# Scaling Remote Sensing Foundation Models: Data Domain Tradeoffs at the Peta-Scale

arXiv: https://arxiv.org/abs/2512.23903 · HTML: https://mlsanity.com/paper/2512.23903/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 14 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://mlsanity.com/paper/2412.02732/) (2024)
- [Revisiting Neural Scaling Laws in Language and Vision](https://mlsanity.com/paper/2209.06640/) (2022)
- [Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective](https://mlsanity.com/paper/2410.05192/) (2024)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [A Billion-scale Foundation Model for Remote Sensing Images](https://mlsanity.com/paper/2304.05215/) (2023)
- [Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing](https://mlsanity.com/paper/2401.15855/) (2024)

## Built on by (most cited first, 1 of 1)

- [TESSERA v2: Scaling Pixel-wise Earth Foundation Models](https://mlsanity.com/paper/2607.03949/) (2026)

## Abstract (arXiv)

We explore the scaling behaviors of artificial intelligence to establish practical techniques for training foundation models on high-resolution electro-optical (EO) datasets that exceed the current state-of-the-art scale by orders of magnitude. Modern multimodal machine learning (ML) applications, such as generative artificial intelligence (GenAI) systems for image captioning, search, and reasoning, depend on robust, domain-specialized encoders for non-text modalities. In natural image domains where internet-scale data is plentiful, well-established scaling laws help optimize the joint scaling of model capacity, training compute, and dataset size. Unfortunately, these relationships are much less well understood in high-value domains like remote sensing (RS). Using over a quadrillion pixels of commercial satellite EO data and MITRE's Federal AI Sandbox, we train progressively larger vision transformer (ViT) backbones, report successes and failure modes observed at peta-scale, and analyze implications for bridging domain gaps across additional RS modalities. We observe that even at this scale, performance is consistent with a data-limited regime rather than a model parameter-limited one. These practical insights are intended to inform data collection strategies, compute budgets, and optimization schedules that advance the future development of frontier scale RS foundation models.