Print This Page

JECAM | Joint Experiment for Crop Assessment and Monitoring

Ukraine

Project Overview

Crop identification and acreage estimation: Estimates are required end-of-season. Early in-season estimates for winter crops (winter wheat and rapeseed) are desirable.

Crop biophysical variables (LAI, fCover, biomass). LAI estimates are going to be assimilated into semi-empirical local yield models. It is desirable to have estimates on a weekly basis through the whole growing season.

 

Yield Prediction and Forecasting

The mapping resolution is 5-10 m for field level estimates and is 30-60 m for regional mapping. The timeliness of the data is with regards to growing season. Field data can be delivered two weeks after acquisitions. Partial data analysis will be done at the end of growing season.


Project Reports

Reports:

2017 Site Progress Report

2016 Site Progress Report

2015 Site Progress Report

2014 Site Progress Report

Papers in peer reviewed journals:

  1. Skakun, S., Kussul, N., Shelestov, A. Y., Lavreniuk, M., & Kussul, O. (2016). Efficiency assessment of multitemporal C-band Radarsat-2 intensity and Landsat-8 surface reflectance satellite imagery for crop classification in Ukraine. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3712-3719.
     
  2. Ghazaryan, G., Dubovyk, O., Kussul, N., & Menz, G. (2016). Towards an Improved Environmental Understanding of Land Surface Dynamics in Ukraine Based on Multi-Source Remote Sensing Time-Series Datasets from 1982 to 2013. Remote Sensing, 8(8), 617.
     
  3. Waldner, F., De Abelleyra, D., Verón, S. R., Zhang, M., Wu, B., Plotnikov, D., ... & Le Maire, G. (2016). Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity. International Journal of Remote Sensing, 37(14), 3196-3231.
     
  4. Lavreniuk, M., Kussul, N., Shelestov, A., Yailymov, B., Oliinyk, T., & Kosteckyi, A. (2016, July). Validation methods for regional retrospective high resolution land cover for Ukraine. In Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International (pp. 4502-4505). IEEE.
     
  5. Kussul, N., Lavreniuk, M., Shelestov, A., & Yailymov, B. (2016, July). Along the season crop classification in Ukraine based on time series of optical and SAR images using ensemble of neural network classifiers. In Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International (pp. 7145-7148). IEEE.
     
  6. Kussul, N., Shelestov, A., Lavreniuk, M., Butko, I., & Skakun, S. (2016, July). Deep learning approach for large scale land cover mapping based on remote sensing data fusion. In Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International (pp. 198-201). IEEE.
     
  7. Kussul, N., Lemoine, G., Gallego, F. J., Skakun, S. V., Lavreniuk, M., & Shelestov, A. Y. (2016). Parcel-Based Crop Classification in Ukraine Using Landsat-8 Data and Sentinel-1A Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(6), 2500-2508.
     
  8. Skakun, S., Kussul, N., Shelestov, A., & Kussul, O. (2016). The use of satellite data for agriculture drought risk quantification in Ukraine. Geomatics, Natural Hazards and Risk, 7(3), 901-917.
     
  9. Waldner, F., Fritz, S., Di Gregorio, A., Plotnikov, D., Bartalev, S., Kussul, N., ... & Löw, F. (2016). A unified cropland layer at 250 m for global agriculture monitoring. Data, 1(1), 3.
     
  10. Kussul, N. N., Lavreniuk, N. S., Shelestov, A. Y., Yailymov, B. Y., & Butko, I. N. (2016). Land Cover Changes Analysis Based on Deep Machine Learning Technique. Journal of Automation and Information Sciences, 48(5).
     
  11. Efficiency Assessment of Multitemporal C-Band Radarsat-2 Intensity and Landsat-8 Surface Reflectance Satellite Imagery for Crop Classification in Ukraine
    S.Skakun, N.Kussul, A.Y. Shelestov, M.Lavreniuk, O. Kussul
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. - 2015. - DOI: 10.1109/JSTARS.2015.2454297.
     
  12. Regional scale crop mapping using multi-temporal satellite imagery 
    N. Kussul, S. Skakun, A. Shelestov, M. Lavreniuk, B. Yailymov, O. Kussul
    International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences. – 2015. - P. 45-52.
     
