Tropical loss enhance pftmask cnpratio badvars

CNP_IO_updated9_dev_dw_repeat.txt

@@ -0,0 +1,75 @@
+# Dataset roots (any absolute paths)
+TRENDY1_PATH: /mnt/proj-shared/AI4BGC_7xw/TrainingData/Trendy_1_data_CNP
+TRENDY05_PATH: /mnt/proj-shared/AI4BGC_7xw/TrainingData/Trendy_05_data_CNP
+TVA4KM_PATH: /mnt/proj-shared/AI4BGC_7xw/TrainingData/TVA_4km_data_CNP
+
+# Optional extra roots (comma-separated)
+DATA_PATHS: /another/path1, /another/path2
+
+# Global fallback pattern if a dataset-specific one isn't set
+#FILE_PATTERN: enhanced_1_training_data_batch_*.pkl
+FILE_PATTERN: 1_training_data_batch_*.pkl
+
+# Per-dataset patterns (overrides FILE_PATTERN for that path only)
+TVA4KM_FILE_PATTERN: enhanced_monthly_training_data_batch_*.pkl
+
+
+LONGITUDE FILTERING - 2 longitudes:
+• 0, 358.75
+
+TIME SERIES VARIABLES (Climate Forcing) - 6 variables:
+• FLDS, PSRF, FSDS, QBOT, PRECTmms, TBOT 
+
+SURFACE PROPERTIES - 49 variables:
+• Latitude, Longitude, AREA, landfrac, LANDFRAC_PFT, PCT_NATVEG
+
+• OCCLUDED_P, SECONDARY_P, LABILE_P, APATITE_P
+
+• SOIL_COLOR, SOIL_ORDER
+
+• PCT_NAT_PFT_0, PCT_NAT_PFT_1, PCT_NAT_PFT_2, PCT_NAT_PFT_3, PCT_NAT_PFT_4, PCT_NAT_PFT_5, PCT_NAT_PFT_6, PCT_NAT_PFT_7, PCT_NAT_PFT_8
+• PCT_NAT_PFT_9, PCT_NAT_PFT_10, PCT_NAT_PFT_11, PCT_NAT_PFT_12, PCT_NAT_PFT_13, PCT_NAT_PFT_14, PCT_NAT_PFT_15, PCT_NAT_PFT_16
+
+• PCT_CLAY_0, PCT_CLAY_1, PCT_CLAY_2, PCT_CLAY_3, PCT_CLAY_4, PCT_CLAY_5, PCT_CLAY_6, PCT_CLAY_7, PCT_CLAY_8, PCT_CLAY_9
+• PCT_SAND_0, PCT_SAND_1, PCT_SAND_2, PCT_SAND_3, PCT_SAND_4, PCT_SAND_5, PCT_SAND_6, PCT_SAND_7, PCT_SAND_8, PCT_SAND_9
+
+PFT PARAMETERS (Plant Functional Type Characteristics) - 44 variables:
+
+• pft_deadwdcn, pft_frootcn, pft_leafcn, pft_lflitcn, pft_livewdcn, pft_c3psn, pft_croot_stem, pft_crop, pft_dleaf 
+• pft_dsladlai, pft_evergreen, pft_fcur, pft_flivewd, pft_flnr, pft_fr_fcel, pft_fr_flab, pft_fr_flig, pft_froot_leaf 
+• pft_grperc, pft_grpnow, pft_leaf_long, pft_lf_fcel, pft_lf_flab, pft_lf_flig, pft_rholnir, pft_rholvis, pft_rhosnir, pft_rhosvis 
+• pft_roota_par, pft_rootb_par, pft_rootprof_beta, pft_season_decid, pft_slatop, pft_smpsc, pft_smpso, pft_stem_leaf, pft_stress_decid 
+• pft_taulnir, pft_taulvis, pft_tausnir, pft_tausvis, pft_woody, pft_xl, pft_z0mr
+
+SCALAR VARIABLES (1D - 4 variables):
+• GPP, NPP, AR, HR
+
+1D PFT VARIABLES (41 variables):
+
+• deadcrootc, deadcrootc_storage, deadcrootn, deadcrootn_storage, deadcrootp, deadcrootp_storage 
+• deadstemc, deadstemc_storage, deadstemn, deadstemn_storage, deadstemp, deadstemp_storage
+
+• leafc, leafc_storage, leafn, leafn_storage, leafp, leafp_storage  
+• frootc, frootc_storage, frootn, frootn_storage, frootp, frootp_storage
+
+• livestemc, livestemc_storage, livestemn, livestemn_storage, livestemp, livestemp_storage, 
+• livecrootc, livecrootc_storage, livecrootn, livecrootn_storage, livecrootp, livecrootp_storage
+
+• cpool, npool, ppool
+
+• tlai, totvegc
+
+2D VARIABLES (layered - 25 variables):
+
+• cwdc_vr, cwdn_vr, cwdp_vr
+
+• litr2c_vr, litr3c_vr
+• litr2n_vr, litr3n_vr
+• litr2p_vr, litr3p_vr
+
+• soil1c_vr, soil1n_vr, soil1p_vr
+• soil2c_vr, soil2n_vr, soil2p_vr
+• soil3c_vr, soil3n_vr, soil3p_vr
+• soil4c_vr, soil4n_vr, soil4p_vr
+
+• labilep_vr , occlp_vr, primp_vr, secondp_vr, solutionp_vr

