Published October 1, 2020 | Version 14042020
Software Open

Random Forest trained to estimate Amazon maximum height based on enviromental factors

  • 1. Universidade Federal dos Vales do Jequitinhonha e Mucuri
  • 2. University of Helsinki
  • 3. University of Cambridge
  • 4. United States Forest Service
  • 5. Universidade de São Paulo
  • 6. Bangor University
  • 7. Swansea University
  • 8. Instituto Nacional de Pesquisas da Amazônia
  • 9. Universidade de Brasília
  • 10. Instituto Nacional de Pesquisas Espaciais


The Random Forest model obtained MAE = 3.62 m, RMSE  = 4.92 m, and R² = 0.735. we initially considered a total of 18 environmental variables: (1) fraction of absorbed photosynthetically active radiation (FAPAR; in %); (2) elevation above sea level (Elevation; in m);  (3) the component of the horizontal wind towards east, i.e. zonal velocity (u-speed ; in m s-1); (4) the component of the horizontal wind towards north, i.e. meridional velocity (v-speed ; in m s-1); (5) the number of days not affected by cloud cover (clear days; in days yr-1); (6) the number of days with precipitation above 20 mm (days > 20mm; in days yr-1 ); (7) the number of months with precipitation below 100 mm (months < 100mm; in months yr-1 ) ; (8) lightning frequency (flashes rate); (9) annual precipitation (in mm); (10) potential evapotranspiration (in mm); (11) coefficient of variation of precipitation (precipitation seasonality; in %); (12) amount of precipitation on the wettest month (precip. wettest; in mm); (13) amount of precipitation on the driest month (precip. driest; in mm); (14) mean annual temperature (in °C); (15)  standard deviation of temperature (temp. seasonality; in °C); (16) annual maximum temperature (in °C); (17) soil clay content (in %); and (18) soil water content (in %). Among the initial 18 environmental variables, two of them (precipitation on driest month and months < 100mm) were excluded due to high correlation (> 0.80) to other independent variables.


Funding was provided by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior Brasil (CAPES; Finance Code 001); Conselho Nacional de Desenvolvi­mento Científico e Tecnológico (Processes 403297/2016-8 and 301661/2019-7); Amazon Fund (grant 14.2.0929.1); Universidade Federal dos Vales do Jequitinhonha e Mucuri (UFVJM); Instituto Nacional de Pesquisas Espaciais (INPE); São Paulo Research Foundation (#2018/21338-3 and #2019/14697-0); INCT-Madeiras da Amazônia and Next Generation Ecosystem Experiments-Tropics (NGEE-Tropics), as part of DOE's Terrestrial Ecosystem Science Program – Contract No. DE-AC02-05CH11231; National Academy of Sciences and US Agency for International Development (grant AID-OAA-A-11-00012); Royal Society University Research Fellowship (URF\R\191014).


Files (2.0 MB)

Name Size Download all
2.0 MB Download

Additional details

Related works

Is referenced by
Journal article: 10.1111/gcb.15423 (DOI)


A 3D perspective on the effects of topography and wind on forest height and dynamics NE/S010750/1
UK Research and Innovation
Understanding mechanisms of habitat change in fragmented tropical forests for improving conservation 319905
Academy of Finland