Impact model: BuRNN1-1

Statistical fire model using the mean of 5 LSTMs at each location. Trained on GFEd5.1. BuRNN v1.1 uses gpp, lai and cveg from VISIT for all simulations.

ISIMIP3b
ISIMIP3a

Confirm data for simulation round ISIMIP3b

Person responsible for model simulations in this simulation round

Seppe Lampe: seppe.lampe@vub.be, 0000-0002-7907-4496, Vrije Universiteit Brussel, Department of Water & Climate (Belgium)

Output Data

Experiments: (*) historical_2015soc_default, ssp126_ssp126soc-noadapt+image_default, ssp585_2015soc_default, ssp126_2015soc_default, ssp585_ssp585soc-noadapt+image_default, ssp370_ssp370soc-noadapt+image_default, ssp370_ssp370soc-adapt+image_default, ssp370_2015soc_default, historical_histsoc_default, ssp126_2015soc-from-histsoc_default, ssp126_ssp126soc-adapt+image_default, ssp585_ssp585soc-adapt+image_default, ssp585_2015soc-from-histsoc_default, ssp370_2015soc-from-histsoc_default
Climate Drivers: GFDL-ESM4, IPSL-CM6A-LR, MPI-ESM1-2-HR, MRI-ESM2-0, UKESM1-0-LL
Date: 2026-07-03

Basic information

Model Version: 1.1

Person responsible for model simulations in this simulation round

Seppe Lampe: seppe.lampe@vub.be, 0000-0002-7907-4496, Vrije Universiteit Brussel, Department of Water & Climate (Belgium)

Additional persons involved: Wim Thiery

Output Data

Experiments: (*) counterclim_2015soc_default, obsclim_2015soc_default, obsclim_histsoc_default, counterclim_histsoc_default
Climate Drivers: GSWP3-W5E5
Date: 2026-07-14

Basic information

Model Version: 1.1

Model Output License: CC0

Model Homepage: https://github.com/VUB-HYDR/BuRNN

Model License: CC BY 4.0

Reference Paper: Main Reference: Lampe S, Gudmundsson L, Kraft B, Hantson S, Kelley D, Humphrey V, Le Saux B, Chuvieco E, Thiery W et al. BuRNN (v1.0): a data-driven fire model. Geoscientific Model Development,19,955-988,2026

Resolution

Spatial aggregation: regular grid

Horizontal resolution: 0.5°x0.5°

Vertically resolved: No

Temporal resolution of input data: climate variables: monthly

Temporal resolution of input data: land use/land cover: annual

Input data

Observed atmospheric climate data sets: GSWP3-W5E5 (ISIMIP3a)

Socio-economic data sets: Historical land transformation, National historical Gross Domestic Product (GDP), Population (national and gridded, historical, ISIMIP3a)

Land use data sets: Historical, gridded land use

Other human influences data sets: Lakes area fraction

Other data sets: Lightning, Land-sea mask

Climate variables: hurs, sfcWind, tasmax, pr

Spin-up

Was a spin-up performed?: Yes

Spin-up design: Repeated the 1901-1903 in front of the 1901-2019 input dataset to spin up the memory of the LSTM (similar procedure as during model training).

Natural Vegetation

Natural vegetation partition: We applied the CLM pft structure and then regrouped the original pfts into 11 pfts (see model description paper).

Natural vegetation dynamics: It is not, for gpp, lai and cveg we used the values available on the ISIMIP repository from VISIT (which was not coupled to BuRNN).

Fire-specific input data sets

What is the time step of the fire model?: Monthly

What is the time step of the exchange between fire and vegetation model? e.g. are carbon pools and cover fractions updated every day?: None

Burnt Area

What are the main components of burned area computation?: Not applicable

Ignition

Which sources of ignition are included?: Natural (climatology)

Is fire ignition implemented as a random process?: Not applicable

How are natural ignitions implemented? which data is used and how is it scaled?: Not applicable

Spread and duration

How does fire spread?: Not applicable

How is fire duration computed?: Not applicable

Fuel load and combustion

How does the model compute fuel load?: Not applicable

List of fuel classes (full names and abbreviations): Not applicable

Is fuel moisture linked to soil moisture/air humidity/precip?: Not applicable

Which carbon pools are combusted?: Not applicable

Is the combustion completeness constant or depends on what (fuel type, moisture?): Not applicable

Landcover

What is the minimum/maximum burned area fraction at grid cell level? over which time period?: 0-~45%

Land-cover classes allowed to burn: Not applicable

Is burned area computed separately for each pft? if not how is burned area separated into the pft-burned area?: No

How are pastures represented?: As managed pastures from the ISIMIP land management dataset

If croplands burn, does the fire model differ for this pft? if yes please describe.: Not applicable

If pastures burn, does the fire model differ for his pft? if yes, please describe: Not applicable

Fire mortality

Vegetation fire mortality: is it constant/constant per pft/depends on (for instance fire intensity, bark thickness, veg height): Not applicable

Model output specifications

How to calculate global annual total outputs: Transform from fraction to surface area by multiplying by grid cell size. Then add it all up.