Print This Page

JECAM | Joint Experiment for Crop Assessment and Monitoring

Burkina Faso - Koumbia

Project Overview

Overall Project Objective of JECAM Site

Goals of the site in terms of:

Project Reports

2016 Site Progress Report

2015 Site Progress Report

2014 Site Progress Report

No papers have been published yet on this site.

Implementation Plans

In situ Data

The points in red in Figure 1 are plots selected for yield prediction and forecasting.  Parcels in yellow are field surveys conducted in October 2015.

Field surveys were conducted on agricultural plots in October 2015. Approximately 900 GPS waypoints were collected to identify crop types following the recommendations of the “JECAM Guidelines for Field Data Collection_v1 0”. Parcels for cropland/crop types identification (in yellow) were manually digitized into polygons (surface data) using the VHSR Pleiades mosaic. Points for yield prediction (in red) will also concur to the validation of the classification products. With few exceptions, almost all points were identified transecting along roads and tracks at the end of the rainy season and using a GPS tablet with Pleiades/SPOT7 base maps.

Figure 1   Plots selected for Yield Prediction and Forecasting, and Field Surveys


Plans for Next Growing Season

Next growing season, we will maintain basically the same approach; however, the approach will be further investigated.

The EO data to be acquired will change as follows:

We will continue programming Pleiades images on the area. The vesting period will be the same.
We plan to renew the order for SPOT 6-7 data (one image in the dry season and one at the end of the rainy season).
We hope that this site will be selected for the acquisition of images from the VENUS mission (spatial resolution : 5m / temporal repetitiveness 2 days)
We will rely again on Landsat-8 images, and add Sentinel-2 multi-spectral images to the dataset in 2016 (including L3A products from the “Sentinel-2 for Agriculture” platform).
We expect to obtain further improvement through the use of SAR data for the generation of 2015 crop type maps. We will renew the acquisition of radar data.

We also hope to renew field surveys: this will depend on the security conditions for the organization of the missions.

Site Description


Burkina Faso JECAM Studt\y Site
Site Extent   Centroid: 11.158, -3.743
Top left: 11.24, -3.743 Bottom Right: 10.196, -3.4

The city of Koumbia is located southwest of Burkina Faso in the province of Tuy, in the Hauts-Basins.

Typical Field Size (Area): 1500 km2

Crop Types: Cotton, maize, sorghum, millet, groundnut

Typical Crop Rotation: Cotton, maize

Crop Calendar: June to October

Climatic Zone: Tropical dry

Soil Texture:  mostly sandy

Landscape Topology: Peneplain with few isolated hills

Irrigation Infrastructure: No

Other Site Specifications: large administrative unit (Commune = 15000 km2)


Photos of the Site:

Sesame Cotton and maize
Groundnuts Herbaceous Savannah
Maize Sorghum
Cow peas Young fallow

Specific Project Objectives & Deliverables


Cropland/Crop Type identification:


(1) Build a cropland/crop type identification map at the highest possible spatial resolution (0.5m) provided by the available EO data for the 2014 agricultural season (data acquired in 2015 that will be processed in 2016), for the different levels of the JECAM nomenclature (see Table 1).

(2) Develop a novel methodology for classification leveraging the data-fusion approach and limiting the use of site-specific prior information, in order to devise a processing chain which can work at a global scale.

Methods: Our data-fusion approach relies on the OBIA (Object Based Image Analysis) paradigm:

Table 1   Modified JECAM Nomenclature including Level 0 (Crop vs Non Crop)

Variable Importance Analysis

To limit the complexity of the overall methodology, we performed a first set of Random Forest classifications to assess the number of important variables to retain. The figure and table below (Figure 1) show the overall accuracies as a function of the number of important variables used for levels 0, A and B. These experiments confirm that a number of variables around 20 (one tenth of the total) is enough to achieve a satisfactory accuracy (above 95% of the maximum achievable accuracy).

Figure 1   Overall Accuracies Obtained Varying the Number of Important Variables Used


Classification assessment using internal Random Forest validation

A first assessment of classification accuracies has been carried out using the internal Random Forest validation strategy (mean of the accuracies on randomly chosen validation samples over different trees). Encouraging results have been obtained, especially for the Levels 0 and A, as reported in Figure 2. Scores for the most detailed levels C and D are very promising, but further inspection is necessary to confirm these outcomes.


Classification assessment using external validation segments

A further set of manually segmented areas (mainly obtained by photo-interpretation) has also been used as an additional test set to assess classifications. Accuracies obtained using this test set are less interesting, especially starting from level B, as shown in Table 2. However, the reliability of the external validation set has to be further inspected.

We could also test the different classification strategies, and verify that the hierarchical approach starting from the level-0 map gives the best accuracies at finer scales.


