Impact of Atmospheric Turbulence and Pointing Error on Earth Observation

2026-05-21

AI Summary

This study addresses the degradation of Earth observation imagery caused by atmospheric turbulence and platform jitter—factors commonly overlooked in training data for existing object detection models. The work proposes the first integrated simulation framework that systematically incorporates vertical-path atmospheric turbulence and satellite pointing errors into the image generation pipeline, producing physically realistic degraded imagery. Using this generator, the robustness of YOLOv8 and RetinaNet is rigorously evaluated under varying levels of degradation. Experimental results demonstrate a significant performance gap: under severe degradation, YOLOv8’s recall drops below 40%, whereas RetinaNet maintains approximately 75% recall. These findings underscore the critical importance of incorporating physically accurate degradation models during training to enhance the real-world deployment performance of object detectors in remote sensing applications.

Abstract

Earth Observation (EO) imagery is often degraded by atmospheric turbulence and pointing jitter; yet, these effects are rarely considered in datasets used to train AI-based detection models. Based on prior work, this paper presents an enhanced image simulator that enables the incorporation of vertical-path atmospheric turbulence and satellite pointing jitter, arising from platform and sensor vibrations, to generate physically realistic distorted images. As a case study, vessel detection is evaluated using YOLOv8 and RetinaNet on images generated by the proposed simulator under different levels of turbulence and pointing errors. Results show that YOLOv8 recall decreases from 91% under ideal conditions to 60% in the presence of weak turbulence, and falls below 40% under strong turbulence or jitter. In contrast, RetinaNet demonstrates greater robustness, maintaining approximately 75% recall across degraded conditions. These results highlight the importance of incorporating realistic physical degradations into EO training datasets to ensure reliable performance of AI-based models in operational environments, as demonstrated in maritime surveillance applications.

Problem

• atmospheric turbulence
• pointing error
• Earth Observation
• AI-based detection
• image degradation

Innovation

• atmospheric turbulence
• pointing error
• image simulation
• Earth Observation
• YOLOv8