  13. Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine A. Kolotii, N. Kussul, A. Shelestov, S. Skakun, B. Yailymov, R. Basarab, M. Lavreniuk, T. Oliinyk, V. Ostapenko International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences. – 2015. - P. 39-44.
     
  14. Mapping of biophysical parameters based on high resolution EO imagery for JECAM test site in Ukraine Andrii Shelestov, Andrii Kolotii, Fernando Camacho, Sergii Skakun, Olga Kussul, Mykola Lavreniuk, Oleksandr Kostetsky Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International - P. 1733-1736.
     
  15. Parcel based classification for agricultural mapping and monitoring using multi-temporal satellite image sequences Nataliia Kussul, Guido Lemoine, Javier Gallego, Sergii Skakun, Mykola Lavreniuk. Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International - P. 165-158.
     
  16. Geospatial intelligence and data fusion techniques for sustainable development problems N.Kussul, A.Shelestov, R.Basarab, S.Skakun, O.Kussul, M. Lavreniuk. 11th International Conference on ICT in Education, Research and Industrial Applications: Integration, Harmonization and Knowledge Transfer, ICTERI 2015 (14-16 May 2015, Lviv, Ukraine). - 2015. - Vol.1356. - P. 196-203.
     
  17. Building a Data Set over 12 Globally Distributed Sites to Support the Development of Agriculture Monitoring Applications with Sentinel-2. Bontemps, Sophie; Arias, Marcela; Cara, Cosmin; Dedieu, Gerard; Guzzonato, Eric; Hagolle, Olivier; Inglada, Jordi; Matton, Nicolas; Morin, David; Popescu, Ramona; Rabaute, Thierry; Savinaud, Mickael; Sepulcre, Guadalupe; Valero, Silvia; Ahmad, Ijaz; Begue, Agnes; Bingfang, Wu; de Abelleyra, Diego; Diarra, Alhousseine; Dupuy, Stephane; French, Andrew; ul Hassan Akhtar, Ibrar; Kussul, Nataliia; Lebourgeois, Valentine; Le Page, Michel; Newby, Terrence; Savin, Igor; Veron, Santiago R.; Koetz, Benjamin; Defourny, Pierre. Remote Sens. 2015, 7, 16062-16090.
     
  18. The use of satellite data for agriculture drought risk quantification in Ukraine 
    Sergii Skakun, Nataliia Kussul, Andrii Shelestov, Olga Kussul
    Geomatics, Natural Hazards and Risk. – 2015. – DOI: 10.1080/19475705.2015.1016555 – P. 1-18.
     
  19. Gallego F.J., Kussul N., Skakun S., Kravchenko O., Shelestov A., and Kussul O., (2014) "Efficiency assessment of using satellite data for crop area estimation in Ukraine", International Journal of Applied Earth Observation and Geoinformation, Vol. 29, pp. 22–30. (http://dx.doi.org/10.1016/j.jag.2013.12.013)
     
  20. Kogan, F., Kussul, N., Adamenko, T., Skakun, S., Kravchenko, O., Kryvobok, O., Shelestov, A., Kolotii, A., Kussul, O. & Lavrenyuk, A., (2013) “Winter wheat yield forecasting in Ukraine based on Earth observation, meteorological data and biophysical models”, International Journal of Applied Earth Observation and Geoinformation, vol. 23, pp. 192-203. (http://dx.doi.org/10.1016/j.jag.2013.01.002)
     
  21. Shelestov, A.Yu., Kravchenko, A.N., Skakun, S.V., Voloshin, S.V., Kussul, N.N., (2013). "Geospatial information system for agricultural monitoring", Cybernetics and Systems Analysis, Volume 49, Issue 1, pp 124-132. (http://dx.doi.org/10.1007/s10559-013-9492-5)
     
  22. Kussul N., Skakun S., Kravchenko O., Shelestov A., Gallego F. J., Kussul  O., (2013) “Application of satellite optical and SAR images for crop mapping and area estimation in Ukraine”, International Journal "Information Technologies & Knowledge", Vol.7, No. 3, pp. 203-210
     
  23. Kussul N., Skakun S., Shelestov A., Kravchenko O., Kussul  O. (2013) “Crop clasification in Ukraine using satellite optical and SAR images”, Models&Analyses, N 2, pp. 118-128.
     
