A New Satellite-Based Precipitation Downscaling Scheme for Data-sparse Areas Using Deep Learning and Transfer Learning

Honglin Zhu*, Qiming Zhou, Aihong Cui

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Numerous statistical downscaling techniques were proposed to improve the spatial resolution of satellite-based precipitation data. However, these downscaling methods generally required observation data, making it difficult to apply in data-scarce areas. To address this issue, this study presented a framework based on transfer learning (TL), in which the pretrained convolutional neural network model in source domain was fine-tuned and implemented in target domains. Results showed that the pretrained model cannot be directly applied in transferred regions due to its poor performance, but the TL model with at least one fine-tunable layers achieved significant improvements and can be employed successfully. It was notable that the fine-tuning model obtained even higher accuracy than the model trained independently with data of target domains. Results also showed that TL model attained a higher performance with more fine-tunable layers, and different fine-tunable layers would impact the downscaling results and should be selected during TL.

Original languageEnglish
Title of host publicationIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Place of PublicationPasadena, CA, USA
PublisherIEEE
Pages1826-1829
Number of pages4
ISBN (Electronic)9798350320107, 9798350320091
ISBN (Print)9798350331745
DOIs
Publication statusPublished - 16 Jul 2023
Event2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States
Duration: 16 Jul 202321 Jul 2023
https://ieeexplore.ieee.org/xpl/conhome/10281394/proceeding

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2023-July

Conference

Conference2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/TerritoryUnited States
CityPasadena
Period16/07/2321/07/23
Internet address

Scopus Subject Areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

User-Defined Keywords

  • deep learning
  • precipitation downscaling
  • satellite remote sensing
  • transfer learning

Fingerprint

Dive into the research topics of 'A New Satellite-Based Precipitation Downscaling Scheme for Data-sparse Areas Using Deep Learning and Transfer Learning'. Together they form a unique fingerprint.

Cite this