Campo Verde Database

Citation Author(s):
Ieda Del'Arco Sanches, Raul Queiroz Feitosa, Pedro Marco Achanccaray Diaz, Marinalva Dias Soares, Alfredo Jose Barreto Luiz, Bruno Schultz, Luis Eduardo Pinheiro Maurano
Submitted by:
Raul Queiroz Feitosa
Last updated:
Tue, 05/17/2022 - 22:17
DOI:
10.21227/H2804B
Data Format:
TIF
Research Article Link:
Campo Verde Database: Seeking to Improve Agricultural Remote Sensing of Tropical Areas
License:
Creative Commons Attribution
2586 Views
Categories:
Geoscience and Remote Sensing
Remote Sensing
Keywords:
agricultural mapping/monitoring, double cropping systems, free available database, remote sensing, SAR, tropical agriculture
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

In tropical/subtropical regions, the favorable climate associated with the use of agricultural technologies, such as no-tillage, minimum cultivation, irrigation, early varieties, desiccants, flowering inducing and crop rotation, makes agriculture highly dynamic. In this paper, we present the Campo Verde agricultural database. The purpose of creating and sharing these data is to foster advancement of remote sensing technology in areas of tropical agriculture, primarily the development and testing of methods for crop recognition and agricultural mapping. Campo Verde is a municipality of Mato Grosso State, localized in the Cerrado (Brazilian Savanna) biome, in central west Brazil. Soybean, maize and cotton are the primary crops cultivated in this region. Double cropping systems (e.g., soybean-maize) are widely adopted in this area. There is also livestock and forestry production. Our database provides the land use classes for 513 fields by month for one Brazilian crop year (between October 2015 and July 2016). This information was gathered during two field campaigns in Campo Verde (December 2015 and May 2016) and by visual interpretation of a time-series of Landsat-8/Operational Land Imager (OLI) images using an experienced interpreter. A set of fourteen pre-processed Synthetic Aperture Radar (SAR) Sentinel-1 and fifteen Landsat-8/OLI mosaic images is also made available. It is important to promote the use of radar data for tropical agricultural applications, especially because the use of optical remote sensing in these regions is hindered by the high frequency of cloud cover. To demonstrate the utility of our database, we present the results of an experiment conducted using the Sentinel 1 dataset.

Instructions: 

Campo Verde is a municipality of Mato Grosso (MT) State in the central west region of Brazil. This municipality is located in the Cerrado Biome at a latitude of 15°32’48” south and longitude of 55°10’08” west, and it has an area of 4,782.118 km2 with an altitude of 736 meters. The agricultural calendar (Brazilian crop year) stretches from late August to the following July, with two planting periods during the rainy and dry seasons (first and second harvests, respectively). In Campo Verde, soybean is planted in September to December and harvested in January to April. Cotton can be planted from October to January and harvested in April to September. Maize is planted in January to March and harvested in June to September, and second- harvest maize is planted in January to March and harvested in June to September.

To build reference data for the Brazilian crop year 2015/2016, two field campaigns were conducted in Campo Verde between 14th and 18th December 2015 and 9th and 13th May 2016. The first campaign aimed to acquire information about the first harvest (summer crops, rainy season); and the last focused on the crops cultivated during the second harvest (dry season). 

In total, 14 land use classes were detected: soybean, maize, cotton, beans, sorghum, NCC–millet, NCC-crotalaria, NCC-brachiaria, NCC-grasses (i.e., identified grasses), pasture, turf grass, eucalyptus, Cerrado and uncultivated soil (i.e., bare soil, soil with crop residues from the previously harvest, soil with weeds).

The database consists in three folders:

  • SAR: a set of 14 Sentinel-1 images, co-registered and calibrated.
  • LANDSAT: a set of 16 Landsat 8 OLI images
  • Reference: an ESRI Shapefile with the classes for each one of the 513 polygons (parcel) in each date.

Comments

Submitted by Andrea Britto M... on Wed, 01/09/2019 - 13:33

   

Submitted by Matheus Ferreira on Mon, 04/08/2019 - 13:50

Hello, I want use the dataset to classification with Random Forest algorithm.
My final assessment is focust in classifying kinds of agricultural crops.
After, i hope submit an analysis results here. 

Submitted by Matheus Santos on Wed, 05/15/2019 - 18:51

Hello, I want to use the dataset to create generative adversarial network to urban growth. After, I hope to submit analysis results here. 

Submitted by Toni Esteves on Wed, 10/23/2019 - 16:28

I would like to run classification algo run on this  dataset to see crop classification and then would like to submit analysis.

Submitted by Vighneshwar Mishra on Thu, 10/31/2019 - 03:46

Hello, i would like to try to use your dataset to train my nerual network, and may submit the results of crop classification.

Submitted by yuchen Xie on Sun, 11/03/2019 - 23:56

Hello，I want to use this dataset, Thank you very much. I think this dataset is very good

Submitted by Zhang Chao on Wed, 03/16/2022 - 08:22

Hello, have you obtained this dataset? If so, can you please send hello, please get this data set. If so, can you please send me a copy

Submitted by jingyi chen on Fri, 12/02/2022 - 02:50

Dataset Files

LOGIN TO ACCESS DATASET FILES

QUESTIONS?