cs.LGJul 27, 2026

From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps

Authors: Ghjulia SialelliRobin YoungYuchang JiangCesar AybarLinus ScheibenreifDamien RobertClemens MosigAdam J. Stewart+4 more

Organizations: Photogrammetry and Remote Sensing, ETH Zurich, Switzerland · ETH AI Center, Zurich, Switzerland · Dept. of Computer Science and Technology, University of Cambridge, UK · Land Change Science, Swiss Federal Research Institute WSL, Switzerland · Asterisk Labs, UK · EcoVision Lab, University of Zurich, Switzerland · Inst. for Earth System Science and Remote Sensing, Leipzig University, Germany · Chair of Data Science in Earth Observation, TU Munich, Germany · RISE Research Institutes of Sweden · Climes, Swedish Centre for Impacts of Climate Extremes · Climate AI Nordics

Abstract

Recent years have seen a rapid expansion in the production of large-scale geospatial maps derived from Earth observation (EO) data, driven largely by advances in machine learning (ML) and large computing infrastructure. Although the barrier to generating such maps has dropped substantially, established best practices have yet to emerge, and design decisions made early in the pipeline can quietly propagate errors into the final product. Producing a technically sound and scientifically credible product remains challenging. Choices made at every stage are tightly coupled: preprocessing decisions shape the training signal, dataset design governs what the model can learn and how reliably its performance can be assessed, and global-scale inference introduces engineering challenges in compute and data access at scale, as well as artifact mitigation. Furthermore, uncertainty quantification and independent map validation each require dedicated methodological attention that is often underestimated. This paper presents a concise, end-to-end account of the recommended practices spanning the pipeline from satellite data to an operational map product. We organize the discussion around six interconnected themes: the EO data infrastructure landscape, data selection and preprocessing, ML dataset construction and model training, uncertainty quantification, map production and distribution, and validation. This paper is a condensed version of a longer guide that provides greater depth across all stages, accessible online at ghjuliasialelli.github.io/ML-EO-Maps/.

Explore similar work

CardsList
  1. Earth Embeddings

    Aug 4, 2026Adam J. Stewart, Heng Fang, Isaac A. Corley +1Cloud-Aware Earth Observation SequencesEarth Observation