Open Access

Using machine learning techniques to reconstruct the signal observed by the GRACE mission based on AMSR-E microwave data

Viktor Szabó

Viktor Szabó

Department of Geodesy and Geodetic Astronomy, Faculty of Geodesy and Cartography, Warsaw University of TechnologyWarsaw, Poland
Orcid profile
Search for this author on
Sciendo|Google Scholar
Szabó, Viktor
, 
Katarzyna Osińska-Skotak

Katarzyna Osińska-Skotak

Department of Photogrammetry, Remote Sensing and Spatial Information Systems, Faculty of Geodesy and Cartography, Warsaw University of TechnologyWarsaw, Poland
Orcid profile
Search for this author on
Sciendo|Google Scholar
Osińska-Skotak, Katarzyna
 and 
Tomasz Olszak

Tomasz Olszak

Department of Geodesy and Geodetic Astronomy, Faculty of Geodesy and Cartography, Warsaw University of TechnologyWarsaw, Poland
Orcid profile
Search for this author on
Sciendo|Google Scholar
Olszak, Tomasz
  
Apr 30, 2024
Using machine learning techniques to reconstruct the signal observed by the GRACE mission based on AMSR-E microwave data's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Apr 30, 2024
Page range: 80 - 86
Received: Jan 20, 2024
Accepted: Apr 21, 2024
DOI: https://doi.org/10.2478/mgrsd-2023-0033
Keywords
© 2024 Viktor Szabó et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Random Forest Regressor model: (a) residuals; (b) prediction identitySource: own elaboration
Random Forest Regressor model: (a) residuals; (b) prediction identitySource: own elaboration

Figure 2.

Random Forest Regressor model spatial distribution of metrics: (a) NSE; (b) RMSE; (c) NRMSE; (d) R2Source: own elaboration
Random Forest Regressor model spatial distribution of metrics: (a) NSE; (b) RMSE; (c) NRMSE; (d) R2Source: own elaboration

Figure 3.

(a) Predicted ΔTWS and true ΔTWS with SM predictors from AMSR-E; (b) Predicted ΔTWS and true ΔTWS with dg validation dataSource: own elaboration
(a) Predicted ΔTWS and true ΔTWS with SM predictors from AMSR-E; (b) Predicted ΔTWS and true ΔTWS with dg validation dataSource: own elaboration

The achieved results on the test data sample

Model RMSE [m] R2 Δ RMSE [%] Δ R2 [%] 1-R2 Δ 1-R2 [%]
Random Forest Regressor 0.035 0.761 51.3 380700.0 0.239 76.1
Extra Trees Regressor 0.035 0.757 50.9 378700.0 0.243 75.7
Extreme Gradient Boosting 0.037 0.739 48.9 369350.0 0.262 73.9
K Neighbors Regressor 0.038 0.725 47.7 362450.0 0.275 72.5
Light Gradient Boosting Machine 0.038 0.715 46.7 357750.0 0.285 71.5
Decision Tree Regressor 0.048 0.546 32.8 273000.0 0.454 54.6
Gradient Boosting Regressor 0.052 0.469 27.3 234600.0 0.531 46.9
Linear Regression 0.069 0.074 3.9 36950.0 0.926 7.4
Least Angle Regression 0.069 0.074 3.9 36950.0 0.926 7.4
Bayesian Ridge 0.069 0.074 3.9 36900.0 0.926 7.4
Ridge Regression 0.069 0.068 3.7 34150.0 0.932 6.8
Huber Regressor 0.070 0.062 3.2 31000.0 0.938 6.2
Orthogonal Matching Pursuit 0.072 0.000 0.2 50.0 1.000 0.0
Lasso Regression 0.072 −0.001 0.2 −150.0 1.001 0.0
Elastic Net 0.072 −0.001 0.2 −150.0 1.001 0.0
Lasso Least Angle Regression 0.072 −0.001 0.2 −150.0 1.001 0.0
Dummy Regressor 0.072 −0.001 0.2 −150.0 1.001 0.0
AdaBoost Regressor 0.073 −0.021 −0.9 −10450.0 1.021 −2.1
Passive Aggressive Regressor 0.086 −0.485 −20.0 −242550.0 1.485 −48.5
sin+cos annual function (baseline) 0.072 0.000 - - 1.000
sin+cos semiannual function 0.095 0.000 −32.7 0.0 1.000 0.0
Language:
English
Publication timeframe:
4 times per year
Journal Subjects:
Geosciences, Geography, Geosciences, other
Journal RSS Feed