Published November 2, 2026 | Version v2

Land use and land cover samples for the municipality of Porto Velho, Rondônia state (RO)

  • 1. São Paulo State University (UNESP)
  • 2. ROR icon Universidade Estadual Paulista (Unesp)

Description

Land use and land cover (LULC) samples with MODIS NDVI time series for the municipality of Porto Velho, Rondônia state (RO), northern Brazil, in the Brazilian Amazon. The dataset comprises 90 sample points equally distributed among three classes: Agriculture (croplands), Forest (forestlands), and Pasture (pasturelands), with 30 samples each. Class labels were assigned by visual interpretation of satellite imagery for the reference year 2024, so earlier portions of the time series may reflect previous land uses.

NDVI time series were obtained from the Temporal Vegetation Analysis System (SATVeg), developed by the Brazilian Agricultural Research Corporation (Embrapa), using MODIS MOD13Q1 (Terra) and MYD13Q1 (Aqua) data at 250 m spatial resolution. Each series covers February 2000 to February 2025 (1,094 observations) and includes original, pre-filtered, and Savitzky–Golay smoothed NDVI values.

The dataset is organized into one folder per sample, grouped by class. Each folder contains the original SATVeg spreadsheet (.xlsx), the NDVI temporal profile plot (.png), and a CSV file with standardized English headers. Consolidated files are also provided: sample metadata (samples.csv), sample locations (samples.geojson), and all time series in long format (ndvi_timeseries.csv). See README.md for details.

The methodology is described in an article submitted to GEOINFO 2026.

Version 2: standardized folder and file names, English-language CSV exports, consolidated time series and sample metadata tables, and GeoJSON sample locations. NDVI values are unchanged from version 1.

Files

README.md

Files (18.2 MB)

Name Size
md5:a2765fc24ceeb69dec150697daa6f4c0
2.5 kB Preview Download
md5:9a3794260488d8caf6e856a59ffd0abf
10.2 kB Preview Download
md5:67f3405da2c68277cd1eb86d7291be05
26.0 kB Preview Download
md5:07aaca84b5cc43d541a13a9bef9eee10
18.1 MB Preview Download

Additional details

Related works

Continues
Publication: 10.3390/agriengineering7010019 (DOI)
Publication: 10.1016/j.rsase.2023.101014 (DOI)
Publication: 10.1016/j.pecon.2024.01.009 (DOI)

Funding

Fundação de Amparo à Pesquisa do Estado de São Paulo
Identification of soybean and corn crops in the Brazilian Cerrado via satellite images 2024/08083-7
Fundação de Amparo à Pesquisa do Estado de São Paulo
Improvement of phenological metrics and computational application to identify soybean and corn in the Cerrado biome 2025/00099-4
Fundação de Amparo à Pesquisa do Estado de São Paulo
Use of dense Sentinel-2/MSI time series and machine learning algorithms to improve crop monitoring in the Cerrado biome 2021/07382-2

Dates

Copyrighted
2025-03-26