AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal oceans
This repository contains the code for the STIMP method, an advanced AI framework to impute and predict Chl_a across a broad spatiotemporal scale in coastal oceans. STIMP's results can be utilized to diagnose and analyze the ecosystem health of coastal oceans based on the remote sensing measurement.
You can install the development version of STIMP:
git clone https://github.com/YangLabHKUST/STIMP.git
cd /path/to/STIMP
conda create -n stimp python=3.9
conda activate stimp
pip install -r requirements.txtThe code for reproducing the results presented in our paper are available on the tutorial website. To reproduce our resluts, it is necessary to first train STIMP and the baselines, which can be found in the tutorials:
- Train STIMP on each coastal ocean area
- Train baselines, including imputation methods and prediction methods, on each coastal ocean area
The resluts presented in our paper are available:
If you find the STIMP package or any of the source code in this repository useful for your work, please cite:
AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems.
Fan Zhang, Hiuseut Kung, Fa Zhang, Can Yang# and Jianping Gan#. 2025.
The python repository STIMP is developed and maintained by Fan Zhang.
Please feel free to contact Fan Zhang ([email protected]), Prof. Can Yang ([email protected]), or Prof. Jianping Gan ([email protected]) if any inquiries.