An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping
This paper proposes an open-boundary locally weighted dynamic time warping (OLWDTW) method using MODIS Normalized Difference Vegetation Index (NDVI) time-series data for cropland recognition. The method solves the problem of flexible planting times for crops in Southeast Asia, which has sufficient t...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-02-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2220-9964/7/2/75 |
| _version_ | 1811202318592376832 |
|---|---|
| author | Xudong Guan Gaohuan Liu Chong Huang Xuelian Meng Qingsheng Liu Chunsheng Wu Xarapat Ablat Zhuoran Chen Qiang Wang |
| author_facet | Xudong Guan Gaohuan Liu Chong Huang Xuelian Meng Qingsheng Liu Chunsheng Wu Xarapat Ablat Zhuoran Chen Qiang Wang |
| author_sort | Xudong Guan |
| collection | DOAJ |
| description | This paper proposes an open-boundary locally weighted dynamic time warping (OLWDTW) method using MODIS Normalized Difference Vegetation Index (NDVI) time-series data for cropland recognition. The method solves the problem of flexible planting times for crops in Southeast Asia, which has sufficient thermal and water conditions. For NDVI time series starting at the beginning of the year and terminating at the end of the year, the method can separate the non-growing season cycle and growing season cycle for crops. The non-growing season cycle may provide some useful information for crop recognition, such as soil conditions. However, the shape of the growing season’s NDVI time series for crops is the key to separating cropland from other land cover types because the shape contains all of the crop growth information. The principle of the OLWDTW method is to enhance the effects of the growing season cycle on the NDVI time series by adding a local weight to the growing season when comparing the similarity of time series based on the open-boundary dynamic time warping (DTW) method. Experiments with two satellite datasets located near the Khorat Plateau in the Lower Mekong Basin validate that OLWDTW effectively improves the precision of cropland recognition compared to a non-weighted open-boundary DTW method in terms of overall accuracy. The method’s classification accuracy on cropland exceeds the non-weighted open-boundary DTW by 5–7%. In future studies, an open-boundary self-adaption locally weighted DTW and a more effective combination rule for different crop types should be explored for the method’s best performance and highest extraction accuracy for cropland. |
| first_indexed | 2024-04-12T02:36:41Z |
| format | Article |
| id | doaj.art-ab936ca3a7f348a5ac11903bb1168ab9 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-04-12T02:36:41Z |
| publishDate | 2018-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-ab936ca3a7f348a5ac11903bb1168ab92022-12-22T03:51:30ZengMDPI AGISPRS International Journal of Geo-Information2220-99642018-02-01727510.3390/ijgi7020075ijgi7020075An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland MappingXudong Guan0Gaohuan Liu1Chong Huang2Xuelian Meng3Qingsheng Liu4Chunsheng Wu5Xarapat Ablat6Zhuoran Chen7Qiang Wang8State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaDepartment of Geography and Anthropology, Louisiana State University, Baton Rouge, LA 70803, USAState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaThis paper proposes an open-boundary locally weighted dynamic time warping (OLWDTW) method using MODIS Normalized Difference Vegetation Index (NDVI) time-series data for cropland recognition. The method solves the problem of flexible planting times for crops in Southeast Asia, which has sufficient thermal and water conditions. For NDVI time series starting at the beginning of the year and terminating at the end of the year, the method can separate the non-growing season cycle and growing season cycle for crops. The non-growing season cycle may provide some useful information for crop recognition, such as soil conditions. However, the shape of the growing season’s NDVI time series for crops is the key to separating cropland from other land cover types because the shape contains all of the crop growth information. The principle of the OLWDTW method is to enhance the effects of the growing season cycle on the NDVI time series by adding a local weight to the growing season when comparing the similarity of time series based on the open-boundary dynamic time warping (DTW) method. Experiments with two satellite datasets located near the Khorat Plateau in the Lower Mekong Basin validate that OLWDTW effectively improves the precision of cropland recognition compared to a non-weighted open-boundary DTW method in terms of overall accuracy. The method’s classification accuracy on cropland exceeds the non-weighted open-boundary DTW by 5–7%. In future studies, an open-boundary self-adaption locally weighted DTW and a more effective combination rule for different crop types should be explored for the method’s best performance and highest extraction accuracy for cropland.http://www.mdpi.com/2220-9964/7/2/75dynamic time warping (DTW)remote sensingLower Mekong BasinMODIStime seriescropscroplandclassification |
| spellingShingle | Xudong Guan Gaohuan Liu Chong Huang Xuelian Meng Qingsheng Liu Chunsheng Wu Xarapat Ablat Zhuoran Chen Qiang Wang An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping ISPRS International Journal of Geo-Information dynamic time warping (DTW) remote sensing Lower Mekong Basin MODIS time series crops cropland classification |
| title | An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping |
| title_full | An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping |
| title_fullStr | An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping |
| title_full_unstemmed | An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping |
| title_short | An Open-Boundary Locally Weighted Dynamic Time Warping Method for Cropland Mapping |
| title_sort | open boundary locally weighted dynamic time warping method for cropland mapping |
| topic | dynamic time warping (DTW) remote sensing Lower Mekong Basin MODIS time series crops cropland classification |
| url | http://www.mdpi.com/2220-9964/7/2/75 |
| work_keys_str_mv | AT xudongguan anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT gaohuanliu anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT chonghuang anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT xuelianmeng anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT qingshengliu anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT chunshengwu anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT xarapatablat anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT zhuoranchen anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT qiangwang anopenboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT xudongguan openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT gaohuanliu openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT chonghuang openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT xuelianmeng openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT qingshengliu openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT chunshengwu openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT xarapatablat openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT zhuoranchen openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping AT qiangwang openboundarylocallyweighteddynamictimewarpingmethodforcroplandmapping |