# Mapping on a Budget: Optimizing Spatial Data Collection for ML

arXiv: https://arxiv.org/abs/2509.03749 · HTML: https://mlsanity.com/paper/2509.03749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [Data Banzhaf: A Robust Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2205.15466/) (2022)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data](https://mlsanity.com/paper/2103.03399/) (2021)
- [Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters](https://mlsanity.com/paper/2305.13456/) (2023)
- [Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning](https://mlsanity.com/paper/1907.07319/) (2019)
- [Adaptive Sampling Strategies to Construct Equitable Training Datasets](https://mlsanity.com/paper/2202.01327/) (2022)
- [Mapping oil palm density at country scale: An active learning approach](https://mlsanity.com/paper/2105.11207/) (2021)
- [Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images](https://mlsanity.com/paper/2110.07782/) (2021)
- [Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy](https://mlsanity.com/paper/2305.01783/) (2023)
- [Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?](https://mlsanity.com/paper/2211.08735/) (2022)

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

- [Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance](https://mlsanity.com/paper/2604.21104/) (2026)
- [Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture](https://mlsanity.com/paper/2609.31201/) (2026)

## Abstract (arXiv)

In applications across agriculture, ecology, and human development, machine learning with satellite imagery (SatML) is limited by the sparsity of labeled training data. While satellite data cover the globe, labeled training datasets for SatML are often small, spatially clustered, and collected for other purposes (e.g., administrative surveys or field measurements). Despite the pervasiveness of this issue in practice, past SatML research has largely focused on new model architectures and training algorithms to handle scarce training data, rather than modeling data conditions directly. This leaves scientists and policymakers who wish to use SatML for large-scale monitoring uncertain about whether and how to collect additional data to maximize performance. Here, we present the first problem formulation for the optimization of spatial training data in the presence of heterogeneous data collection costs and realistic budget constraints, as well as novel methods for addressing this problem. In experiments simulating different problem settings across three continents and four tasks, our strategies reveal substantial gains from sample optimization. Further experiments delineate settings for which optimized sampling is particularly effective. The problem formulation and methods we introduce are designed to generalize across application domains for SatML; we put special emphasis on a specific problem setting where our coauthors can immediately use our findings to augment clustered agricultural surveys for SatML monitoring in Togo.