the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Decoding the Architecture of Drought: SHAP-Enhanced Insights into the Climate Forces Reshaping the Sahel
Abstract. The Sahel region faces increasing drought variability, driven by complex interactions between climatic indices and hydrological extremes. This study explores the correlation between the Standardized Precipitation Evapotranspiration Index (SPEI) and multiple climatic indices using trend analysis, cross-correlation, and an innovative SHAP-driven (SHapley Additive exPlanations) clustering approach. The Seasonal Kendall (SK) test identified statistically significant decreasing SPEI-12 trends in 57.5 % of the gridded data, particularly in the western (Senegal and Mauritania) and southeastern regions of the Sahel (South Sudan). In contrast, 19.3 % of the data, primarily in the central-western Sahel (Burkina Faso and Niger), exhibited statistically significant increasing trends. Correlation analysis between SPEI-12 and climatic indices revealed strong negative relationships between SPEI and Global Mean Temperature (GMT, correlation coefficient up to -0.76) and Indo-Pacific Warm Pool (IPWP, -0.71), underscoring their role in drought intensification. Conversely, the Atlantic Multidecadal Oscillation (AMO, 0.40) showed a positive correlation, emphasizing its influence on regional hydrology. Clustering delineated three distinct drought-prone regions, with Cluster C2, including the Sahel regions of Senegal, Mauritania, and Mali, (western Sahel) experiencing the most severe drought intensification (Z = -5.04). The SHAP-driven clustering approach, which incorporates a Machine Learning (ML) Random Forest (RF) model to classify data points into clusters, allowing the SHAP method to quantify the influence of each climatic variable on the clustering process, further highlights the dominant role of AMO and the North Tropical Atlantic Index (NTA) in shaping regional drought dynamics. This study provides a novel framework integrating explainable AI into drought assessment, offering valuable insights for climate adaptation and water resource management in the Sahel.
- Preprint
(3098 KB) - Metadata XML
-
Supplement
(390 KB) - BibTeX
- EndNote
Status: final response (author comments only)
-
RC1: 'Comment on egusphere-2025-1308', Anonymous Referee #1, 24 May 2025
-
AC1: 'Reply on RC1', Francesco Granata, 11 Jun 2025
The Authors thank the Reviewer for the time devoted to the thorough evaluation of the manuscript and for the valuable and constructive comments provided. Detailed responses to each comment are included in the attached file.
Best regards,
Francesco Granata
-
AC1: 'Reply on RC1', Francesco Granata, 11 Jun 2025
-
RC2: 'Comment on egusphere-2025-1308', Anonymous Referee #2, 30 May 2025
The manuscript titled "Decoding the Architecture of Drought: SHAP-Enhanced Insights into the Climate Forces Reshaping the Sahel" presents a robust, interdisciplinary analysis of drought patterns in the Sahel region. The authors employ a multi-method approach that combines the Standardized Precipitation Evapotranspiration Index (SPEI), Seasonal Kendall (SK) trend analysis, cross-correlation with 31 climatic indices, and a SHAP-enhanced clustering methodology using Random Forest (RF) to explore the spatial-temporal variability of drought and its climatic drivers.
Key findings include:
- A significant downward trend in SPEI-12 across 57.5% of the Sahel, particularly in the west and southeast, indicating intensified drought conditions.
- Strong negative correlations between drought severity and Global Mean Temperature (GMT) and Indo-Pacific Warm Pool (IPWP); Atlantic Multidecadal Oscillation (AMO) showed spatially heterogeneous impacts.
- The clustering analysis delineates three distinct regions with unique drought dynamics and climate-drought interactions.
- The SHAP framework reveals the differential contribution of climatic indices to drought clustering, offering high interpretability and novel insight into region-specific vulnerabilities.
- Title and Abstract
Suggestions:
- Include quantitative results (e.g., number of clusters, correlation values) in the abstract to enhance clarity and impact.
- Slightly reduce jargon in the abstract for broader accessibility (e.g., explain “SHAP” in simpler terms before the acronym).
- Introduction
Suggestions:
- Include a short paragraph summarizing existing clustering approaches and why SHAP-RF is a significant improvement.
- Reduce the length of some paragraphs to improve readability and flow.
- Materials and Methods
Suggestions:
- Consider summarizing the 31 climate indices in a supplementary table only, instead of the main text, or condensing Table 1.
- Include more explanation or citation on how SHAP values are computed and interpreted in the clustering context for readers unfamiliar with explainable AI techniques.
- Results
Suggestions:
- Provide statistical significance or validation metrics for SHAP impacts (e.g., confidence intervals or feature importance rankings).
- The explanations of Beeswarm plots can be expanded for clarity.
- Include more information on model performance (e.g., accuracy, F1-score of RF classification for clusters).
- Discussion
Suggestions:
- Integrate more discussion on potential policy or adaptation strategies based on cluster-specific vulnerabilities.
- Acknowledge limitations such as the temporal range of the data (1951–2018), and possible bias due to data resolution or missing climatic drivers.
- Figures and Tables
Suggestions:
- Improve color consistency and legends for clarity (e.g., avoid ambiguous shades).
- Add numerical cluster centroids or representative climate patterns for each cluster.
- Language and Style
Suggestions:
- Consider simplifying overly dense or jargon-heavy sentences (especially in the Introduction and Discussion).
- Check for consistency in the use of abbreviations (e.g., GMT vs. Global Mean Temperature) and ensure all acronyms are introduced properly.
- Novelty and Impact
Suggestions:
- Emphasize more clearly in the Conclusion how the framework can be generalized to other regions beyond the Sahel.
Citation: https://doi.org/10.5194/egusphere-2025-1308-RC2 -
AC2: 'Reply on RC2', Francesco Granata, 11 Jun 2025
The Authors thank the Reviewer for the time devoted to the thorough evaluation of the manuscript and for the valuable and constructive comments provided. Detailed responses to each comment are included in the attached file.
Best regards,
Francesco Granata
Viewed
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
706 | 84 | 17 | 807 | 32 | 9 | 23 |
- HTML: 706
- PDF: 84
- XML: 17
- Total: 807
- Supplement: 32
- BibTeX: 9
- EndNote: 23
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
This paper investigates how various climate indices impacts drought assessment measured by SPEI, based on an explainable-AI framework. Below are my major concerns followed by minor comments.
Major comments:
Minor comments: