Montzka et al. (2026) AI in soil moisture remote sensing

Identification

• Journal: RWTH Publications (RWTH Aachen)
• Year: 2026
• Date: 2026-01-01
• Authors: Carsten Montzka, L. Brocca, Hao Yu Chen, Narendra N. Das, Antara Dasgupta, Mehdi Rahmati, Thomas Jagdhuber
• DOI: 10.18154/rwth-2026-00129

Research Groups

• RWTH Aachen University (Germany)
  • Juniorprofessur für Data-driven Computing in Civil Engineering
  • Lehrstuhl und Institut für Wasserbau und Wasserwirtschaft
• Collaborating institutions from Italy, People's Republic of China, and USA (implied by author affiliations and involved countries)

Short Summary

This paper provides a comprehensive review and synthesis of the application of Artificial Intelligence (AI) techniques in the field of soil moisture remote sensing, highlighting current advancements, methodologies, and future research directions.

Objective

• To synthesize and review the current state-of-the-art and future potential of Artificial Intelligence applications in remote sensing for soil moisture estimation and monitoring.

Study Configuration

• Spatial Scale: Conceptual/Review paper, covering diverse spatial scales inherent to remote sensing applications, ranging from local to global.
• Temporal Scale: Conceptual/Review paper, covering diverse temporal scales inherent to remote sensing applications, from sub-daily to decadal.

Methodology and Data

• Models used: Discussion and synthesis of various Artificial Intelligence (AI) models (e.g., machine learning, deep learning algorithms) as applied in the reviewed literature for soil moisture retrieval.
• Data sources: Discussion and synthesis of various remote sensing data sources (e.g., satellite, airborne, ground-based observations) and ancillary data utilized in the reviewed literature for soil moisture estimation.

Main Results

• The paper synthesizes the state-of-the-art in applying AI to soil moisture remote sensing, identifying key advancements, prevalent methodologies, and emerging challenges.
• It highlights the effectiveness of AI in improving the accuracy, spatial resolution, and temporal retrieval capabilities of soil moisture products from various remote sensing platforms.
• It likely identifies current limitations and proposes future research avenues for integrating AI more effectively into soil moisture remote sensing.

Contributions

• Provides a comprehensive and structured overview of the rapidly evolving field of AI applications in soil moisture remote sensing.
• Serves as a valuable reference for researchers by consolidating diverse findings, identifying research gaps, and outlining future research directions and opportunities.

Funding

• Not explicitly stated in the provided text.

Citation

@article{Montzka2026AI,
  author = {Montzka, Carsten and Brocca, L. and Chen, Hao Yu and Das, Narendra N. and Dasgupta, Antara and Rahmati, Mehdi and Jagdhuber, Thomas},
  title = {AI in soil moisture remote sensing},
  journal = {RWTH Publications (RWTH Aachen)},
  year = {2026},
  doi = {10.18154/rwth-2026-00129},
  url = {https://doi.org/10.18154/rwth-2026-00129}
}