EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatiotemporal Deep Learning for Continuous Illumination Mapping and Sun-Synchronous Path Planning in Lunar Polar Exploration Under Chang’E-7 Mission Constraints

Yang Chen, Hao Zhang, Jianfeng Lu, Guangfei Wei

Remote Sensing · 02.09.2026 · 18 (17) · 2950

DOI: 10.3390/rs18172950 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.09.2026. Verfasst von Yang Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Natural Science Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The lunar south polar region’s extreme illumination conditions impose strict energy constraints for solar-powered rover operations. Traditional Sun-synchronous path planning relies on dynamic time-dependent illumination evaluation, leading to high computational costs. We present CIRsE-Net, a spatiotemporal deep learning model that generates 72 h continuous illumination maps from hourly sequential illumination data. The model integrates a lightweight SST-VGG encoder (a customized 14-layer CNN for spatial feature extraction), BiGRU temporal modelling (a bidirectional recurrent network for capturing forward and backward temporal dependencies), and a consistency-aware spatiotemporal attention mechanism. On three different lunar illumination datasets (20 m/pixel, 5 m/pixel, and 20 m/pixel with a 2 m panel height), the model achieves Dice scores up to 0.983 and accuracy up to 0.985. When integrated with an enhanced 3ST-A* planner, the framework converts dynamic path planning into a static search task, reducing computational overhead while preserving path optimality and satisfying slope and illumination constraints. This work provides a validated methodological framework for Chang’E-7 mission planning and future lunar polar exploration missions by transforming dynamic path planning into a static search task.

Förderung

  • Anhui Natural Science Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Chen, Y., Zhang, H., Lu, J., & Wei, G. (2026). Spatiotemporal Deep Learning for Continuous Illumination Mapping and Sun-Synchronous Path Planning in Lunar Polar Exploration Under Chang’E-7 Mission Constraints. Remote Sensing, 18(17), 2950. https://doi.org/10.3390/rs18172950

Vancouver

Chen Y, Zhang H, Lu J, Wei G. Spatiotemporal Deep Learning for Continuous Illumination Mapping and Sun-Synchronous Path Planning in Lunar Polar Exploration Under Chang’E-7 Mission Constraints. Remote Sensing. 2026;18(17):2950. doi:10.3390/rs18172950

BibTeX
@article{Chen2026,
  author = {Chen, Yang and Zhang, Hao and Lu, Jianfeng and Wei, Guangfei},
  title = {Spatiotemporal Deep Learning for Continuous Illumination Mapping and Sun-Synchronous Path Planning in Lunar Polar Exploration Under Chang’E-7 Mission Constraints},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {17},
  pages = {2950},
  doi = {10.3390/rs18172950}
}
Kostenlos starten →