Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.18206 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911121077698560 |
|---|---|
| author | Chaturvedi, Ritvik |
| author_facet | Chaturvedi, Ritvik |
| contents | This project implements a ResNet-based pipeline for land use and land cover (LULC) classification on Sentinel-2 imagery, benchmarked across three heterogeneous GPUs. The workflow automates data acquisition, geospatial preprocessing, tiling, model training, and visualization, and is fully containerized for reproducibility. Performance evaluation reveals up to a 2x training speed-up on an NVIDIA RTX 3060 and a Tesla T4 compared to the Apple M3 Pro baseline, while maintaining high classification accuracy on the EuroSAT dataset. These results demonstrate the feasibility of deploying deep learning LULC models on consumer and free cloud GPUs for scalable geospatial analytics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18206 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Practical GPU Choices for Earth Observation: ResNet-50 Training Throughput on Integrated, Laptop, and Cloud Accelerators Chaturvedi, Ritvik Distributed, Parallel, and Cluster Computing Machine Learning 68T45, 86A32 I.2.10; I.5.4 This project implements a ResNet-based pipeline for land use and land cover (LULC) classification on Sentinel-2 imagery, benchmarked across three heterogeneous GPUs. The workflow automates data acquisition, geospatial preprocessing, tiling, model training, and visualization, and is fully containerized for reproducibility. Performance evaluation reveals up to a 2x training speed-up on an NVIDIA RTX 3060 and a Tesla T4 compared to the Apple M3 Pro baseline, while maintaining high classification accuracy on the EuroSAT dataset. These results demonstrate the feasibility of deploying deep learning LULC models on consumer and free cloud GPUs for scalable geospatial analytics. |
| title | Practical GPU Choices for Earth Observation: ResNet-50 Training Throughput on Integrated, Laptop, and Cloud Accelerators |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning 68T45, 86A32 I.2.10; I.5.4 |
| url | https://arxiv.org/abs/2508.18206 |