Print This Page

JECAM | Joint Experiment for Crop Assessment and Monitoring

Brazil - São Paulo

Project Overview

The main objectives:

Crop identification and Crop Area Estimation

Goals of the site in terms of:

Mapping Resolution: 30 m for landscape scale
Timeliness (with regards to growing season):  annual /seasonal 
Operational implementation plans (if any):  N/A

This project is in the research and development phase.


Project Reports

2017 Site Progress Report

2016 Site Progress Report

2015 Site Progress Report

2014 Site Progress Report

 

  1. Waldner, F., De Abelleyra, D., Verón, S.R., Zhang, M., Wu, B., Plotnikov, D., Bartalev, S., Lavreniuk, M., Skakun, S., Kussul, N., Le Maire, G., Dupuy, S., Jarvis, I. & Defourny, P. (2016) Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity. International Journal of Remote Sensing, 37, 3196-3231.
     
  2. Le Maire G., Dupuy S., Boury J., Lebourgeois V., Bégué A., Presentation of the JECAM Brazil – Botucatu (São Paulo) site activities , JECAM/GEOGLAM Science Meeting, Kiev, 11-12 October, 2016 (poster)
     
  3. Boury J (2016), Cartographie de l’occupation et de l’usage du sol au Brésil à l’échelle du paysage, M1 Université Paris Diderot, Master dissertation

Implementation Plans

Plans for Next Growing Season:

We will try to maintain the current approach, by doing field inventories every 2.5-3 months on the south-western part of the JECAM area (265 sites), mainly covered by croplands. A general inventory will be conducted before april 2017, synchronously with a SPOT7 image acquisition.

 

In situ Data:

We collected 847 GPS point in the field in December 2014, following the JECAM protocol and updated nomenclature for our site specificities. GPS points were chosen along roads to cover most part of the JECAM area (see figure below). GPS points were afterwards converted to polygons based on the images.

During the 2015 and 2016 years, measurements field visits were done every 3 months (March, May, August, November) for a subset of 265 sites located in the “annual crop” area of the image (i.e. South West). The most precise nomenclature was used (species), and other attributes such as irrigation or not, height of the crop, etc. were also recorded.

In February 2016, all the 847 GPS points measured in December 2014 were visited, including the 265 sites located above. Most of the other 582 sites (847-265) were located in areas with a majority of perennial crops i.e. an annual visit is mostly sufficient. These sites are mostly Eucalyptus plantations, sugarcane, pastures, coffee plantations, citrus plantations, pines plantations). Land used changes occurred in a few of these sites, and they were discarded in some of the treatments. This complete dataset field inventory will be done again before april 2017.

Illustration of the 847 polygons of the classified area, measured in December 2014 and January 2016

 

During 2015 and 2016 years, on the 265 sites visited regularly, 96 sites were annual culture fields, others were mainly pasture and sugarcane. These sites presented a large variety of crop cycles, listed in the table and figure below. There are a very large number of combinations of land cover classes through the year. To see a bit more clearly, we have added different colors for soya, corn and “winter cereal”. We can see that many fields alternate between soya and corn, or soya and winter crop, with the soya being planted during the wet season and the corn/winter crop during the dry winter months. For the corn, the scheme is a bit different, because it could be planted all along the year. For the sugarcane, not presented in the figure, the date of harvest could be almost all along the year. Some fields have a succession of 3 different cultures during the year.

 

Example of crop types measured every ~3 months on the same polygons in 2015 and beginning 2016

 

Main Crops Calendar:


Site Description

Locations

Brazil - São Paulo - Itatinga
Site Extent   Centroid: -22.9677, -48.7274
Top left: -22.4780, -49.1290 Bottom Right: -23.5895, -47.8720

Site Description

Location: Lat -22.9677, Lon -48.7274
Topography: slope <5% in centroid area
Soils: Ferralsols, 20% Clay (in centroid area)
Drainage class/irrigation: Moderately to well drained, high water consumption for Eucalyptus stands, cropland sometimes irrigated
Crop calendar: Eucalyptus: 6 years rotations ; Other crops and sugarcane: monitoring started in December 2014, but mainly sugarcane monoculture, oran
Field size: 40 ha for Eucalyptus field, large fields for other crop classes
Climate and weather: Humid Tropical (Aw Koppen), weather stations
Agricultural methods used:

Photograph(s) Many photographs have been taken during all field campaigns.


