High resolution soil moisture mapping in 3D space and time using machine learning and depth functions

被引:0
|
作者
Zhang, Mo [1 ,2 ]
Ge, Yong [1 ,2 ,3 ,4 ]
Heuvelink, Gerard B. M. [5 ,6 ]
Ma, Yuxin [7 ]
机构
[1] Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Coll Resources & Environm, Beijing, Peoples R China
[3] Jiangxi Normal Univ, Key Lab Poyang Lake Wetland & Watershed Res, Minist Educ, Nanchang, Peoples R China
[4] Key Lab Intelligent Monitoring & Comprehens Manage, Nanchang, Jiangxi, Peoples R China
[5] Wageningen Univ, Soil Geog & Landscape Grp, POB 47, NL-6700 AA Wageningen, Netherlands
[6] ISR World Soil Informat, POB 353, NL-6700 AJ Wageningen, Netherlands
[7] New South Wales Dept Climate Change Energy Environ, Parramatta, NSW 2150, Australia
关键词
Spatial interpolation; Downscaling method; Random forest; Equal-area spline depth function; Knowledge-driven approach; ROOT-ZONE; ORGANIC-CARBON; DYNAMICS; CLIMATE; SMAP; INTERPOLATION; ASSIMILATION; REGRESSION; VEGETATION; PROFILE;
D O I
10.1016/j.geoderma.2024.117117
中图分类号
S15 [土壤学];
学科分类号
0903 ; 090301 ;
摘要
Soil moisture is a key factor in hydrological, biological, and chemical processes, and plays a critical role in maintaining ecosystem balance. To generate high-resolution soil moisture maps at regional scales, researchers primarily employed in-situ observation-based spatial interpolation and remote sensing-based downscaling methods. However, direct comparisons between these methods are scarce. Additionally, remote sensing techniques are limited to the topsoil layer, and in-situ observations often have large depth intervals, thereby constraining the vertical resolution of subsurface soil moisture mapping. To address these challenges, we utilized an equal-area spline depth function combined with machine learning to map high spatial-vertical-resolution daily soil moisture across the Qinghai-Tibet Plateau. The performance of spatial interpolation and downscaling methods in mapping surface soil moisture at 0-5 cm depth were also compared. The results revealed that both spatial interpolation and downscaling methods produced unbiased predictions. However, prediction accuracy was lower in the peripheral subareas of the study area which had lower sampling density. Maps generated through the spatial interpolation method better captured detailed environmental covariates, whereas those obtained with downscaling methods were smoother. The fitting of depth functions introduced only small errors, but caution is still needed when predicting at unobserved depths. For subsurface soil moisture mapping using depth functions combined with spatial interpolation, validation results at two depth intervals showed improvements over surface predictions, with a root mean squared error (RMSE) reduced by 6.45 % to 17.2 % and unbiased RMSE by 5.95 % to 19.04 %. Furthermore, the analysis of variable importance highlighted the critical role of time-varying covariates. Future research should focus on optimizing depth functions and combining datadriven with knowledge-driven approaches. This study serves as a reference for mapping soil moisture with fine spatial-vertical-resolution in large-scale study areas.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Depth perception of texture with high-resolution 3D display
    Bando, T.
    Sasaki, Y.
    PERCEPTION, 2012, 41 : 83 - 83
  • [32] Measurement of Soil Tillage Using UAV High-Resolution 3D Data
    Rebelo, Carla
    Nascimento, Joao
    REMOTE SENSING, 2021, 13 (21)
  • [33] 3D Microseismic Monitoring Using Machine Learning
    Chen, Yangkang
    Saad, Omar M.
    Savvaidis, Alexandros
    Chen, Yunfeng
    Fomel, Sergey
    JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH, 2022, 127 (03)
  • [34] A Perspective on Using Machine Learning in 3D Bioprinting
    Yu, Chunling
    Jiang, Jingchao
    INTERNATIONAL JOURNAL OF BIOPRINTING, 2020, 6 (01) : 4 - 11
  • [35] Real-time defect detection in 3D printing using machine learning
    Khan, Mohammad Farhan
    Alam, Aftaab
    Siddiqui, Mohammad Ateeb
    Alam, Mohammad Saad
    Rafat, Yasser
    Salik, Nehal
    Al-Saidan, Ibrahim
    MATERIALS TODAY-PROCEEDINGS, 2021, 42 : 521 - 528
  • [36] High Resolution Soil Moisture Mapping Using AIRSAR Observations During SMEX02
    Bindlish, Rajat
    Jackson, Thomas J.
    Van der Velde, Rogier
    2006 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-8, 2006, : 2324 - +
  • [37] Space-time mapping of soil organic carbon through remote sensing and machine learning
    Bartsch, Bruno dos Anjos
    Rosin, Nicolas Augusto
    Rosas, Jorge Tadeu Fim
    Poppiel, Raul Roberto
    Makino, Fernando Yutaro
    Vogel, Leticia Guadagnin
    Novais, Jean Jesus Macedo
    Falcioni, Renan
    Alves, Marcelo Rodrigo
    Dematte, Jose A. M.
    SOIL & TILLAGE RESEARCH, 2025, 248
  • [38] Probabilistic Modeling of Conformational Space for 3D Machine Learning Approaches
    Jahn, Andreas
    Hinselmann, Georg
    Fechner, Nikolas
    Henneges, Carsten
    Zell, Andreas
    MOLECULAR INFORMATICS, 2010, 29 (05) : 441 - 455
  • [39] Dasymetric Mapping Using UAV High Resolution 3D Data within Urban Areas
    Rebelo, Carla
    Rodrigues, Antonio Manuel
    Tenedorio, Jose Antonio
    REMOTE SENSING, 2019, 11 (14):
  • [40] High-resolution 3D mapping: Opportunities and limitations of the Rhythmia™ mapping system
    Ellermann C.
    Frommeyer G.
    Eckardt L.
    Herzschrittmachertherapie + Elektrophysiologie, 2018, 29 (3) : 284 - 292