  24. Kussul, N.; Skakun, S.; Shelestov, A.; Kussul, O., "The use of satellite SAR imagery to crop classification in Ukraine within JECAM project," 2014 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp.1497-1500, 13-18 July 2014. doi: 10.1109/IGARSS.2014.6946721
     
  25. Kussul, N.; Kolotii, A.; Skakun, S.; Shelestov, A.; Kussul, O.; Oliynuk, T., "Efficiency estimation of different satellite data usage for winter wheat yield forecasting in Ukraine," 2014 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 5080-5082, 13-18 July 2014. doi: 10.1109/IGARSS.2014.6947639.

Presentations:

  1. Andrii Shelestov, “Large scale crop mapping in Ukraine using Google Earth Engine”, AGU Fall Meeting, 12-16 of December, 2016, San Francisco, USA
     
  2. Andrii Kolotii, “Sen2-Agri country level demonstration for Ukraine”, AGU Fall Meeting, 12-16 of December, 2016, San Francisco, USA
     
  3. Andrii Kolotii, “Essential climatic variables estimation with satellite imagery”, AGU Fall Meeting, 12-16 of December, 2016, San Francisco, USA
     
  4. Mykola Lavreniuk, “Validation methods for regional retrospective high resolution land cover for Ukraine”, IGARSS 2016 IEEE International Geoscience and Remote Sensing Symposium was held on 10-15 of July 2016 in Beijing, China.
     
  5. Nataliia Kussul, “Along the season crop classification in Ukraine based on time series of optical and SAR images using ensemble of neural network classifiers”, IGARSS 2016 IEEE International Geoscience and Remote Sensing Symposium was held on 10-15 of July 2016 in Beijing, China.
     
  6. Nataliia Kussul,  “Deep learning approach for large scale land cover mapping based on remote sensing data fusion”, IGARSS 2016 IEEE International Geoscience and Remote Sensing Symposium was held on 10-15 of July 2016 in Beijing, China.
     
  7. Mykola Lavreniuk, “Crop Classification Strategies Using Hybrid Sentinel-1, Sentinel-2 and Landsat-8 Data Series in Ukraine”, ESA Living Planet Symposium, 9-13 of May, 2016, Prague, Czech Republic
     
  8. Nataliia Kussul, “Large Scale Land Cover Mapping Using Data Fusion and Deep Learning Approach in Ukraine”, 6th EARSeL SIG LU/LC & 2nd EARSeL LULC/NASA LCLUC Workshop, 6-7 May, 2016, Prague, Czech Republic
     
  9. M. Lavreniuk, “Regional scale crop mapping using multi-temporal satellite imagery”, 36th International Symposium on Remote Sensing of Environment – ISRSE-36, 11-15 of May, 2015 in Berlin, Germany.
     
  10. A. Shelestov, “Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine”, 36th International Symposium on Remote Sensing of Environment – ISRSE-36, 11-15 of May, 2015 in Berlin, Germany.
     
  11. N. Kussul, “PARCEL BASED CLASSIFICATION FOR AGRICULTURAL MAPPING AND MONITORING USING MULTI-TEMPORAL SATELLITE IMAGE SEQUENCES “, IGARSS 2015 IEEE International Geoscience and Remote Sensing Symposium was held on 26-31 of July 2015 in Milan, Italy.
     
  12. A. Shelestov, “Mapping of biophysical parameters based on high resolution EO imagery for JECAM test site in Ukraine”, IGARSS 2015 IEEE International Geoscience and Remote Sensing Symposium was held on 26-31 of July 2015 in Milan, Italy.
     
  13. M. Lavreniuk, “Regional retrospective high resolution land cover for Ukraine: methodology and results”, IGARSS 2015 IEEE International Geoscience and Remote Sensing Symposium was held on 26-31 of July 2015 in Milan, Italy.
     
