format_version: ml_modis_npz_v1
data:
  path: data/ml_modis_fake.npz
  samples: 1400
  years: [2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020]
  months: [9, 10]
  platforms: [Terra, Aqua]
  dimensions:
    predictors: 114
    targets: 4
  variables:
    profile:
      names: [temperature, specific_humidity, relative_humidity, u_wind, v_wind, omega, geopotential, cloud_liquid, cloud_fraction]
      pressure_levels_hpa: [1000, 950, 900, 850, 800, 750, 700, 650, 600, 550]
      count: 90
    single_level:
      names: [sst, surface_pressure, mslp, skin_temperature, t2m, d2m, u10, v10, surface_solar_radiation, surface_thermal_radiation, latent_heat_flux, sensible_heat_flux, boundary_layer_height, total_column_water_vapour, total_column_cloud_liquid, cape, cin, low_cloud_cover, sea_ice_fraction, precipitation, cos_sza, latitude, longitude, platform_hour]
      count: 24
    targets:
      names: [Nd, reff, LWP, CF]
      units: [cm-3, um, g-m-2, fraction]
    coordinates:
      latitude_degrees_north: [45, 75]
      longitude_degrees_east: [-60, 30]
model:
  trees: 12
  max_depth: 9
  min_leaf: 7
  max_features: 38
  bootstrap_fraction: 0.6
  split_candidates: 12
paper_model:
  trees: 100
  max_depth: null
  min_leaf: 7
  max_features: 38
  bootstrap_fraction: 0.6
  split_candidates: 12
train:
  excluded_year: 2014
  independent_models: 8
runtime:
  seed: 20220908
  device: cpu
  distributed_backend: gloo
paths:
  checkpoint: result/checkpoints/ml_modis.pt
  training_metrics: result/training/metrics.json
  predictions: result/output/predictions.npz
  evaluation_dir: result/evaluation
evaluation:
  cloud_albedo: 0.38
  clear_sky_ocean_albedo: 0.07
  importance_top_k: 10
  figure_dpi: 150