commands.txt

@@ -112,7 +112,7 @@ python train_cnp_model.py \
   --variable-list CNP_IO_updated9_dev_dw.txt \
   --training-config-json config/training_config_experiment_2.json \
   --pft-zero-sparsity-weight 1.0 \
-  --epoch 50 \
+  --epoch 80 \
   --tropical-only \
   2>&1 | tee training_cpool_experiment.log &
 
@@ -160,4 +160,10 @@ python train_cnp_model.py \
   --variable-list CNP_IO_updated9_dev_dw.txt \
   --training-config config/training_config_experiment_2_plus.json \
   --epoch 80 \
+  --tropical-only
+
+
+  python train_cnp_model.py \
+  --variable-list CNP_IO_updated9_dev_dw_repeat.txt \
+  --training-config config/training_config_experiment_2_repeat.json \
   --tropical-only

config/training_config_experiment_2.json

@@ -0,0 +1,131 @@
+{
+  "training_hyperparameters": {
+    "num_epochs": 100,
+    "batch_size": 128,
+    "learning_rate": 0.0001,
+    "optimizer_type": "adam",
+    "weight_decay": 0.0,
+    "use_scheduler": false,
+    "xsmrpool_loss_weight": 10.0,
+    "litter_c_loss_weight": 1.0,
+    "litter_n_loss_weight": 1.0,
+    "litter_p_loss_weight": 1.0,
+    "scalar_loss_weight": 1.0,
+    "vector_loss_weight": 1.0,
+    "matrix_loss_weight": 1.0
+  },
+  "reproducibility_config": {
+    "random_seed": 42,
+    "strict_determinism": false,
+    "train_split": 0.8,
+    "normalization": "individual",
+    "dropout_p": null
+  },
+  "data_filtering_config": {
+    "tropical_only": true,
+    "tropical_lat_range": [-23.5, 23.5]
+  },
+  "variable_weights": {
+    "pft1d_weights": {
+      "cpool": 6,
+      "npool": 8,
+      "ppool": 8,
+      "totvegc": 6,
+      "leafc": 6,
+      "leafn": 6,
+      "leafp": 6,
+      "leafc_storage": 5,
+      "leafn_storage": 5,
+      "leafp_storage": 5,
+      "deadstemc": 6,
+      "deadstemn": 6,
+      "deadstemp": 5,
+      "frootc": 4,
+      "frootn": 4,
+      "frootp": 4,
+      "frootc_storage": 3,
+      "frootn_storage": 3,
+      "frootp_storage": 3,
+      "tlai": 4
+    },
+    "soil2d_weights": {
+      "primp_vr": 9,
+      "litr2c_vr": 8,
+      "litr2p_vr": 8,
+      "litr2n_vr": 8,
+      "soil1c_vr": 7,
+      "soil1n_vr": 7,
+      "soil1p_vr": 7,
+      "litr3n_vr": 5,
+      "labilep_vr": 5,
+      "secondp_vr": 2.5,
+      "solutinorganicp_vr": 5,
+      "litr3p_vr": 5
+    },
+    "scalar_weights": {
+      "GPP": 1.5,
+      "NPP": 1.5,
+      "AR": 1.2,
+      "HR": 1.2
+    }
+  },
+  "tail_aware_config": {
+    "loss": "log1p_mse",
+    "epsilon": 1e-8
+  },
+  "tail_aware_weights": {
+    "cpool": 6,
+    "deadstemc": 6,
+    "deadcrootc": 5,
+    "livestemc": 5,
+    "livecrootc": 5,
+    "npool": 8,
+    "ppool": 8,
+    "totvegc": 6,
+    "leafc": 6,
+    "leafn": 6,
+    "leafp": 6,
+    "leafc_storage": 5,
+    "leafn_storage": 5,
+    "leafp_storage": 5,
+    "deadstemp": 5,
+    "deadstemn": 6,
+    "frootc": 4,
+    "frootn": 4,
+    "frootp": 4,
+    "labilep": 5,
+    "labilep_vr": 5,
+    "primp_vr": 9,
+    "litr2c_vr": 8,
+    "litr2p_vr": 8,
+    "litr2n_vr": 8,
+    "litr3c_vr": 5,
+    "litr3p_vr": 5,
+    "litr3n_vr": 5,
+    "soil1c_vr": 7,
+    "soil1n_vr": 7,
+    "soil1p_vr": 7
+  },
+  "pft_mask_config": {
+    "mask_absent_pfts": true,
+    "pft_presence_threshold": 0.0
+  },
+  "pft_zero_sparsity_config": {
+    "weight": 1.0,
+    "threshold": 1e-8
+  },
+  "pft_zero_sparsity_weights": {
+    "cpool": 2,
+    "deadstemc": 1,
+    "deadcrootc": 1,
+    "livestemc": 1,
+    "livecrootc": 1
+  },
+  "pft1d_activation_overrides": {
+    "cpool": "abs",
+    "deadstemc": "abs",
+    "deadcrootc": "abs",
+    "livestemc": "abs",
+    "livecrootc": "abs"
+  }
+}

