# Learning-Based Planning for Improving Science Return of Earth Observation Satellites

arXiv: https://arxiv.org/abs/2509.07997 · HTML: https://mlsanity.com/paper/2509.07997/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 0 of its 23 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 2 of 2)

- [Learning Potentials for Dynamic Matching and Application to Heart Transplantation](https://mlsanity.com/paper/2602.08878/) (2026)
- [Dynamic Targeting of Satellite Observations Using Supplemental Geostationary Satellite Data and Hierarchical Planning](https://mlsanity.com/paper/2603.06719/) (2026)

## Abstract (arXiv)

Earth observing satellites are powerful tools for collecting scientific information about our planet, however they have limitations: they cannot easily deviate from their orbital trajectories, their sensors have a limited field of view, and pointing and operating these sensors can take a large amount of the spacecraft's resources. It is important for these satellites to optimize the data they collect and include only the most important or informative measurements. Dynamic targeting is an emerging concept in which satellite resources and data from a lookahead instrument are used to intelligently reconfigure and point a primary instrument. Simulation studies have shown that dynamic targeting increases the amount of scientific information gathered versus conventional sampling strategies. In this work, we present two different learning-based approaches to dynamic targeting, using reinforcement and imitation learning, respectively. These learning methods build on a dynamic programming solution to plan a sequence of sampling locations. We evaluate our approaches against existing heuristic methods for dynamic targeting, showing the benefits of using learning for this application. Imitation learning performs on average 10.0% better than the best heuristic method, while reinforcement learning performs on average 13.7% better. We also show that both learning methods can be trained effectively with small amounts of data.