Skip to content

Zjut-MultimediaPlus/PRE-Net

Repository files navigation

PRE-Net

Overview

This repository contains the code for the research presented in the paper [From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion] accecpted by 2025 KDD. This task leverages the complementary strengths of multimodal data (IR, PMW, and PR) to address the constraints of narrow coverage and enhance retrieval accuracy. It includes the code for training and testing the model, as well as the necessary scripts and configurations for easy execution.

Dataset & Model Weights

The dataset and pre-trained model weights for this project are not included in the repository due to their large size. You can download them from the following links:

Please follow the instructions in the links to download and place the files in the appropriate directory (e.g., data/ for dataset, checkpoints/ for model weights).

Usage

Training

To train the model, run the train.sh script. This will automatically start the training process with the available dataset.

bash train.sh

Testing

After training, you can use the test.sh script to evaluate the model performance on the test dataset.

bash test.sh

Citation

If you use this code in your research, please cite the following paper:

@article{wang2025swath,
  title={From swath to full-disc: Advancing precipitation retrieval with multimodal knowledge expansion},
  author={Wang, Zheng and Ying, Kai and Xu, Bin and Wang, Chunjiao and Bai, Cong},
  booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2},
  pages={3091--3101},
  year={2025}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published