Cropland classification using Sentinel-1 time series: Methodological performance and prediction uncertainty assessment

Erkki Tomppo, Oleg Antropov, Jaan Praks

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Multinomial logistic regression was tested as an optional method. The Overall Accuracies (OA) varied depending on the number of species included in the classification, and whether all or not field parcels were included. OA with nine species groups was 72% when all parcels were included, 81% when the parcels area threshold (for incorporating parcels into classification) was 0.5 ha, and around 90% when the threshold was 4 ha. The OA gradually increased when adding extra Sentinel-1 scenes up until the early August, and the initial scenes were acquired in early June or mid-May. After that, only minor improvements in the crop recognition accuracy were noted. The ik-NN method gave greater overall accuracies than the logistic regression analysis with all data combinations tested. The width of the 95% confidence intervals with ik-NN for the estimate of the probability of the species with the largest probability on an individual parcel varied depending on the species, the area threshold of the parcel and the number of the Sentinel-1 scenes used. The results ranged between 0.06-0.08 units (6-8% points) for the most common species when the Sentinel-1 scenes were between 1 June and 12 August. The results were well-received by the authorities and encourage further research to continue the study towards an operational method in which the space-borne SAR data are a part of the information chain.

Original languageEnglish
Article number2480
JournalRemote Sensing
Volume11
Issue number21
DOIs
Publication statusPublished - 1 Nov 2019
MoE publication typeA1 Journal article-refereed

Fingerprint

time series
prediction
crop
logistics
synthetic aperture radar
genetic algorithm
confidence interval
regression analysis
growing season
polarization
method
geometry
methodology

Keywords

  • Boreal region
  • C-band
  • Classification
  • Crops
  • ESA Sentinel-1
  • Genetic algorithm
  • K-NN
  • Multinomial logistic regression
  • Synthetic aperture radar

Cite this

@article{bcb15bdb20b848b292fc3892ae199139,
title = "Cropland classification using Sentinel-1 time series: Methodological performance and prediction uncertainty assessment",
abstract = "Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Multinomial logistic regression was tested as an optional method. The Overall Accuracies (OA) varied depending on the number of species included in the classification, and whether all or not field parcels were included. OA with nine species groups was 72{\%} when all parcels were included, 81{\%} when the parcels area threshold (for incorporating parcels into classification) was 0.5 ha, and around 90{\%} when the threshold was 4 ha. The OA gradually increased when adding extra Sentinel-1 scenes up until the early August, and the initial scenes were acquired in early June or mid-May. After that, only minor improvements in the crop recognition accuracy were noted. The ik-NN method gave greater overall accuracies than the logistic regression analysis with all data combinations tested. The width of the 95{\%} confidence intervals with ik-NN for the estimate of the probability of the species with the largest probability on an individual parcel varied depending on the species, the area threshold of the parcel and the number of the Sentinel-1 scenes used. The results ranged between 0.06-0.08 units (6-8{\%} points) for the most common species when the Sentinel-1 scenes were between 1 June and 12 August. The results were well-received by the authorities and encourage further research to continue the study towards an operational method in which the space-borne SAR data are a part of the information chain.",
keywords = "Boreal region, C-band, Classification, Crops, ESA Sentinel-1, Genetic algorithm, K-NN, Multinomial logistic regression, Synthetic aperture radar",
author = "Erkki Tomppo and Oleg Antropov and Jaan Praks",
year = "2019",
month = "11",
day = "1",
doi = "10.3390/rs11212480",
language = "English",
volume = "11",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI",
number = "21",

}

Cropland classification using Sentinel-1 time series : Methodological performance and prediction uncertainty assessment. / Tomppo, Erkki; Antropov, Oleg; Praks, Jaan.

In: Remote Sensing, Vol. 11, No. 21, 2480, 01.11.2019.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Cropland classification using Sentinel-1 time series

T2 - Methodological performance and prediction uncertainty assessment

AU - Tomppo, Erkki

AU - Antropov, Oleg

AU - Praks, Jaan

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Multinomial logistic regression was tested as an optional method. The Overall Accuracies (OA) varied depending on the number of species included in the classification, and whether all or not field parcels were included. OA with nine species groups was 72% when all parcels were included, 81% when the parcels area threshold (for incorporating parcels into classification) was 0.5 ha, and around 90% when the threshold was 4 ha. The OA gradually increased when adding extra Sentinel-1 scenes up until the early August, and the initial scenes were acquired in early June or mid-May. After that, only minor improvements in the crop recognition accuracy were noted. The ik-NN method gave greater overall accuracies than the logistic regression analysis with all data combinations tested. The width of the 95% confidence intervals with ik-NN for the estimate of the probability of the species with the largest probability on an individual parcel varied depending on the species, the area threshold of the parcel and the number of the Sentinel-1 scenes used. The results ranged between 0.06-0.08 units (6-8% points) for the most common species when the Sentinel-1 scenes were between 1 June and 12 August. The results were well-received by the authorities and encourage further research to continue the study towards an operational method in which the space-borne SAR data are a part of the information chain.

AB - Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Multinomial logistic regression was tested as an optional method. The Overall Accuracies (OA) varied depending on the number of species included in the classification, and whether all or not field parcels were included. OA with nine species groups was 72% when all parcels were included, 81% when the parcels area threshold (for incorporating parcels into classification) was 0.5 ha, and around 90% when the threshold was 4 ha. The OA gradually increased when adding extra Sentinel-1 scenes up until the early August, and the initial scenes were acquired in early June or mid-May. After that, only minor improvements in the crop recognition accuracy were noted. The ik-NN method gave greater overall accuracies than the logistic regression analysis with all data combinations tested. The width of the 95% confidence intervals with ik-NN for the estimate of the probability of the species with the largest probability on an individual parcel varied depending on the species, the area threshold of the parcel and the number of the Sentinel-1 scenes used. The results ranged between 0.06-0.08 units (6-8% points) for the most common species when the Sentinel-1 scenes were between 1 June and 12 August. The results were well-received by the authorities and encourage further research to continue the study towards an operational method in which the space-borne SAR data are a part of the information chain.

KW - Boreal region

KW - C-band

KW - Classification

KW - Crops

KW - ESA Sentinel-1

KW - Genetic algorithm

KW - K-NN

KW - Multinomial logistic regression

KW - Synthetic aperture radar

UR - http://www.scopus.com/inward/record.url?scp=85074631318&partnerID=8YFLogxK

U2 - 10.3390/rs11212480

DO - 10.3390/rs11212480

M3 - Article

AN - SCOPUS:85074631318

VL - 11

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 21

M1 - 2480

ER -