  14. N. Kussul, «Satellite Based Crop Classification and Field Area Estimation in Ukraine”, 8-th GEOSS Asia-Pacific Symposium, 9-11 of September 2015, People's Republic of China.
     
  15. A. Shelestov, “Geospatial Solutions for Data Sharing within WDS and JECAM”, 8-th GEOSS Asia-Pacific Symposium, 9-11 of September 2015, People's Republic of China.
     
  16. N. Kussul, “Satellite monitoring products at national and regional levels”, Joint Workshop on Information Needs in Crop Monitoring, 22-23 of October 2015, Kyiv, Ukraine.
     
  17. A. Shelestov, “Kyiv JECAM Site Progress (Ukraine)”, Annual JECAM Meeting, 15-16 of November 2015, Brussels, Belgium.
     
  18. Kussul N., EO for agriculture monitoring in Ukraine within international initiatives GLAM and JECAM, presented at GEO European Projects’ Workshop-7, 15-16 May 2013, Barcelona, Spain.
     
  19. Kussul N., Agricultural monitoring satellite‐based data fusion: experience and developments of Space Research Institute, Ukraine, presented at Regional workshop "Satellite Monitoring of Agricultural Lands in Northern Eurasia“, October 28-31, 2013, Moscow, Russia.
     
  20. Shelestov A., Ukrainian JECAM test site, presented at Regional workshop "Satellite Monitoring of Agricultural Lands in Northern Eurasia“, October 28-31, 2013, Moscow, Russia.
     
  21. Kussul N., et al., Assessment of Relative Efficiency of using MODIS Data to Winter Wheat Yield Forecasting in Ukraine, presented at IGARSS 2013, July 25, 2013, Melbourne, Australia.
     
  22. Kussul N., et al., Agricultural Satellite Monitoring and Crop Yield Forecasting in Ukraine, presented at Crop Yield Forecasting in South East Europe Workshop, 30-31 May, 2013, Skopje, Macedonia.
     
  23. Kussul N., et al., Natural Disasters Risk Assessment at UN-SPIDER Regional Support Office in Ukraine, presented at CEOS WGISS-36, May 16-19, 2013, Frascati, Italy, ESA/ESRIN. 

Implementation Plans

In situ:

Two types of ground data were collected (within ESA Sen2-Agri Project):

 

Along the roads:

About 7689 fields were observed for major crop and non-crop classes (Fig. 6). Distribution of the crop classes is shown in Table 1 (Training set) and Table 2 (Validation set).

Table 1 Training set structure (in JECAM Guidelines nomenclature)


 

Table 2. Validation set structure (in JECAM Guidelines nomenclature)


Figure 6. Crop mapping datasets distribution

 

 


 

These data were used for crop type map production over JECAM test site in Ukraine and crop type map for the territory of Ukraine (within ESA Sen2-Agri Project).

 

Observations of biophysical parameters:

7 field campaigns to characterize the vegetation biophysical parameters at the Pshenichne test site were carried out (Table 3):

In total 121 sample was collected (winter wheat – 42 ESU, maize – 37 ESU, soy beans - 42 ESU ).

Table 3. Biophysical parameters measurements, collected during the field campaigns

Digital Hemispheric Photographs (DHP) images were acquired with a NIKON D70 and CANON 550D cameras. Hemispherical photos allow the calculation of LAI and FCOVER measuring gap fraction through an extreme wide-angle camera lens (i.e. 180º) (Weiss et al., 2004). The hemispherical images acquired during the field campaign are processed with the CAN-EYE software (http://www.avignon.inra.fr/can_eye) to derive LAI, FAPAR and FCOVER biophysical parameters. Ground data collection is performed according to VALERI-protocol.

The in situ biophysical values were used for producing LAI, FCOVER and FAPAR maps from optical satellite images, and provide cross-validation, and validation of global remote sensing products.


Site Description

Locations

The main activities in 2016 were carried out for the JECAM test site in Kyiv region.

The site consists of two parts:

The latitude and longitude of the site and sub-site are given in Table 1.


