| --- |
| language: |
| - en |
| license: gemma |
| library_name: jax |
| pipeline_tag: image-text-to-text |
| tags: |
| - gemma |
| - earth-observation |
| - remote-sensing |
| - satellite-imagery |
| - lora |
| - jax |
| - tunix |
| base_model: google/gemma-3-4b-it |
| datasets: |
| - akshaydudhane/EarthDial-Dataset |
| metrics: |
| - exact_match |
| - precision |
| - recall |
| - f1 |
| - jaccard |
| --- |
| |
| # Gemma Earth (Gemma 3 4B IT LoRA for Earth Observation) |
|
|
| ## Model Description |
|
|
| Gemma Earth is a domain-adapted Earth Observation model built by fine-tuning Google Gemma 3 4B IT with LoRA adapters for satellite scene understanding. |
|
|
| The current release focuses on multi-label land-use and land-cover classification from the EarthDial BigEarthNet subset, with a pipeline designed to extend to additional EarthDial tasks. |
|
|
| This project provides an end-to-end JAX stack pipeline for dataset preparation, LoRA fine-tuning, checkpointing, evaluation, and inference serving. |
|
|
| Project repository: https://github.com/haruiz/gemma_earth |
| |
| - Base model: google/gemma-3-4b-it |
| - Adaptation: LoRA |
| - Training stack: JAX + Flax (NNX) + Tunix + Qwix + Optax + Orbax + Grain |
| - Primary task: remote-sensing scene classification (multi-label) |
| |
| ## Intended Use |
| |
| ### Primary Use |
| |
| - Earth Observation and remote-sensing research |
| - Multi-label scene classification on EarthDial/BigEarthNet-style samples |
| - Benchmarking and experimentation with TPU-based JAX fine-tuning workflows |
| |
| |
| |
| ## Training Data |
| |
| - Dataset source: akshaydudhane/EarthDial-Dataset |
| - Current focus: EarthDial classification subset (BigEarthNet) |
| - Training setup in this project uses sampled subsets and validation splits configured via environment variables |
| |
| ## Training Procedure |
| |
| - Hardware: Google Cloud TPU v5litepod-8 |
| - LoRA configuration (default project setup): |
| - Rank: 32 |
| - Alpha: 64.0 |
| - Typical sequence length: 768 |
| - Optimizer schedule includes warmup + decay (Optax) |
| |
| ## Evaluation Summary |
| |
| Benchmark run size: 1500 samples |
| |
| | Metric | Baseline | Fine-tuned | Delta (absolute) | |
| | --- | ---: | ---: | ---: | |
| | Exact Match | 2.53% | 22.80% | +20.27 pp | |
| | Sample Precision | 27.27% | 68.53% | +41.27 pp | |
| | Sample Recall | 10.35% | 71.86% | +61.51 pp | |
| | Sample F1 | 14.18% | 68.16% | +53.98 pp | |
| | Sample Jaccard | 10.35% | 57.47% | +47.12 pp | |
| | Micro Precision | 29.57% | 63.56% | +33.99 pp | |
| | Micro Recall | 9.25% | 67.00% | +57.75 pp | |
| | Micro F1 | 14.09% | 65.24% | +51.15 pp | |
| | Macro F1 | 6.53% | 31.50% | +24.97 pp | |
| |
| The adapted model significantly improves over baseline across all reported metrics. |
| |
| ## How To Use |
| |
| This model is intended to be used with the Gemma Earth codebase. |
| |
| ~~~bash |
| # Example: run one-image evaluation using a Hugging Face checkpoint directory |
| python scripts/one_example_eval.py \ |
| --model-checkpoint-source huggingface \ |
| --model-dir /path/to/hf_checkpoint_dir \ |
| --image-path /path/to/image.jpg |
| ~~~ |
| |
| ~~~bash |
| # Example: run benchmark evaluation with Hugging Face checkpoint source |
| python main.py benchmark \ |
| --num-examples 1500 \ |
| --eval-restore-policy permissive \ |
| --model-checkpoint-source huggingface |
| ~~~ |
| ## Citation |
| |
| If you use this model, please cite: |
| |
| ~~~bibtex |
| @misc{gemma_earth_2026, |
| title={Gemma Earth: Fine-tuning Gemma for Remote Sensing Scene Classification}, |
| author={Henry Ruiz}, |
| year={2026}, |
| howpublished={GitHub repository}, |
| url={https://github.com/haruiz/gemma_earth}, |
| } |
| ~~~ |
| |
| Related references: |
| |
| ~~~bibtex |
| @misc{soni2024earthdial, |
| title={EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues}, |
| author={Soni, Sagar and Dudhane, Akshay and Debary, Hiyam and Fiaz, Mustansar and Munir, Muhammad Akhtar and Danish, Muhammad Sohail and Fraccaro, Paolo and Watson, Campbell D and others}, |
| year={2024}, |
| eprint={2412.15190}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV}, |
| doi={10.48550/arXiv.2412.15190}, |
| url={https://arxiv.org/abs/2412.15190} |
| } |
|
|
| @misc{sumbul2019bigearthnet, |
| title={BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding}, |
| author={Sumbul, Gencer and Charfuelan, Marcela and Demir, Beg{"u}m and Markl, Volker}, |
| year={2019}, |
| eprint={1902.06148}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CV}, |
| doi={10.48550/arXiv.1902.06148}, |
| url={https://arxiv.org/abs/1902.06148} |
| } |
| ~~~ |
| |
| ## Model And License Notes |
| |
| This model is derived from Gemma 3 4B IT. Use must comply with the Gemma license and any applicable dataset terms. |
| |