Figure 2   Overall Accuracies for Single Level Classification using Internal RF Validation



Level 0

Level A

Level B


87.4 %

87.4 %

50.5 %



90.5 %

54.1 %

By grouping


84 %

37.1 %


Table 2   Overall Accuracies for Different Classification Strategies using External Validation Data

In the next Figures, some samples of the cropland/crop-type maps generated for the 2014 agricultural season are shown.

Figure 3   Level 0 Map (Crop vs Non Crop) for Koumbia Village

Figure 4   Details of Classifications at Levels 0, A and B

Yield Prediction and Forecasting:


(1) Describe and evaluate the main crop systems of the site: crop varieties, crop rotation, use of inputs, tillage, fallow, use of plough or tractors and

(2) quantify the yield variability obtained by farmers and evaluate the link with the climate variability.

Methods: Six villages have been selected according to their spatial distribution, their accessibility, the studies already carried out, and the remote sensing image footprints. In agreement with the farmers and peasant organizations, thirty plots have been chosen in each village, to carry out two types of survey:

Figure 5   Site with Villages and Monitored Plots

Figure 6 shows the cotton yields for each village in recent years, and Figure 26 shows the crop rotation with maize.

Figure 6   Cotton Yields for each Village, 2011 - 2013

Figure 7 Crop Rotation with Maize 2009-2011

Figure 8 shows the rainfall at the rain gauges in Boni village, and Figure 9 shows the sowing related to rainfall in Gombeledougou.

Figure 8   Rainfall at the 3 rain gauges in Boni Village, 2014


Figure 9   Sowing Related to Recorded Rainfall in Gombeledougou, 2014

Data analysis for 2015 growing season is still ongoing. The number of monitored plots has been raised to 160, 85 cultivated with maize, 33 with cotton and 42 with sorghum.


An appropriate general workflow based on the fusion of heterogeneous data has been successfully carried out for the identification of crop types. Current classification scores, although to be further validated, stand unprecedented for the Burkina Faso site and confirm that the proposed approach is promising. However, further development has to be carried out in order to:

We followed the recommendations of the “JECAM guides” for the acquisition of field data. However, we have adapted to the nomenclature cultures present on our site.

We modified the project objectives in the sense that we added the study of Yield Prediction and Forecasting.

In Situ Observations

  1. Parameter: yield on some plots
    Data Collection Protocol:
    Frequency: once a year
  2. Parameter: Cropped specie at plot level
    Data Collection Protocol:
    Frequency: once a year
  3. Parameter: Cropping practices observations on some plots
    Data Collection Protocol:
    Frequency: once a year
  4. Parameter: Stage observations on some plots
    Data Collection Protocol:
    Frequency: once a year

EO Data Requirements

Approximate Start Date of Acquisition: September 2012
Approximate End Date of Acquisition: December 2013
Spatial Resolution: 0.5m - 30km
Temporal Frequency: Weekly or monthly, depended on the sensor
Latency of Data Delivery:
Wavelengths Required: RGB, NIR
Across Swath: N/A
Along Track: N/A

SAR Data Requirements

Approximate Start Date of Acquisition: N/A
Approximate End Date of Acquisition: N/A
Spatial Resolution: N/A
Temporal Frequency: N/A
Latency of Data Delivery: N/A
Wavelengths Required: N/A
Polarization N/A
Incidence Angle Restrictions: N/A
Across Track: N/A
Along Track: N/A


Burkina Faso JECAM Studt\y Site

Latitude: 11.158
Longitude: -3.743

Site Extent
Top left
Latitude: 11.24
Longitude: -3.743
Bottom Right
Latitude: 10.196
Longitude: -3.4

Optical Sensors

Imaging Mode: OLI+TIRS
Spatial Resolution: 15m
Acquisition Frequency: 21
Pre-Processing Level: Ortho

Imaging Mode: XS+P(bundle)
Spatial Resolution: 0.5m
Acquisition Frequency: 1 time
Pre-Processing Level: Ortho

Imaging Mode: NIR, R, G
Spatial Resolution: 20m
Acquisition Frequency: 4 times
Pre-Processing Level: Ortho

Worldview 2
Imaging Mode: XS+P (bundle)
Spatial Resolution: 0.5 m
Acquisition Frequency: 1 time
Pre-Processing Level: Ortho

Imaging Mode: VIS, NIR
Spatial Resolution: 6m
Acquisition Frequency: 14 times
Pre-Processing Level:

SPOT (or equivalent) / Sentinel-2
Imaging Mode: XS (VIS, NIR, MIR)
Spatial Resolution: 10 m
Acquisition Frequency: 10 days
Pre-Processing Level: Ortho
Application: Cloud Mask

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)