Publications
Two publications · same data · distinct framings
Publications
Both publications below are anchored on the same district-month panel of Nepal typhoid surveillance, the same feature engineering, and the same open-source modules. They diverge in scope: the research manuscript presents a tightened three-model comparison with XGBoost as the operational headline; the Master’s thesis extends the framework with a Weighted Ensemble and a full five-chapter scholarly treatment.
Predictive Modeling of Typhoid Incidence in Nepal Under Extreme Climate Change Scenarios Using Machine Learning Algorithm
A tightened, single-publication account of a three-model machine-learning framework — Random Forest, XGBoost, and a Multilayer Perceptron — for predicting district-level typhoid incidence across Nepal’s 77 districts and 108 months (2015–2023). XGBoost is presented as the operational model (R² = 0.8614, RMSE = 129.07 cases / district-month, MAE = 69.50, MAPE = 44.64 %), selected on lowest MAE, interpretability under partial inputs, and reproducibility under a fixed random seed. Climate inputs are drawn entirely from freely available reanalysis sources (ERA5-Land, CHIRPS) and national records (HMIS, DRR portal).
| About | Abstract · Highlights · Figures · Read the paper · How to cite |
| Paper (APA) | Landing · Introduction · Literature Review · Methodology · Results · Discussion · Data · Sources |
| Presentation | Defense-grade slide deck — distilled findings, high-impact register |
| Notebook | Python notebook — the full reproducible pipeline embedded inline |
Predictive Modeling of Typhoid Incidence in Nepal Under Extreme Climate Change Scenarios Using Machine Learning
The full scholarly treatment, organised into five chapters (Introduction, Literature Review, Methodology, Results, Discussion). The thesis extends the three-model manuscript framework with a Weighted Ensemble of Random Forest, XGBoost, and the sequential model — the headline result on the held-out 12-month test window: R² = 0.8675, RMSE = 126.20 cases / district-month, MAE = 68.07, MAPE = 41.01 %. The discussion places the findings within the institutional context of Nepal’s National Adaptation Plan 2021–2050, DHIS2 operationalisation, and the policy implications for typhoid conjugate-vaccine deployment in the Terai.
| About | Abstract · Highlights · Figures · Read the paper · How to cite |
| Paper (APA) | Landing · Introduction · Literature Review · Methodology · Results · Discussion · Data · Sources |
| Presentation | Defense-grade slide deck — distilled findings, high-impact register |
| Notebook | Python notebook |
Disclamier : Not the actual source data committed to this site.