Skip to content

Wildfire occurrence modeling using Terrestrial Ecosystem Models and Artificial Intelligence

License

Notifications You must be signed in to change notification settings

FiRE-HNL/alaska-wildfire-occurrence

Repository files navigation

title emoji colorFrom colorTo sdk pinned license app_port
Alaska Wildfire Occurrence
🔥
green
red
docker
false
apache-2.0
7860

wildfire-occurrence

Wildfire occurrence modeling using Terrestrial Ecosystem Models and Artificial Intelligence

DOI

CG Lightning Probability Forecast

Tutorial Exercises

Lecture Topic Interactive Link
Python Spatial Visualization Open In Colab
Python ALDN Validation Open In Colab

Objectives

  • Probabilistic wildfire occurrence model
  • Model both occurrence, spread and risk of fire
  • Create data pipeline between UAF TEM and NCCS/SMCE resources
  • 30m local Alaska models, 1km circumpolar models
  • Integration of precipitation, temperature and lightning datasets

Containers

Python Container

module load singularity
singularity build --sandbox /lscratch/$USER/container/wildfire-occurrence docker://nasanccs/wildfire-occurrence:latest

Quickstart

Running WRF

conda activate ilab-pytorch; PYTHONPATH="/explore/nobackup/people/$USER/development/wildfire-occurrence" python /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/view/wrf_pipeline_cli.py -c /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/templates/config.yaml --start-date 2023-06-06 --forecast-lenght 10 --pipeline-step all

Extracting variables from WRF

Running this script to extract variables from WRF and perform lightning inference

singularity shell --nv -B /explore/nobackup/projects/ilab,/explore/nobackup/projects/3sl,$NOBACKUP,/lscratch,/explore/nobackup/people /lscratch/jacaraba/container/wildfire-occurrence/
python wrf_analysis.py 

Generate output variables

singularity exec --env PYTHONPATH="/explore/nobackup/people/jacaraba/development/wildfire-occurrence" --nv -B /explore/nobackup/projects/ilab,/explore/nobackup/projects/3sl,$NOBACKUP,/lscratch,/explore/nobackup/people /lscratch/jacaraba/container/wildfire-occurrence python /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/view/wrf_pipeline_cli.py -c /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/templates/config.yaml --start-date 2023-06-29 --forecast-lenght 10 --pipeline-step postprocess

Generate output variables

singularity exec --env PYTHONPATH="/explore/nobackup/people/jacaraba/development/wildfire-occurrence" --nv -B /explore/nobackup/projects/ilab,/explore/nobackup/projects/3sl,$NOBACKUP,/lscratch,/explore/nobackup/people /lscratch/jacaraba/container/wildfire-occurrence python /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/view/lightning_pipeline_cli.py -c /explore/nobackup/people/$USER/development/wildfire-occurrence/wildfire_occurrence/templates/config.yaml --pipeline-step preprocess

Dataset Generation and Training

singularity exec --env PYTHONPATH="/explore/nobackup/people/jacaraba/development/wildfire-occurrence" --nv -B /explore/nobackup/projects/ilab,/explore/nobackup/projects/3sl,$NOBACKUP,/lscratch,/explore/nobackup/people /lscratch/jacaraba/container/wildfire-occurrence python /explore/nobackup/people/jacaraba/development/wildfire-occurrence/wildfire_occurrence/model/lightning/lightning_model.py

Full Data Pipeline Command

singularity exec --env PYTHONPATH="/explore/nobackup/people/jacaraba/development/wildfire-occurrence" --nv -B /explore/nobackup/projects/ilab,/explore/nobackup/projects/3sl,$NOBACKUP,/lscratch,/explore/nobackup/people /lscratch/jacaraba/container/wildfire-occurrence python /explore/nobackup/people/jacaraba/development/wildfire-occurrence/wildfire_occurrence/model/lightning/lightning_model.py 

Contributors

About

Wildfire occurrence modeling using Terrestrial Ecosystem Models and Artificial Intelligence

Resources

License

Stars

Watchers

Forks

Packages

No packages published