Specific Project Objectives & Deliverables

The method for mapping land cover in this site was described in the JECAM poster presented at Kiev:

We have seen from the dec 2014 results that it is possible to classify the perennial crops and forests with a good precision, with a single class “annual crop”. Once the “annual crop” mask generated in the first step, we will improve its sub-classification in a second step.  There is a big challenge for the classification of the cropland areas in the level of species, as we have seen last year: the lowest accuracies was for the annual crop species. The different options are: perform a classification with a reduced number of species, by grouping species types (eg. winter cereal). Another option is to classify the entire annual rotation, with a reduced number of rotation obtained from the table with a merge similar type of rotations. The last option is to perform a date-by-date classification at the species scale, however, some species have few training points. It was however the method that we selected, but grouping some species together. Indeed, the diversity of intra-annual crop cycles are very variable.

Another main question is which remote sensing data could be used. Indeed, during the wet season, very few images are available. Therefore, we are developing a new classification program which could use all the available data, including Landsat 7 data or images only partly covering the area. This is a challenge mainly for the issue of the “no data” values within the time series (clouds, area covered by the satellite, Landsat 7 SLC issue, etc.). For this, we will test two options: 1) filling the “no-data” with an advanced gap filling algorithm, based on the available data at that period and the surrounding data 2) training different classification models in function of the available data. The second algorithm showed better results and was kept for the rest of the study.

Annual land cover map :

The global accuracy for the 11 class nomenclature was 0.88 on the calibration dataset (see confusion matrix below) for February 2016. The highest confusion was between sugarcane and pasture, orange orchards and other perennial classes, and bare soil and annual crops. However, the confusion matrix is not independent from the calibration dataset, and accuracies may therefore be overestimated.

 

Visual interpretation of the obtained map show good prediction for most of the classes. The clear distinction between sugarcane area in the NW and E, forest plantation in the Center West, annual crops in the south and pastures in the Center East is largely coherent with other large scale maps of the area such as the Probio Map (http://www.mma.gov.br).

The orange orchards are well predicted for large fields, but there is a confusion with natural vegetation for small polygons.

Crop map at 3-month time step: The global accuracy was computed for each field inventory dates, considering only the crop class that had more than 10 observations in the calibration dataset (see tables below). The calibration dataset is therefore largely reduced to 115 to 222 observations. The global accuracies are given in the figure below, and highly depends on the date.

Conclusions

While the algorithm used was able to deal efficiently with clouds or other no-data, there are at least three main issues with this ongoing work :

This JECAM site is particularly interesting to test classification algorithm including perennial tree-based agriculture (eucalyptus, pines, coffee, orchards), pastures, perennial crop (sugarcane), and annual crop.


In Situ Observations

  1. Parameter: Nomenclature
    Data Collection Protocol:

    Find on the Implementation Plans page.

    Frequency:

EO Data Requirements

Approximate Start Date of Acquisition: February 1
Approximate End Date of Acquisition: September 1
Spatial Resolution: 250 m - 300 m
Temporal Frequency: Monthly (approximately)
Latency of Data Delivery:
Wavelengths Required: R, NIR
Across Swath: 17.6 km - 60 km
Along Track: 14 km

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

Locations

Brazil - São Paulo - Itatinga

Centroid
Latitude: -22.9677
Longitude: -48.7274

Site Extent
Top left
Latitude: -22.4780
Longitude: -48.7274
Bottom Right
Latitude: -23.5895
Longitude: -47.8720


Optical Sensors

MODIS TERRA
Imaging Mode: NIR, R
Spatial Resolution: 250m
Acquisition Frequency: ~220 scenes
Pre-Processing Level: TOC reflectance, NDVI product
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)