config/training_config_experiment_2_repeat.json

@@ -0,0 +1,135 @@
+{
+  "_description": "Repeat of run_20260212_162802_experiment_2: 100 epochs, AdamW, cosine scheduler. Use this config (with same variable list) to reproduce experiment_2 behavior.",
+  "training_hyperparameters": {
+    "num_epochs": 100,
+    "batch_size": 128,
+    "learning_rate": 0.0001,
+    "optimizer_type": "adamw",
+    "weight_decay": 0.01,
+    "use_scheduler": true,
+    "scheduler_type": "cosine",
+    "scheduler_step_size": 10,
+    "scheduler_gamma": 0.1,
+    "xsmrpool_loss_weight": 10,
+    "litter_c_loss_weight": 1,
+    "litter_n_loss_weight": 1,
+    "litter_p_loss_weight": 1,
+    "scalar_loss_weight": 1,
+    "vector_loss_weight": 1,
+    "matrix_loss_weight": 1
+  },
+  "reproducibility_config": {
+    "random_seed": 42,
+    "strict_determinism": false,
+    "train_split": 0.8,
+    "normalization": "individual",
+    "dropout_p": null
+  },
+  "data_filtering_config": {
+    "tropical_only": true,
+    "tropical_lat_range": [-23.5, 23.5]
+  },
+  "variable_weights": {
+    "pft1d_weights": {
+      "cpool": 6,
+      "npool": 8,
+      "ppool": 8,
+      "totvegc": 6,
+      "leafc": 6,
+      "leafn": 6,
+      "leafp": 6,
+      "leafc_storage": 5,
+      "leafn_storage": 5,
+      "leafp_storage": 5,
+      "deadstemc": 6,
+      "deadstemn": 6,
+      "deadstemp": 5,
+      "frootc": 4,
+      "frootn": 4,
+      "frootp": 4,
+      "frootc_storage": 3,
+      "frootn_storage": 3,
+      "frootp_storage": 3,
+      "tlai": 4
+    },
+    "soil2d_weights": {
+      "primp_vr": 9,
+      "litr2c_vr": 8,
+      "litr2p_vr": 8,
+      "litr2n_vr": 8,
+      "soil1c_vr": 7,
+      "soil1n_vr": 7,
+      "soil1p_vr": 7,
+      "litr3n_vr": 5,
+      "labilep_vr": 5,
+      "secondp_vr": 2.5,
+      "solutinorganicp_vr": 5,
+      "litr3p_vr": 5
+    },
+    "scalar_weights": {
+      "GPP": 1.5,
+      "NPP": 1.5,
+      "AR": 1.2,
+      "HR": 1.2
+    }
+  },
+  "tail_aware_config": {
+    "loss": "log1p_mse",
+    "epsilon": 1e-8
+  },
+  "tail_aware_weights": {
+    "cpool": 6,
+    "deadstemc": 6,
+    "deadcrootc": 5,
+    "livestemc": 5,
+    "livecrootc": 5,
+    "npool": 8,
+    "ppool": 8,
+    "totvegc": 6,
+    "leafc": 6,
+    "leafn": 6,
+    "leafp": 6,
+    "leafc_storage": 5,
+    "leafn_storage": 5,
+    "leafp_storage": 5,
+    "deadstemp": 5,
+    "deadstemn": 6,
+    "frootc": 4,
+    "frootn": 4,
+    "frootp": 4,
+    "labilep": 5,
+    "labilep_vr": 5,
+    "primp_vr": 9,
+    "litr2c_vr": 8,
+    "litr2p_vr": 8,
+    "litr2n_vr": 8,
+    "litr3c_vr": 5,
+    "litr3p_vr": 5,
+    "litr3n_vr": 5,
+    "soil1c_vr": 7,
+    "soil1n_vr": 7,
+    "soil1p_vr": 7
+  },
+  "pft_mask_config": {
+    "mask_absent_pfts": true,
+    "pft_presence_threshold": 0
+  },
+  "pft_zero_sparsity_config": {
+    "weight": 1,
+    "threshold": 1e-8
+  },
+  "pft_zero_sparsity_weights": {
+    "cpool": 2,
+    "deadstemc": 1,
+    "deadcrootc": 1,
+    "livestemc": 1,
+    "livecrootc": 1
+  },
+  "pft1d_activation_overrides": {
+    "cpool": "abs",
+    "deadstemc": "abs",
+    "deadcrootc": "abs",
+    "livestemc": "abs",
+    "livecrootc": "abs"
+  }
+}