Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub
Most deep learning application studies have limited accessibility and reproducibility for researchers and students in many domains, especially in earth and climate sciences. In order to provide a step towards improving the accessibility of deep learning models in such disciplines, this study present...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/3185 |
| _version_ | 1797615746394619904 |
|---|---|
| author | Muhammed Sit Ibrahim Demir |
| author_facet | Muhammed Sit Ibrahim Demir |
| author_sort | Muhammed Sit |
| collection | DOAJ |
| description | Most deep learning application studies have limited accessibility and reproducibility for researchers and students in many domains, especially in earth and climate sciences. In order to provide a step towards improving the accessibility of deep learning models in such disciplines, this study presents a community-driven framework and repository, EarthAIHub, that is powered by TensorFlow.js, where deep learning models can be tested and run without extensive technical knowledge. In order to achieve this, we present a configuration data specification to form a middleware, an abstraction layer, between the framework and deep learning models. Once an easy-to-create configuration file is generated for a model by the user, EarthAIHub seamlessly makes the model publicly available for testing and access using a web platform. The platform and community-enabled model repository will benefit students and researchers who are new to the deep learning domain by enabling them to access and test existing models in the community with their datasets, and researchers to share their novel deep learning models with the community. The platform will help researchers test models before adapting them to their research and learn about a model’s details and performance. |
| first_indexed | 2024-03-11T07:31:03Z |
| format | Article |
| id | doaj.art-bce412cc628744a3bb8aef5b9d5220c0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:31:03Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-bce412cc628744a3bb8aef5b9d5220c02023-11-17T07:20:27ZengMDPI AGApplied Sciences2076-34172023-03-01135318510.3390/app13053185Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHubMuhammed Sit0Ibrahim Demir1IIHR–Hydroscience & Engineering, University of Iowa, Iowa City, IA 52242, USAIIHR–Hydroscience & Engineering, University of Iowa, Iowa City, IA 52242, USAMost deep learning application studies have limited accessibility and reproducibility for researchers and students in many domains, especially in earth and climate sciences. In order to provide a step towards improving the accessibility of deep learning models in such disciplines, this study presents a community-driven framework and repository, EarthAIHub, that is powered by TensorFlow.js, where deep learning models can be tested and run without extensive technical knowledge. In order to achieve this, we present a configuration data specification to form a middleware, an abstraction layer, between the framework and deep learning models. Once an easy-to-create configuration file is generated for a model by the user, EarthAIHub seamlessly makes the model publicly available for testing and access using a web platform. The platform and community-enabled model repository will benefit students and researchers who are new to the deep learning domain by enabling them to access and test existing models in the community with their datasets, and researchers to share their novel deep learning models with the community. The platform will help researchers test models before adapting them to their research and learn about a model’s details and performance.https://www.mdpi.com/2076-3417/13/5/3185deep learningtensorflowneural networksweb applicationcitizen sciencescientific communication |
| spellingShingle | Muhammed Sit Ibrahim Demir Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub Applied Sciences deep learning tensorflow neural networks web application citizen science scientific communication |
| title | Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub |
| title_full | Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub |
| title_fullStr | Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub |
| title_full_unstemmed | Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub |
| title_short | Democratizing Deep Learning Applications in Earth and Climate Sciences on the Web: EarthAIHub |
| title_sort | democratizing deep learning applications in earth and climate sciences on the web earthaihub |
| topic | deep learning tensorflow neural networks web application citizen science scientific communication |
| url | https://www.mdpi.com/2076-3417/13/5/3185 |
| work_keys_str_mv | AT muhammedsit democratizingdeeplearningapplicationsinearthandclimatesciencesonthewebearthaihub AT ibrahimdemir democratizingdeeplearningapplicationsinearthandclimatesciencesonthewebearthaihub |