2/235 |
work_keys_str_mv | AT wenfangzhan timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT fengluo timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT hengluo timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT junlili timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT yongchuangwu timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT zhixiangyin timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT yanlanwu timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping AT penghaiwu timeseriesbasedspatiotemporalfusionnetworkforimprovingcroptypemapping |