Multivariate Fractal Autoencoder (MFAE): Sparse Sensor Placement via Cross-Variable Synergy for Ocean Data Reconstruction
- 2 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 22345-22358
Abstract
Optimizing sensor placement is crucial for enhancing the coverage and data-acquisition efficiency of ocean monitoring systems. Traditional approaches primarily rely on univariate ocean data for sensor placement, failing to capture the multidimensional coupling characteristics of the ocean environment, while the potential of multivariate datasets remains underexplored. To address this limitation, this work proposes an innovative multivariate fractal autoencoder (MFAE) framework that leverages multivariate data to solve the sparse sensor placement problem. The MFAE optimizes sensor placement by dynamically updating multivariate feature weights and extracting latent spatial correlations. Furthermore, by optimizing feature weight initialization and enhancing autoencoder training protocols, we propose an entropy-weighted MFAE (EnMFAE) to establish an accurate nonlinear mapping between low-dimensional sampling spaces and full-state reconstructions. Validation experiments are conducted on temperature and salinity datasets from the North Pacific and Arctic Oceans, and the results demonstrate the superior performance of MFAE and EnMFAE relative to the proper orthogonal decomposition (POD), QR, and random placement baselines. With only ten selected sensors, the MFAE achieves average reconstruction error reductions of 2.96% (for temperature) and 2.12% (for salinity) in the North Pacific, and 5.78% (for temperature) and 7.71% (for salinity) in the Arctic, respectively, significantly outperforming the compared random placement method with decoder-based reconstruction. MFAE offers a novel paradigm for optimizing sensor networks in complex ocean environments by leveraging multivariate data reconstruction.Keywords
Funding Information
- National Natural Science Foundation of China (52331012)
- National Natural Science Foundation of China (52201401)
- National Natural Science Foundation of China (52071200)
- National Natural Science Foundation of China (52201403)
- National Natural Science Foundation of China (52102397)
- National Natural Science Foundation of China (2021YFC2801002)
- Shanghai Committee of Science and Technology (23010502000)
- Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission (23CGA61)
- China Scholarship Council (202508310266)
This publication has 47 references indexed in Scilit:
- FedAHPIP: Federated Learning with Adaptive Hot Parameter Identification and Personalized Anchoring for multi-agent collaborationJournal of Industrial Information Integration, 2026
- Enhancing image–text matching through multi-level semantic consistency alignmentThe Visual Computer, 2025
- Optimal multi-type sensor placement using hybrid graph theory and numerical observability analysis for system observability and cybersecurity enhancementElectric Power Systems Research, 2024
- A review on multi-view learningFrontiers of Computer Science, 2024
- A physics-driven sensor placement optimization methodology for temperature field reconstructionApplied Thermal Engineering, 2024
- TMHD: Twin-Bridge Scheduling of Multi-Heterogeneous Dependent Tasks for Edge ComputingFuture Generation Computer Systems, 2024
- Optimal sensor placement for reconstructing wind pressure field around buildings using compressed sensingJournal of Building Engineering, 2023
- Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields2022
- Novel Energy-Efficient Opportunistic Routing Protocol for Marine Wireless Sensor Networks Based on Compressed Sensing and Power ControlJournal of Ocean University of China, 2022
- Multi-view Subspace Adaptive Learning via Autoencoder and Attention2020