Preprints
https://doi.org/10.5194/egusphere-2026-2352
https://doi.org/10.5194/egusphere-2026-2352
12 May 2026
 | 12 May 2026

Reducing False Alarms in Small-Scale Slope Early Warning Systems via Deep Learning-Driven Asynchronous Displacement and Rainfall Data Fusion

Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu

Abstract. Real-time crackmeter-based warning systems for rainfall-induced small-scale slope failures suffer from prohibitively high false alarm rates. Across diverse geological settings, existing approaches relying on fixed thresholds or isolated rainfall–displacement relationships are highly sensitive to noise, lacking the robustness to reliably distinguish genuine deformation signals from spurious measurements. To address this operational bottleneck, this study reframes the early warning paradigm from a traditional fixed-threshold alerting process reliant on manual discrimination to an automated alert truth verification problem, proposing a real-time binary classification framework to isolate true early warnings from sensor-triggered false alarms. Utilizing a multi-source dataset of crackmeter displacement and rainfall measurements from diverse monitored slopes in Fujian Province, China, all true early warning instances were rigorously calibrated via field investigations. A patch-based dual-branch temporally-aware Transformer model was developed to explicitly address asynchronous multi-rate data fusion, strict temporal causality between rainfall and displacement, and stringent real-time decision constraints. By simultaneously capturing long-term rainfall-displacement interactions and high-resolution displacement dynamics, the model outperforms competitive baselines, achieving a precision of 90.91 %, a recall of 93.53 %, and an F2-score of 92.99 % in identifying true early warnings. Interpretability analysis reveals the model’s decisions are primarily driven by localized displacement trends and relative rainfall intensity, aligning with expert judgment. The proposed framework significantly curtails false alarms without compromising reliability, acting as a robust decision-support layer to enhance automated slope hazard monitoring. Future work will fuse additional sensor types to suppress false alarms via cross-validation of multi-physical responses.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share

Journal article(s) based on this preprint

02 Nov 2026
Reducing false alarms in crackmeter-based early warning of small-scale slope deformation via deep learning-driven asynchronous displacement–rainfall data fusion
Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu
Nat. Hazards Earth Syst. Sci., 26, 5441–5467, https://doi.org/10.5194/nhess-26-5441-2026,https://doi.org/10.5194/nhess-26-5441-2026, 2026
Short summary
Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2026-2352', Anonymous Referee #1, 21 May 2026
    • RC2: 'Referee comment on egusphere-2026-2352', Anonymous Referee #2, 09 Jul 2026
      • AC2: 'Reply on RC2', Shubing Ouyang, 12 Aug 2026
    • AC1: 'Reply on RC1', Shubing Ouyang, 12 Aug 2026

Peer review completion

AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload
ED: Submit a revised manuscript (13 Aug 2026) by Timothy Tiggeloven
AR by Shubing Ouyang on behalf of the Authors (26 Aug 2026)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (07 Sep 2026) by Timothy Tiggeloven
RR by Anonymous Referee #3 (07 Oct 2026)
ED: Publish as is (12 Oct 2026) by Timothy Tiggeloven
ED: Publish as is (12 Oct 2026) by Timothy Tiggeloven (Executive editor)
AR by Shubing Ouyang on behalf of the Authors (16 Oct 2026)

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2026-2352', Anonymous Referee #1, 21 May 2026
    • RC2: 'Referee comment on egusphere-2026-2352', Anonymous Referee #2, 09 Jul 2026
      • AC2: 'Reply on RC2', Shubing Ouyang, 12 Aug 2026
    • AC1: 'Reply on RC1', Shubing Ouyang, 12 Aug 2026

Peer review completion

AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload
ED: Submit a revised manuscript (13 Aug 2026) by Timothy Tiggeloven
AR by Shubing Ouyang on behalf of the Authors (26 Aug 2026)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (07 Sep 2026) by Timothy Tiggeloven
RR by Anonymous Referee #3 (07 Oct 2026)
ED: Publish as is (12 Oct 2026) by Timothy Tiggeloven
ED: Publish as is (12 Oct 2026) by Timothy Tiggeloven (Executive editor)
AR by Shubing Ouyang on behalf of the Authors (16 Oct 2026)

Journal article(s) based on this preprint

02 Nov 2026
Reducing false alarms in crackmeter-based early warning of small-scale slope deformation via deep learning-driven asynchronous displacement–rainfall data fusion
Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu
Nat. Hazards Earth Syst. Sci., 26, 5441–5467, https://doi.org/10.5194/nhess-26-5441-2026,https://doi.org/10.5194/nhess-26-5441-2026, 2026
Short summary
Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu

Model code and software

The code of PatchDC Shubing Ouyang https://github.com/ShubingOuyangcug/PatchDC

Shubing Ouyang, Daichao Li, Minjiang Liu, Fengjian Ge, Xia Zheng, Yuan Li, and Sheng Wu

Viewed

Total article views: 989 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
593 338 58 989 54 45
  • HTML: 593
  • PDF: 338
  • XML: 58
  • Total: 989
  • BibTeX: 54
  • EndNote: 45
Views and downloads (calculated since 12 May 2026)
Cumulative views and downloads (calculated since 12 May 2026)

Viewed (geographical distribution)

Total article views: 922 (including HTML, PDF, and XML) Thereof 922 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 17 Nov 2026
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
Current landslide warning systems produce too many false alarms, causing alarm fatigue. To fix this, an artificial intelligence model was developed to act as an automated truth-checker. By combining real-time data on ground cracking and local rainfall, the model learns to distinguish genuine slope failures from harmless sensor noise. Over 93 percent of real landslide threats were successfully identified while false ones were ignored. This ensures reliable safety alerts and saves expert time.
Share