Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917323332386816 |
|---|---|
| author | Dollinger, Johannes Robert, Damien Plekhanova, Elena Drees, Lukas Wegner, Jan Dirk |
| author_facet | Dollinger, Johannes Robert, Damien Plekhanova, Elena Drees, Lukas Wegner, Jan Dirk |
| contents | Deep learning on climatic data holds potential for macroecological applications. However, its adoption remains limited among scientists outside the deep learning community due to storage, compute, and technical expertise barriers. To address this, we introduce Climplicit, a spatio-temporal geolocation encoder pretrained to generate implicit climatic representations anywhere on Earth. By bypassing the need to download raw climatic rasters and train feature extractors, our model uses x3500 less disk space and significantly reduces computational needs for downstream tasks. We evaluate our Climplicit embeddings on biomes classification, species distribution modeling, and plant trait regression. We find that single-layer probing our Climplicit embeddings consistently performs better or on par with training a model from scratch on downstream tasks and overall better than alternative geolocation encoding models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks Dollinger, Johannes Robert, Damien Plekhanova, Elena Drees, Lukas Wegner, Jan Dirk Computer Vision and Pattern Recognition Deep learning on climatic data holds potential for macroecological applications. However, its adoption remains limited among scientists outside the deep learning community due to storage, compute, and technical expertise barriers. To address this, we introduce Climplicit, a spatio-temporal geolocation encoder pretrained to generate implicit climatic representations anywhere on Earth. By bypassing the need to download raw climatic rasters and train feature extractors, our model uses x3500 less disk space and significantly reduces computational needs for downstream tasks. We evaluate our Climplicit embeddings on biomes classification, species distribution modeling, and plant trait regression. We find that single-layer probing our Climplicit embeddings consistently performs better or on par with training a model from scratch on downstream tasks and overall better than alternative geolocation encoding models. |
| title | Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05089 |