Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification
Crop classification is a crucial prerequisite for the collection of agricultural statistics, efficient crop management, biodiversity control, the design of agricultural policy, and food security. Crops are characterized by significant change during the growing season, and this information can be use...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-03-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243422000095 |
| _version_ | 1797961283746660352 |
|---|---|
| author | Edyta Woźniak Marcin Rybicki Wlodek Kofman Sebastian Aleksandrowicz Cezary Wojtkowski Stanisław Lewiński Jędrzej Bojanowski Jan Musiał Tomasz Milewski Przemysław Slesiński Artur Łączyński |
| author_facet | Edyta Woźniak Marcin Rybicki Wlodek Kofman Sebastian Aleksandrowicz Cezary Wojtkowski Stanisław Lewiński Jędrzej Bojanowski Jan Musiał Tomasz Milewski Przemysław Slesiński Artur Łączyński |
| author_sort | Edyta Woźniak |
| collection | DOAJ |
| description | Crop classification is a crucial prerequisite for the collection of agricultural statistics, efficient crop management, biodiversity control, the design of agricultural policy, and food security. Crops are characterized by significant change during the growing season, and this information can be used to improve classification accuracy. However, capturing variation in vegetation cover requires a reliable source of valid data. Sentinel-1 radar images are a good candidate, as they supply information about Earth’s surface every six days, independent of weather and light conditions. In this paper, we present a method for crop classification based on radar polarimetry. We propose a set of multi-temporal indices derived from time series Sentinel-1 images that aim to characterize crop phenology. A big data, object-oriented classification technique is developed and tested on 16 crop types for the whole of Poland. Our analysis found that overall accuracy varied (regionally) from 86.36 to 89.13% in 2019, and from 85.95 to 89.81% in 2020. F1 scores for individual crops varied from 0.73 to 0.99, and the use of our multi-temporal phenological indices increased F1 scores by about 0.14 compared to calculations using only basic parameters. Results obtained for the whole country demonstrate the efficacy of the method and its resistance to environmental conditions. |
| first_indexed | 2024-04-11T00:56:35Z |
| format | Article |
| id | doaj.art-7530a7b29dc8428d8287dc861dc97619 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-11T00:56:35Z |
| publishDate | 2022-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-7530a7b29dc8428d8287dc861dc976192023-01-05T04:31:03ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322022-03-01107102683Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classificationEdyta Woźniak0Marcin Rybicki1Wlodek Kofman2Sebastian Aleksandrowicz3Cezary Wojtkowski4Stanisław Lewiński5Jędrzej Bojanowski6Jan Musiał7Tomasz Milewski8Przemysław Slesiński9Artur Łączyński10Centrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, Poland; Corresponding author at: Bartycka 18A, 00-716 Warszawa, Poland.Centrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, PolandCentrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, Poland; Institut de Planetologie et d’Astrophysique de Grenoble, CNRS/UGA, Grenoble, FranceCentrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, PolandCentrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, PolandCentrum Badań Kosmicznych Polskiej Akademii Nauk (CBK PAN), Warsaw, PolandRemote Sensing Centre, Institute of Geodesy and Cartography, Warsaw, PolandRemote Sensing Centre, Institute of Geodesy and Cartography, Warsaw, PolandStatistics Poland, Warsaw, PolandStatistics Poland, Warsaw, PolandStatistics Poland, Warsaw, PolandCrop classification is a crucial prerequisite for the collection of agricultural statistics, efficient crop management, biodiversity control, the design of agricultural policy, and food security. Crops are characterized by significant change during the growing season, and this information can be used to improve classification accuracy. However, capturing variation in vegetation cover requires a reliable source of valid data. Sentinel-1 radar images are a good candidate, as they supply information about Earth’s surface every six days, independent of weather and light conditions. In this paper, we present a method for crop classification based on radar polarimetry. We propose a set of multi-temporal indices derived from time series Sentinel-1 images that aim to characterize crop phenology. A big data, object-oriented classification technique is developed and tested on 16 crop types for the whole of Poland. Our analysis found that overall accuracy varied (regionally) from 86.36 to 89.13% in 2019, and from 85.95 to 89.81% in 2020. F1 scores for individual crops varied from 0.73 to 0.99, and the use of our multi-temporal phenological indices increased F1 scores by about 0.14 compared to calculations using only basic parameters. Results obtained for the whole country demonstrate the efficacy of the method and its resistance to environmental conditions.http://www.sciencedirect.com/science/article/pii/S0303243422000095Phenological indicesRadar polarimetryCrop classificationSentinel-1Agriculture |
| spellingShingle | Edyta Woźniak Marcin Rybicki Wlodek Kofman Sebastian Aleksandrowicz Cezary Wojtkowski Stanisław Lewiński Jędrzej Bojanowski Jan Musiał Tomasz Milewski Przemysław Slesiński Artur Łączyński Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification International Journal of Applied Earth Observations and Geoinformation Phenological indices Radar polarimetry Crop classification Sentinel-1 Agriculture |
| title | Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification |
| title_full | Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification |
| title_fullStr | Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification |
| title_full_unstemmed | Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification |
| title_short | Multi-temporal phenological indices derived from time series Sentinel-1 images to country-wide crop classification |
| title_sort | multi temporal phenological indices derived from time series sentinel 1 images to country wide crop classification |
| topic | Phenological indices Radar polarimetry Crop classification Sentinel-1 Agriculture |
| url | http://www.sciencedirect.com/science/article/pii/S0303243422000095 |
| work_keys_str_mv | AT edytawozniak multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT marcinrybicki multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT wlodekkofman multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT sebastianaleksandrowicz multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT cezarywojtkowski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT stanisławlewinski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT jedrzejbojanowski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT janmusiał multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT tomaszmilewski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT przemysławslesinski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification AT arturłaczynski multitemporalphenologicalindicesderivedfromtimeseriessentinel1imagestocountrywidecropclassification |