Image-Driven Spatial Interpolation with Deep Learning for Radio Map Construction

Katsuya Suto, Shinsuke Bannai, Koya Sato, Kei Inage, Koichi Adachi, Takeo Fujii

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Radio maps are a promising technology that can boost the capability of wireless networks by enhancing spectrum efficiency. Since spatial interpolation is a critical challenge to construct a precise radio map, the latest works have proposed deep learning (DL)-based interpolation methods. However, a DL model that achieves enough estimation accuracy for practical uses has not yet been established due to the complexity of radio propagation characteristics. Therefore, we propose a novel DL framework that transforms the spatial interpolation problem into a shadowing adjustment problem suitable for DL-based approaches. We evaluate the performance using real measurement data in urban and suburban areas to show that the proposed framework outperforms the state-of-the-art deep learning models.

Original languageEnglish
Article number9365700
Pages (from-to)1222-1226
Number of pages5
JournalIEEE Wireless Communications Letters
Issue number6
Publication statusPublished - Jun 2021


  • Convolutional neural networks
  • radio map
  • radio propagation
  • spatial interpolation


Dive into the research topics of 'Image-Driven Spatial Interpolation with Deep Learning for Radio Map Construction'. Together they form a unique fingerprint.

Cite this