FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation

Authors: Kun Chen, Peng Ye, Hao Chen, kang chen, Tao Han, Wanli Ouyang, Tao Chen, LEI BAI

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4 Experiments
Researcher Affiliation Collaboration 1 Fudan University 2 Shanghai Artificial Intelligence Laboratory
Pseudocode No The paper describes its model architecture and components, but does not provide structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/Open Earth Lab/FNP.
Open Datasets Yes We demonstrate the effectiveness of our methodology on the ERA5 dataset [27], a global atmospheric reanalysis archive... The ERA5 dataset can be downloaded from the official website of Climate Data Store (CDS) at https://cds.climate.copernicus.eu.
Dataset Splits Yes We divide the ERA5 data from 1979-2015 as the training set, 2016-2017 as validation set, and 2018 as test set.
Hardware Specification Yes The training is run on 4 NVIDIA Tesla A100 GPUs with a global batch size of 16, and takes approximately 2.5 days. The inference only needs a few minutes to perform data assimilation for a whole year on single A100 GPU.
Software Dependencies No The paper mentions implementing the model based on the 'neural processes family project' and using the 'AdamW optimizer', but does not specify version numbers for general software libraries or programming languages.
Experiment Setup Yes The FNP model is implemented based on the open-source code of the neural processes family project [14], and trained for 20 epochs using the AdamW optimizer [39] with a learning rate of 1e-4... The dimension of data embedding for default setting is 128 and the number N of NFLs is 4, and a Gaussian likelihood is used with a negative log-likelihood (NLL) loss.