Data for manuscript "Emulator-based calibration of a dynamic grassland model using recurrent neural networks and Hamiltonian Monte Carlo" by Aakula et al.

DOI

Data and python code for the manuscript "Emulator-based calibration of a dynamic grassland model using recurrent neural networks and Hamiltonian Monte Carlo", for performing emulator hyperparameter optimization and training. Python file optimize_LSTM_emulator.py can be used either for training an LSTM emulator with predefined hyperparameters or to optimize hyperparameters from a given hyperparameter space. The training data for each fold is included in the files of shape training_data_fold_{}.parquet. The data is obtained from model simulations, including model inputs (meteorological forcings obtained from ERA5 data), model parameters (sampled from distributions defined in the manuscript) and model (BASGRA) outputs. Text file examples.txt gives instructions and examples on running the script.

Identifier
DOI https://doi.org/10.57707/fmi-b2share.bac65edfcadb459b89248090d2412240
Source https://fmi.b2share.csc.fi/records/bac65edfcadb459b89248090d2412240
Metadata Access https://fmi.b2share.csc.fi/api/oai2d?verb=GetRecord&metadataPrefix=eudatcore&identifier=oai:b2share.eudat.eu:b2rec/bac65edfcadb459b89248090d2412240
Provenance
Creator Viivi Aakula
Publisher Finnish Meteorological Institute
Contributor Viivi Aakula; Julius Vira
Publication Year 2025
Funding Reference Research Council of Finland; Strategic Research Council at the Research Council of Finland; Ministry of Agriculture and Forestry of Finland; Business Finland; EU Horizon Europe; European Union – NextGenerationEU
Rights CC-BY; info:eu-repo/semantics/openAccess
OpenAccess true
Contact viivi.aakula(at)fmi.fi
Representation
Language English
Resource Type Dataset
Format parquet; txt; py
Size 383.3 MB; 7 files
Discipline Environmental science
Spatial Coverage (-20.000W, 35.000S, 60.000E, 72.000N)
Temporal Coverage 1941-04-30T22:00:00.000Z 2023-04-30T21:00:00.000Z