Preprints
https://doi.org/10.5194/egusphere-2022-1326
https://doi.org/10.5194/egusphere-2022-1326
 
05 Jan 2023
05 Jan 2023
Status: this preprint is open for discussion.

Dynamic weighted ensemble of geoscientific models via automated machine learning-based classification

Hao Chen1,2,4, Tiejun Wang1,2,3, Yonggen Zhang1,2, Yun Bai5, and Xi Chen1,2,3 Hao Chen et al.
  • 1Institute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin, 300072, China
  • 2Tianjin Key Laboratory of Earth Critical Zone Science and Sustainable Development in Bohai Rim, Tianjin University, Tianjin, 300072, China
  • 3Tianjin Bohai Rim Coastal Earth Critical Zone National Observation and Research Station, Tianjin University, Tianjin, 300072, China
  • 4State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, 100101, China
  • 5Research Center for Remote Sensing Information and Digital Earth, College of Computer Science and Technology, Qingdao University, Qingdao, 266071, China

Abstract. Despite recent developments in geoscientific (e.g., physics/data-driven) models, effectively assembling multiple models for approaching a benchmark solution remains challenging in many sub-disciplines of geoscientific fields. Here, we proposed an automated machine learning-assisted ensemble framework (AutoML-Ens) that attempts to resolve this challenge. Details of the methodology and workflow of AutoML-Ens were provided, and a prototype model was realized with the key strategy of mapping between the probabilities derived from the machine learning classifier and the dynamic weights assigned to the candidate ensemble members. Based on the newly proposed framework, its applications for two real-world examples (i.e., mapping global soil water retention parameters and estimating remotely sensed cropland evapotranspiration) were investigated and discussed. Results showed that compared to conventional ensemble approaches, AutoML-Ens was superior across the datasets (the training, testing, and overall datasets) and environmental gradients with improved performance metrics (e.g., coefficient of determination, Kling-Gupta efficiency, and root mean squared error). The better performance suggested the great potential of AutoML-Ens for improving quantification and reducing uncertainty in estimates due to its two unique features, i.e., assigning dynamic weights for candidate models and taking full advantage of AutoML-assisted workflow. In addition to the representative results, we also discussed the interpretational aspects of the used framework and its possible extensions. More importantly, we emphasized the benefits of combining data-driven approaches with physics constraints for geoscientific model ensemble problems with high dimensionality in space and non-linear behaviors in nature.

Hao Chen et al.

Status: open (until 02 Mar 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Hao Chen et al.

Viewed

Total article views: 165 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
131 30 4 165 19 1 3
  • HTML: 131
  • PDF: 30
  • XML: 4
  • Total: 165
  • Supplement: 19
  • BibTeX: 1
  • EndNote: 3
Views and downloads (calculated since 05 Jan 2023)
Cumulative views and downloads (calculated since 05 Jan 2023)

Viewed (geographical distribution)

Total article views: 182 (including HTML, PDF, and XML) Thereof 182 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 Jan 2023
Download
Short summary
Effectively assembling multiple models for approaching a benchmark solution remains a long-standing issue for various geoscience domains. We here proposed an automated machine learning-assisted ensemble framework (AutoML-Ens) that attempts to resolve this challenge. Results demonstrated the great potential of AutoML-Ens for improving estimations due to its two unique features, i.e., assigning dynamic weights for candidate models and taking full advantage of AutoML-assisted workflow.