Research data for land use modelling 2012 - 2022 in Mato Grosso, Brazil

General description:

The research data presented in this repository is to model land use change in the state of Mato Grosso, Brazil from 2012 to 2022. The data is subdivided into four sections:

1) Observed land use maps for 2012 and 2022;

2) Predictor variables to calculate location suitabiliy raster layers for each land use class;

3) Projected land use maps for 2022 (with different modelling methods for location suitability);

4) AGB maps for 2010 for impact assessment.

The code for calculation of location suitability rasters and the land use modelling can be found on GitHub (https://github.com/nomisthomsen/CLUMondoPy).

1. Observed land use maps for 2012 and 2022:

The observed land use maps for 2012 and 2022 were retrieved from MapBiomas. The data was clipped to the extent of Mato Grosso, reclassified and resampled.

Source: 

"MapBiomas Project - Collection 8 of the Annual Land Use Land Cover Maps of Brazil, accessed on 28.03.25 through the link: 'projects/mapbiomas-workspace/public/collection8/mapbiomas_collection80_integration_v1' in Google Earth Engine™.

2. Predictor variables for location suitability:

Predictor variables were retrieved from different sources, see table below. All data are publicly available for free. Most of the data was accessed and processed in Google Earth Engine™ (GEE) on 28.03.25.

3. Projected land use maps 2022

Projected land use maps contain the results of CLUMondo modelling with different modelling methods for location suitability calculation. These include:

• Logistic Regression
• Random Forest
• XGBoost
• Multilayer Pereceptron (MLP)
• Support Vector Machine (SVM)

4. AGB map 2010 (Carbon_ESA_2010_MT.tif)

Above ground biomass (AGB) map created by ESA CCI (Santoro et al. 2024) for the year 2010. The data was clipped to the extent of Mato Grosso, reprojected and resampled. The data was accessed in Google Earth Engine™ with the following link: "projects/sat-io/open-datasets/ESA/ESA_CCI_AGB"

References:

Chen, Zuoqi; Yu, Bailang; Yang, Chengshu; Zhou, Yuyu; Yao, Shenjun; Qian, Xingjian et al. (2021): An extended time series (2000–2018) of global NPP-VIIRS-like nighttime light data from a cross-sensor calibration. In Earth Syst. Sci. Data 13 (3), pp. 889–906. DOI: 10.5194/essd-13-889-2021.

FAO; IASSA (2021): Global Agro Ecological Zones version 4 (GAEZ v4). Available online at http://www.fao.org/gaez/, checked on 8/25/2025.

Farr, Tom G.; Rosen, Paul A.; Caro, Edward; Crippen, Robert; Duren, Riley; Hensley, Scott et al. (2007): The Shuttle Radar Topography Mission. In Reviews of Geophysics 45 (2), Article 2005RG000183. DOI: 10.1029/2005RG000183.

Hijmans, Robert J.; Cameron, Susan E.; Parra, Juan L.; Jones, Peter G.; Jarvis, Andy (2005): Very high resolution interpolated climate surfaces for global land areas. In Intl Journal of Climatology 25 (15), pp. 1965–1978. DOI: 10.1002/joc.1276.

Malaria Atlas Project (2015): Friction Surface. High-resolution maps of land-base travel speed: Malaria Atlas Project. Available online at https://data.malariaatlas.org/, checked on 8/21/2025.

Santoro, Maurizio; Cartus, Oliver; Quegan, Shaun; Kay, Heather; Lucas, Richard M.; Araza, Arnan et al. (2024): Design and performance of the Climate Change Initiative Biomass global retrieval algorithm. In Science of Remote Sensing 10, p. 100169. DOI: 10.1016/j.srs.2024.100169.

Sorichetta, Alessandro; Hornby, Graeme M.; Stevens, Forrest R.; Gaughan, Andrea E.; Linard, Catherine; Tatem, Andrew J. (2015): High-resolution gridded population datasets for Latin America and the Caribbean in 2010, 2015, and 2020. In Scientific data 2, p. 150045. DOI: 10.1038/sdata.2015.45.

Weiss, D. J.; Nelson, A.; Gibson, H. S.; Temperley, W.; Peedell, S.; Lieber, A. et al. (2018): A global map of travel time to cities to assess inequalities in accessibility in 2015. In Nature 553 (7688), pp. 333–336. DOI: 10.1038/nature25181.