Figure 1. JECAM Test Sites Location. Kyiv region (a) and intensive observation sub-site - Vasilkov county (b)


Figure 3. Soybeans field (July, 29, 2016)
 


Specific Project Objectives & Deliverables

Results:

Crop mapping:

Crop mapping is performed using Sentinel-1/SAR data together with Sentine-2 optical imagery (Fig. 7). There were 15 Sentinel-1/SAR images available during the period March–September 2016 while only 5 cloud-free Sentinel-2 images are available during the same period. When integrating Sentinel-1 and Sentinel-2 together, overall accuracy reaches to 88.1%.



Figure 7. Crop type map over JECAM test site

 

Biophysical parameters retrieval:

Biophysical parameters collection over JECAM test site was performed within ESA Sen-2 Agri project for validation. LAI products can be treated as important outcome from Sen2-Agri to Sendai framework


Figure 8. LAI relation to NDVI for maize and soybeans

 


Figure 9. LAI samples from ESA Sen-2 Agri Project over JECAM site


 


In Situ Observations

  1. Parameter: crop height
    Data Collection Protocol:
    Frequency: about two times for each crop per year.
  2. Parameter: Crop Type
    Data Collection Protocol:

    along the road field survey and stratified area frame sampling survey (segment survey).

    Frequency: once a year (in June-July when all crops are still present).
  3. Parameter: Digital Hemispheric Photographs
    Data Collection Protocol:

    Images were acquired with a NIKON D70 camera, hemispherical images acquired during the field campaign are processed with the CAN-EYE software (http://www.avignon.inra.fr/can_eye) to derive LAI, FAPAR and FCOVER

    Frequency:

EO Data Requirements

Approximate Start Date of Acquisition: April 1 (min) - September 1 previous year (preferred): Autumn images of the previous year are desirable to discriminate between winter and spring crops.
Approximate End Date of Acquisition: October 1 - Images acquired for specific days
Spatial Resolution: 30 m (min), 5-10 m (preferred): 30 m is required for crop area estimates, 5-10 meters is desirable for field-based biopar parameters retrieval (for intensive observation sub-site)
Temporal Frequency: 1-2 acquisitions per month: One cloud-free image composite per month is required for crop mapping. Two acquisitions per month is required for intensive observation sub-site
Latency of Data Delivery: weekly
Wavelengths Required: G,R,NIR
Across Swath: 210: To cover whole Kyiv region. 25 km is enough to cover intensive observation sub-region.
Along Track: 270: To cover whole Kyiv region. 15 km is enough to cover intensive observation sub-region.

SAR Data Requirements

Approximate Start Date of Acquisition: April 1 (min) - September 1 previous year (preferred): Autumn images of the previous year are desirable to discriminate between winter and spring crops.
Approximate End Date of Acquisition: October 1
Spatial Resolution: 30 m (min), 10 m (preferred): 30 m is required for crop area estimates, 10 meters is desirable due to SAR speckle
Temporal Frequency: 1-2 acquisitions per month: One image composite per month is required for crop mapping. Two acquisitions per month is desirable to test crop classification accuracy due to different incidence angles
Latency of Data Delivery: weekly
Wavelengths Required: X,C (min), X,C,L (preferred): Different wavelengths will help discriminate crop at different (low, medium, high) biomass level and should increase final crop classification accuracy
Polarization Quad polarization: Quad polarization is required to test crop classification accuracy using SAR and optical data. Also quad-pol data will be used to select best dual-polarization option.
Incidence Angle Restrictions: No restriction. Observations with different incidence angles will be used to select optimal range of incidence angles for crop classification
Across Track: 210: To cover whole Kyiv region.
Along Track: 270: To cover whole Kyiv region.

Locations


Optical Sensors

Landsat-8
Imaging Mode:
Spatial Resolution: 30m
Acquisition Frequency: 6 times, Aug-Oct 2014
Pre-Processing Level: L1
Application:

Proba-V
Imaging Mode:
Spatial Resolution: 100m
Acquisition Frequency: 7 times
Pre-Processing Level: L1
Application:

JECAM | Joint Experiment for Crop Assessment and Monitoring | Group on Earth Observation

©2013 Joint Experiment for Crop Assessment and Monitoring © HER MAJESTY THE QUEEN IN RIGHT OF CANADA SA MAJESTE LA REINE DU CHEF DU CANADA (2012)