Application of Machine Learning and Remote Sensing for Gap-filling Daily Precipitation Data of a Sparsely Gauged Basin in East Africa

Marzie Faramarzzadeh, Mohammad Reza Ehsani, Mahdi Akbari, Reyhane Rahimi, Mohammad Moghaddam, Ali Behrangi, Björn Klöve, Ali Torabi Haghighi, Mourad Oussalah

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

Access to spatiotemporal distribution of precipitation is needed in many hydrological applications. However, gauges often have spatiotemporal gaps. To mitigate this, we considered three main approaches: (i) using remotely sensing and reanalysis precipitation products; (ii) machine learning-based approaches; and (iii) a gap-filling software explicitly developed for filling the gaps of daily precipitation records. This study evaluated all approaches over a sparsely gauged basin in East Africa. Among the examined precipitation products, PERSIANN-CDR outperformed other satellite products in terms of root mean squared error (7.3 mm), and correlation coefficient (0.46) while having a large bias (50%) compared to the available in situ precipitation records. PERSIANN-CDR also demonstrates the highest skill in distinguishing rainy and non-rainy days. On the other hand, Random Forest outperformed all other approaches (including PERSIANN-CDR) with the least relative bias (-2%), root mean squared error (6.9 mm), and highest correlation coefficient (0.53).

Original languageEnglish (US)
Article number8
JournalEnvironmental Processes
Volume10
Issue number1
DOIs
StatePublished - Mar 2023

Keywords

  • Deep learning
  • Gap-filling
  • Machine learning
  • Precipitation products
  • Random forest
  • ReddPrec

ASJC Scopus subject areas

  • Environmental Engineering
  • Water Science and Technology
  • Pollution
  • Management, Monitoring, Policy and Law
  • Health, Toxicology and Mutagenesis

Fingerprint

Dive into the research topics of 'Application of Machine Learning and Remote Sensing for Gap-filling Daily Precipitation Data of a Sparsely Gauged Basin in East Africa'. Together they form a unique fingerprint.

Cite this