PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 2, 2026Electronics0 citationsOpen Access

Real-Time Adaptive Optimization for Underwater Optical Wireless Communications Using LSTM–NSGA-II

View Full Paper
OBOliger Veronica Mendoza BetancourtYWYì Wáng

Key Points

  • The study aims to enhance underwater optical wireless communication systems by predicting turbulence and optimizing transmission parameters.
  • Integration of LSTM networks with NSGA-II for real-time turbulence prediction.
  • Multi-objective adaptive optimization of parameters like power and modulation scheme.
  • Validation using field data from the Marine Institute in the Baltic Sea.
  • Achieved a 45% reduction in bit error rate (BER).
  • Improved energy efficiency by 36%.
  • Maintained a signal-to-noise ratio (SNR) prediction accuracy of 94.7%.
  • Achieved an adaptive response latency of 28.6 ms.

Abstract

Underwater optical wireless communication (UOWC) systems are significantly challenged by turbulence-induced signal degradation in dynamic channel conditions. This paper presents a novel framework that integrates Long Short-Term Memory (LSTM) networks with the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to enable real-time turbulence prediction and multi-objective adaptive optimization of transmission parameters, including power, modulation scheme, and beam divergence. Experimental results demonstrate that the proposed LSTM–NSGA-II framework achieves a 45% reduction in bit error rate (BER) and a 36% improvement in energy efficiency compared to conventional static systems, while maintaining a signal-to-noise ratio (SNR) prediction accuracy of 94.7% and an adaptive response latency of 28.6 ms. Validation using field data from the Marine Institute in the Baltic Sea confirms the framework’s practical applicability and robustness, highlighting its potential to enhance autonomous and military underwater operations in turbulent environments. This work represents a significant step toward more reliable and efficient UOWC systems.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Betancourt et al. (2026) studied this question.

synapsesocial.com/papers/6980fe8ac1c9540dea810a52https://doi.org/10.3390/electronics15030611
Ask AI
Helpful
Bookmark
Share
View Full Paper