Skip to content
DraconiticResearch
Search Sources API
184,584 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BYInternational Journal of Applied Earth Observations and Geoinformation

Robust reinforcement learning multi-baseline phase unwrapping algorithm with JPEG-LS

  • Shiji Yang1
  • Wu Zhu
  • Hui Liu2
  • Ruixuan Zhang1
  • Haoran Gao1
  • Lei Xu3
  • Mengyuan Zhu3
  • Tong Yang4
4 affiliations
  1. 1College of Geological Engineering and Geomatics, Chang’an University, Xi’an 710054, China
  2. 2Advanced Research Institute for Digital-Twin Water Conservancy, North China University of Water Resources and Electric Power, Zhengzhou 450046, China
  3. 3College of Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China
  4. 4Yunnan Communications Investment & Construction Group Co., Ltd, Kunming 650000, China
Read full textDOICite

Abstract

Multi-baseline (MB) phase unwrapping (PU) breaks through the limitations of the phase continuity assumption, but existing MBPU algorithms cannot adapt well to noisy environments. A robust reinforcement learning integer programming multi-baseline PU algorithm with JPEG-LS (RL-MBPU) is proposed. First, the cutting plane–pure integer programming cut-selection process is formulated as a sequential reinforcement-learning problem. An efficacy-guided imitation strategy is used to initialize an MBPU-structure-aware single-cut policy, which is further optimized by an actor–critic method using Cut-PAR2-based trajectory returns to reduce the root-node proof cost. Finally, the initial ambiguity number solution is corrected using dynamic median edge detector based on JPEG-LS, and the PU is completed by using the prediction of the left, top, and top-left neighbors of the current pixel and combining it with the local gradient threshold determination. In both simulation and real data experiments, the RL-MBPU algorithm demonstrated stable PU performance, including computational efficiency and noise robustness for interferograms of different sizes. Compared with the minimum-cost flow and cutting plane–pure integer programming algorithms, the RL-MBPU algorithm reduces the root mean square error by approximately 61.2% and 14.5%, respectively, while improving efficiency by approximately 54.1% and 42.4%, respectively. This can further support high-precision interferometric synthetic aperture radar applications.

Related

  1. Meta reinforcement learning for robust quadruped locomotion under joint failures
    Likai Wu, Chee-Onn Chow, Wei Ru Wong +3
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceGeophysics & seismologyPLOS
  2. DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning
    Peng Jin, Yinan Feng, Yinpeng Chen +2
    arXivPreprintCC BY-NC-SA 4.0Full textGeophysics & seismologyarXiv
  3. DispSAC: Surface-wave dispersion inversion using soft actor-critic reinforcement learning
    Mingteng Tian, Yingjie Yang
    EarthArXivPreprintCC BY 4.0Full textGeophysics & seismologyEarthArXiv
  4. IrriTwin: Integrating reinforcement learning with soil water and crop models toward digital-twin-oriented irrigation scheduling
    Menghua Xu, Xiujuan Wang, Mengzhen Kang +4
    Journal of HydrologyPeer-reviewedCC BY 4.0Full text2 citedHydrology & soilsHAL
  5. Reinforcement-Learning-Enabled Supervisory Control of a Full-Scale Anaerobic Digestion Facility Using a Calibrated Digital Twin.
    Ahmed I Yunus, Srinivas Jalla, Joe F Bozeman +1
    Environmental science & technologyPeer-reviewedCC BYFull textEnvironmental science & pollutionEurope PMC

Cite

BibTeXRIS
BibTeX
@article{yang2026robust,
  title = {{Robust reinforcement learning multi-baseline phase unwrapping algorithm with JPEG-LS}},
  author = {Shiji Yang and Wu Zhu and Hui Liu and Ruixuan Zhang and Haoran Gao and Lei Xu and Mengyuan Zhu and Tong Yang},
  journal = {International Journal of Applied Earth Observations and Geoinformation},
  year = {2026},
  month = oct,
  doi = {10.1016/j.jag.2026.105648},
  url = {https://doi.org/10.1016/j.jag.2026.105648},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Robust reinforcement learning multi-baseline phase unwrapping algorithm with JPEG-LS
AU  - Shiji Yang
AU  - Wu Zhu
AU  - Hui Liu
AU  - Ruixuan Zhang
AU  - Haoran Gao
AU  - Lei Xu
AU  - Mengyuan Zhu
AU  - Tong Yang
PY  - 2026
DA  - 2026/10/30
JO  - International Journal of Applied Earth Observations and Geoinformation
DO  - 10.1016/j.jag.2026.105648
UR  - https://doi.org/10.1016/j.jag.2026.105648
AB  - Multi-baseline (MB) phase unwrapping (PU) breaks through the limitations of the phase continuity assumption, but existing MBPU algorithms cannot adapt well to noisy environments. A robust reinforcement learning integer programming multi-baseline PU algorithm with JPEG-LS (RL-MBPU) is proposed. First, the cutting plane–pure integer programming cut-selection process is formulated as a sequential reinforcement-learning problem. An efficacy-guided imitation strategy is used to initialize an MBPU-structure-aware single-cut policy, which is further optimized by an actor–critic method using Cut-PAR2-based trajectory returns to reduce the root-node proof cost. Finally, the initial ambiguity number solution is corrected using dynamic median edge detector based on JPEG-LS, and the PU is completed by using the prediction of the left, top, and top-left neighbors of the current pixel and combining it with the local gradient threshold determination. In both simulation and real data experiments, the RL-MBPU algorithm demonstrated stable PU performance, including computational efficiency and noise robustness for interferograms of different sizes. Compared with the minimum-cost flow and cutting plane–pure integer programming algorithms, the RL-MBPU algorithm reduces the root mean square error by approximately 61.2% and 14.5%, respectively, while improving efficiency by approximately 54.1% and 42.4%, respectively. This can further support high-precision interferometric synthetic aperture radar applications.
SN  - 1569-8432
SN  - 1872-826X
ER  -