High-resolution European daily soil moisture derived with machine learning (2003-2020)
- 주제(기타) Multidisciplinary Sciences
- 설명문(일반) [Sungmin, O.; Park, Seon Ki] Ewha Womans Univ, Dept Climate & Energy Syst Engn, Seoul, South Korea; [Orth, Rene; Weber, Ulrich] Max Planck Inst Biogeochem, Dept Biogeochem Integrat, Jena, Germany; [Park, Seon Ki] Ewha Womans Univ, Ctr Climate Environm Change Predict Res, Seoul, South Korea; [Park, Seon Ki] Ewha Womans Univ, Severe Storm Res Ctr, Seoul, South Korea
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- OA유형 Green Published, gold, Green Submitted
- 발행기관 NATURE PORTFOLIO
- 발행년도 2022
- URI http://www.dcollection.net/handler/ewha/000000203108
- 본문언어 영어
- Published As https://doi.org/10.1038/s41597-022-01785-6
- PubMed https://pubmed.ncbi.nlm.nih.gov/36376361
초록/요약
Machine learning (ML) has emerged as a novel tool for generating large-scale land surface data in recent years. ML can learn the relationship between input and target, e.g. meteorological variables and in-situ soil moisture, and then estimate soil moisture across space and time, independently of prior physics-based knowledge. Here we develop a high-resolution (0.1 degrees) daily soil moisture dataset in Europe (SoMo.ml-EU) using Long Short-Term Memory trained with in-situ measurements. The resulting dataset covers three vertical layers and the period 2003-2020. Compared to its previous version with a lower spatial resolution (0.25 degrees), it shows a closer agreement with independent in-situ data in terms of temporal variation, demonstrating the enhanced usefulness of in-situ observations when processed jointly with high-resolution meteorological data. Regional comparison with other gridded datasets also demonstrates the ability of SoMo.ml-EU in describing the variability of soil moisture, including drought conditions. As a result, our new dataset will benefit regional studies requiring high-resolution observation-based soil moisture, such as hydrological and agricultural analyses.
more