On-board efficiency: comparing compressed deep learning and classical models for Earth observation
TL;DR
A unified experimental framework is introduced that jointly evaluates compressed deep learning models and CML ensembles on two representative EO benchmarks and provides empirical guidance for selecting model families and compression strategies when designing future on-board EO systems.
Abstract
On-board processing is emerging as a key enabler for Earth observation (EO) missions, reducing downlink requirements and supporting more autonomous, event-driven operations. Deep convolutional neural networks (CNNs) deliver state-of-the-art performance on many EO tasks, but their memory footprint and computational demands remain challenging for space-qualified hardware. Classical machine learning (CML) pipelines based on hand-crafted spectral and textural features offer a lighter alternative, yet it is unclear how they compare with modern compressed deep models under deployment-relevant efficiency metrics. This work introduces a unified experimental framework that jointly evaluates compressed deep learning (CDL) models and CML ensembles on two representative EO benchmarks: EuroSAT for land-cover classification and HYPERVIEW for hyperspectral soil-property regression. Starting from a common CNN baseline, we evaluate pruning and post-training quantization, and use the selected baseline as the teacher in family-conditioned KD experiments. We contrast the resulting models with optimized tree-based ensembles trained on engineered features. For the benchmark comparisons we measure predictive efficacy, inference time and serialized model size, enabling a systematic comparison of the trade-offs between accuracy, runtime and storage. In our experiments, quantization provides the largest observed storage reduction among the tested CDL variants, moderate pruning can preserve predictive performance more closely in some settings, and the effectiveness of knowledge distillation depends more strongly on the dataset, student design, and distillation setting. Classical ensembles remain attractive when low prediction-stage latency or small serialized models are required and a moderate loss in accuracy is acceptable. For raw-input deployment, their runtime benefit also depends on the cost and implementation of descriptor extraction. The proposed analysis provides empirical guidance for selecting model families and compression strategies when designing future on-board EO systems.