Fully Integrated Deep-Ocean Flexible Temperature–Depth Sensor with Neural Network Compensation

Earth’s deep ocean shapes global heat transport, carbon cycling and abyssal circulation, yet large regions remain undersampled. While conventional instruments provide precise single point measurements, their rigidity and weight limit deployment on emerging platforms that could extend observational reach. Here, we introduce the fully integrated, flexible temperature–depth sensor deployable on curved and mobile surfaces for deep-sea measurements. The compact, lightweight, stress-adaptive low-power electronics (average quiescent current: 24.63 µA) unit operates as a co-designed cyber–physical platform, where the porous laser-induced graphene–polydimethylsiloxane composite sensing element achieves a broad measurement range over 0–10 MPa hydrostatic pressure, while temperature–pressure compensation through a dual-hidden-layer neural network combined with polynomial fitting yields a depth error of ≤±0.91% full scale and temperature accuracy of ≤±0.29 °C. Deep-sea trials to 4812.2 m show structural integrity under ~50 MPa hydrostatic pressure, demonstrating durability in extreme environments and enabling sensing on platforms inaccessible to conventional instruments. Marine pressure monitoring helps reveal ocean dynamics and assess human impacts. This work reports a self-contained low-power flexible marine temperature depth (FMTD) sensor featuring wide range, high precision and restrained temperature drift.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-11-07
DOI
https://doi.org/10.1038/s41467-026-78009-7
Primary Topic
Advanced Sensor and Energy Harvesting Materials
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Fully Integrated Deep-Ocean Flexible Temperature–Depth Sensor with Neural Network Compensation

Yang Yang, Huaping Wu, Zihong Wei, Maggie C. Y. Lau et al.
Nature Communications
Advanced Sensor and Energy Harvesting Materials
article

Fully Integrated Deep-Ocean Flexible Temperature–Depth Sensor with Neural Network Compensation

Yang Yang, Huaping Wu, Zihong Wei, Maggie C. Y. Lau, Yaxiaer Yalikun, Zhuhang Dai, Rongjie Lin, Diye Wu, Chenjing Shang, Zhenting Ye, A. S. Ismail, Quan Hong, Hai Zhang
article en

Abstract

Earth’s deep ocean shapes global heat transport, carbon cycling and abyssal circulation, yet large regions remain undersampled. While conventional instruments provide precise single point measurements, their rigidity and weight limit deployment on emerging platforms that could extend observational reach. Here, we introduce the fully integrated, flexible temperature–depth sensor deployable on curved and mobile surfaces for deep-sea measurements. The compact, lightweight, stress-adaptive low-power electronics (average quiescent current: 24.63 µA) unit operates as a co-designed cyber–physical platform, where the porous laser-induced graphene–polydimethylsiloxane composite sensing element achieves a broad measurement range over 0–10 MPa hydrostatic pressure, while temperature–pressure compensation through a dual-hidden-layer neural network combined with polynomial fitting yields a depth error of ≤±0.91% full scale and temperature accuracy of ≤±0.29 °C. Deep-sea trials to 4812.2 m show structural integrity under ~50 MPa hydrostatic pressure, demonstrating durability in extreme environments and enabling sensing on platforms inaccessible to conventional instruments. Marine pressure monitoring helps reveal ocean dynamics and assess human impacts. This work reports a self-contained low-power flexible marine temperature depth (FMTD) sensor featuring wide range, high precision and restrained temperature drift.

Nature Communications
Shenzhen University (CN), Zagazig University (EG), Chinese Academy of Sciences (CN), Institute of Deep-Sea Science and Engineering (CN), University of Chinese Academy of Sciences (CN), Zhejiang University of Technology (CN), Nara Institute of Science and Technology (JP)
National Natural Science Foundation of China, Natural Science Foundation of Zhejiang Province
Life below water
Openalex Percentile: Top 27%
Advanced Sensor and Energy Harvesting Materials
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon