add README

README.md

@@ -1 +1,53 @@
-# AI Sustainability Catalog
+# AI Sustainability Hub
+
+Welcome to the **AI Sustainability Hub**! This repository provides a collection of resources related to AI and sustainability, including datasets, models, publications, and tools. Our goal is to support and advance research in the intersection of artificial intelligence and environmental sustainability.
+
+## Sections
+
+### Datasets
+Discover a range of datasets focused on climate change, environmental monitoring, and more. For the latest datasets, please refer to `public/datasets.yml`. 
+
+### Models
+Explore AI models designed to address sustainability challenges:
+- **Aurora**: An atmospheric model for weather forecasting. [Learn more](https://www.microsoft.com/en-us/research/publication/aurora-a-foundation-model-of-the-atmosphere/)
+- **Pangu-Weather**: A medium-range weather forecasting model. [Learn more](https://www.nature.com/articles/s41586-023-06185-3)
+
+### Publications
+Access key papers and reports in the field:
+- **PCT-CycleGAN**: Radar-based precipitation nowcasting. [Read more](https://dl.acm.org/doi/abs/10.1145/3583780.3615006)
+- **TIP-GAN**: Discovery of climate tipping points. [Read more](https://arxiv.org/abs/2302.10274)
+
+### Tools
+Utilize tools for AI and sustainability projects:
+- **Climate Prediction Toolkit**: Tools for climate modeling. [Explore](https://www.climateprediction.net/)
+- **Virtual Earth System Laboratory**: Real-time simulations of earth processes. [Discover](https://sealevel.nasa.gov/data_tools/2/)
+
+# Development Commands
+
+To set up and run the development environment, use the following commands:
+
+### Node.js (npm)
+
+- **Install Dependencies:**
+  ```bash
+  npm install
+  ```
+- **IRun Development Server:**
+  ```bash
+  npm run dev
+  ```
+
+## Contributing
+We welcome contributions to improve this repository. For guidelines on how to contribute, please see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+
+## License
+This project is licensed under the [MIT License](LICENSE).
+
+## Contact
+For any questions or support, please contact us at [[email protected]](mailto:[email protected]).
+
+---
+
+**Note:** To add new datasets,models,publications and tools please update the `public/datasets.yml` file accordingly.
+

public/datasets.yml

@@ -119,7 +119,6 @@ datasets:
     subcategory: Disaster Response
     subsubcategory: Emergency Management Data
 
-
 models:
   - name: Aurora
     description: A foundation model of the atmosphere, pre-trained on large-scale atmospheric data for various weather tasks.
@@ -298,8 +297,6 @@ models:
       paper: https://ieeexplore.ieee.org/document/9342115
       code_and_weights: null
 
-  # Additional Models for Remaining Categories
-
   - name: SolarNet
     description: Deep learning model designed for predicting solar energy production from meteorological data.
     category: Renewable Energy
@@ -366,8 +363,6 @@ models:
       paper: https://iopscience.iop.org/article/10.1088/1748-9326/acf33d
       code: https://github.com/eco-net/eco-net
 
-# new data 
-
   - name: SeCo
     description: Seasonal Contrast- Unsupervised Pre-Training From Uncurated Remote Sensing Data.
     category: Remote Sensing
@@ -463,7 +458,7 @@ models:
     publication: RS2022
     year: 2022
     resource:
-      paper: https://www.mdpi.com/2072-4292/14/22/5675#
+      paper: https://www.mdpi.com/2072-4292/14/22/5675
       code: https://github.com/ZhAnGToNG1/transfer_learning_cspt
 
 
@@ -705,7 +700,7 @@ models:
     year: 2023
     resource:
       paper: https://arxiv.org/abs/2312.16385
-      code: https://engine-aiearth.aliyun.com/#/  
+      code: https://engine-aiearth.aliyun.com/
 
 
   - name: SAR-JEPA
@@ -993,8 +988,6 @@ models:
       paper: https://arxiv.org/abs/2408.08447
       code: null
 
-# Remote Sensing Vision Language
-
   - name: RSGPT
     description: A Remote Sensing Vision Language Model and Benchmark.
     category: Remote Sensing Vision Language
@@ -1017,7 +1010,6 @@ models:
       paper: https://arxiv.org/abs/2306.11029
       code: https://github.com/ChenDelong1999/RemoteCLIP
 
-
   - name: GeoRSCLIP
     description: RS5M- A Large Scale Vision-Language Dataset for Remote Sensing Vision-Language Foundation Model.
     category: Remote Sensing Vision Language
@@ -1153,8 +1145,6 @@ models:
       paper: https://github.com/Jack-bo1220/Awesome-Remote-Sensing-Foundation-Models/tree/main
       code: https://github.com/Luo-Z13/SkySenseGPT
 
-# Remote Sensing Generative Foundation Models
-
   - name: Seg2Sat
     description: Segmentation to aerial view using pretrained diffuser models.
     category: Remote Sensing Generative Foundation
@@ -1222,7 +1212,7 @@ models:
       paper: https://arxiv.org/abs/2405.13570
       code: https://jiupinjia.github.io/metaearth/
 
-# Remote Sensing Vision-Location Foundation Models
+
 
   - name: CSP
     description: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations.
@@ -1258,7 +1248,7 @@ models:
       code: https://github.com/microsoft/satclip
 
 
-# Remote Sensing Vision-Audio Foundation Models
+
 
   - name: SARL
     description: Self-supervised audiovisual representation learning for remote sensing data.
@@ -1272,7 +1262,7 @@ models:
       code:  https://github.com/khdlr/SoundingEarth
 
 
-# Remote Sensing Task-specific Foundation Models
+
 
   - name: SS-MAE
     description: Spatial-Spectral Masked Auto-Encoder for Mulit-Source Remote Sensing Image Classification.
@@ -1397,7 +1387,7 @@ models:
       code: https://github.com/htcr/sam_road
 
 
-# Remote Sensing Agents
+
 
   - name: GeoLLM-QA
     description: Evaluating Tool-Augmented Agents in Remote Sensing Platforms.
@@ -1421,7 +1411,7 @@ models:
       paper: https://arxiv.org/abs/2406.07089
       code: null
 
-# Benchmarks for RSFMs
+
 
   - name: RPRSMB
     description: Revisiting pre-trained remote sensing model benchmarks- resizing and normalization matters.
@@ -1514,9 +1504,6 @@ models:
       paper: https://arxiv.org/abs/2406.12384
       code: https://vrsbench.github.io/
 
-
-# end
-
 publications:
   - title: PCT-CycleGAN Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting
     venue: 32nd ACM International Conference on Information and Knowledge Management