![]() |
International Journal of Scientific Research and Engineering Development( International Peer Reviewed Open Access Journal ) ISSN [ Online ] : 2581 - 7175 |

WISE-Guard: An Explainable Multi-Pathway Spatio-Temporal Framework for Water-Related Disease Risk Prediction and Water Treatment Decision Support
📑 Paper Information
| 📑 Paper Title | WISE-Guard: An Explainable Multi-Pathway Spatio-Temporal Framework for Water-Related Disease Risk Prediction and Water Treatment Decision Support |
| 👤 Authors | Sushma M V, Angel Praises A P, Ashwini C J, Manish L, Suhas S L, D Samiksha Jain |
| 📘 Published Issue | Volume 9 Issue 6 |
| 📅 Year of Publication | 2026 |
| 🆔 Unique Identification Number | IJSRED-V9I6P60 |
📝 Abstract
Water-related diseases remain a persistent public-health challenge, particularly in communities where safe water, sanitation,
hygiene infrastructure and timely disease surveillance are limited. These conditions do not arise through a single transmission
pathway: waterborne infections are acquired through contaminated water; water-washed diseases are associated with
inadequate water for hygiene; water-based infections involve aquatic intermediate hosts; and water-related vector diseases are
transmitted by vectors that breed in or near water. At the same time, water treatment decisions depend on the contaminant,
water matrix and treatment performance rather than on a generic water-quality score. This paper proposes WISE-Guard, an
explainable, multi-pathway decision-support framework that integrates water-quality observations, meteorological and
hydrological indicators, sanitation and hygiene proxies, vector and aquatic-host indicators, geospatial relationships, and
aggregated disease surveillance. A shared data-validation and representation layer feeds separate prediction heads for the four
water-related disease pathways, while a distinct water-assessment module estimates water-quality status and supports evidencebased treatment recommendations. Random Forest and XGBoost provide tabular baselines; a PyTorch spatio-temporal model
learns geographical and temporal dependencies. Missingness indicators, source-quality scores, probability calibration and
SHAP-based explanations are incorporated to communicate limitations and support human review. The paper defines a
reproducible implementation and evaluation protocol using temporal, spatial and combined holdout validation. Since this is a
proposed framework, no experimental performance is claimed. The intended contribution is an integrated and auditable
architecture that connects disease-risk estimation with pathway-appropriate prevention and water-treatment decision support without treating a model prediction as a diagnosis or a water safety certification
📝 How to Cite
Sushma M V, Angel Praises A P, Ashwini C J, Manish L, Suhas S L, D Samiksha Jain, "WISE-Guard: An Explainable Multi-Pathway Spatio-Temporal Framework for Water-Related Disease Risk Prediction and Water Treatment Decision Support" International Journal of Scientific Research and Engineering Development, V9(6): Page(436-444) November - December 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.
📘 Other Details
