Contract-Governed Training for Earth Observation: Observed Service Agreement Graphs and Coverage-Accuracy Trade-offs
This addresses the issue of ensuring fair and targeted service for specific regions or classes in Earth observation models, representing a novel method for a known bottleneck in training governance.
The paper tackles the problem of Earth observation models lacking explicit guarantees on which regions or classes are served during training by introducing a contract-governed training paradigm with Observed Service Agreement Graphs (OSAG). The result is that OSAG substantially reduces priority coverage error while maintaining global accuracy and improving high-priority accuracy, as demonstrated on datasets like AVIRIS hyperspectral scenes and Sentinel-2 EuroSAT.
Earth observation (EO) models are frequently trained under implicit sampling policies that optimize global accuracy but provide no explicit guarantees on who (which regions, classes, or mission-critical strata) is being served throughout training. This paper introduces a contract-governed training paradigm for EO in which training samples are grouped into service contracts -- semantically meaningful units such as (dataset, region, rare-crop indicator) -- and each contract is assigned a target service share. We instantiate this paradigm as an Observed Service Agreement Graph (OSAG), a lightweight governance layer that (i) monitors contract-level exposure (coverage) during optimization, (ii) drives empirical coverage toward target shares via contract-normalized sampling weights, and (iii) exposes explicit accuracy-governance trade-offs through two knobs: a sampling mixture coefficient alpha and a contract-regularization weight lambda_C. We provide a compact theory in a toy setting: OSAG sampling concentrates empirical coverage to targets; coverage deviations upper-bound service-risk deviations; and contract design (coarse vs. fine) modulates governance cost. Experiments on AVIRIS hyperspectral scenes (Indian Pines plus Salinas) and multispectral Sentinel-2 EuroSAT demonstrate that OSAG can substantially reduce priority coverage error while maintaining global accuracy and improving high-priority accuracy. A EuroSAT coarse-vs-fine contract ablation further evidences how semantically refined contracts can reduce the accuracy cost per unit of governance improvement.