Supplementary data for "Deep learning for industrial processes: Forecasting amine emissions from a carbon capture plant"

A preliminary analysis of the data already has been discussed in 10.2139/ssrn.3812299.

Raw data

Raw measurement data is in the Excel files `day*_raw.xlsx`.

Model

Covariate and label scaler objects are serialized in joblib format in the following files:

• 20210812_y_transformer_co2_ammonia_reduced_feature_set
• 20210812_y_transformer__reduced_feature_set
• 20210812_x_scaler_reduced_feature_set

Checkpoints of the models are in the `*.pth.tar` files.  An example for loading the models is:

from pyprocessta.model.tcn import TCNModelDropout

model_cov = TCNModelDropout(
    input_chunk_length=8,
    output_chunk_length=1,
    num_layers=5,
    num_filters=16,
    kernel_size=6,
    dropout=0.3,
    weight_norm=True,
    batch_size=32,
    n_epochs=100,
    log_tensorboard=True,
    optimizer_kwargs={"lr": 2e-4},
)

model_cov.load_from_checkpoint('20210814_2amp_pip_model_reduced_feature_set_darts')

which assumes that the checkpoints are placed as `model_best.pth.tar` in a folder called `20210812_2amp_pip_model_reduced_feature_set_darts`.