6 — Data

Manuscript · APA section

Manuscript · Section 6 of 7 · Paper landing

6.1 Source datasets

Dataset Variable Resolution Provider Reference
HMIS Monthly outpatient typhoid case counts District-month MoHP / DoHS, Government of Nepal (Ministry of Health and Population, Government of Nepal, 2023)
DRR Portal Flood event counts District-month event records NDRRMA / MoHA, Government of Nepal (NPDRR Nepal, 2025)
CHIRPS v2.0 Precipitation 0.05° (~5 km) → area-weighted district mean Climate Hazards Group, UC Santa Barbara (Funk et al., 2015)
ERA5-Land 2 m mean air temperature; relative humidity 0.1° (~9 km) → area-weighted district mean ECMWF · Copernicus C3S (Muñoz-Sabater et al., 2021)
District shapefiles Administrative boundaries District polygons (2021 census) Central Bureau of Statistics, Nepal (Central Bureau of Statistics, 2021)

6.2 Access conditions

6.3 Variable definitions

6.3.1 Raw variables

Variable Definition Unit Range Source
cases Monthly OPD enteric-fever cases per district count 1 – 2,772 HMIS (Ministry of Health and Population, Government of Nepal, 2023)
precip Monthly district-mean precipitation mm 0 – 1,100 CHIRPS (Funk et al., 2015)
temp_mean Monthly district-mean 2 m air temperature °C −18 to +31.5 ERA5-Land (Muñoz-Sabater et al., 2021)
humidity Monthly district-mean relative humidity % 25.7 – 95.7 ERA5-Land (Muñoz-Sabater et al., 2021)
flood_events Count of flood events recorded count 0 – 8 DRR Portal (NPDRR Nepal, 2025)

6.3.2 Engineered features

Feature Derivation
log_cases log(cases + 1) — primary ML outcome
cases_lag1 cases shifted 1 month within district
precip_lag1 CHIRPS precipitation shifted 1 month
temp_mean_lag1 ERA5-Land temperature shifted 1 month
humidity_lag1 ERA5-Land humidity shifted 1 month
flood_lag1 DRR flood count shifted 1 month
precip_roll3 rolling mean precipitation over t, t−1, t−2
temp_roll3 rolling mean temperature over t, t−1, t−2
monsoon 1 if month ∈ {Jun, Jul, Aug, Sep}; else 0
month_sin, month_cos sin/cos(2π × month / 12) — cyclical encoding

6.4 Harmonization pipeline

  1. Calendar conversion — Bikram Sambat → Gregorian via 12-month mapping table (max alignment error ~15 days).
  2. District-code reconciliation — CBS 3-digit codes as primary spatial merge key; 12 name-spelling variants resolved.
  3. Numeric cleaning — comma-formatted HMIS counts parsed; 847 records corrected.
  4. Spatial aggregation — CHIRPS and ERA5-Land grids aggregated to district polygons by area-weighted zonal statistics.
  5. Missing data — 2,463 district-months excluded; no outcome imputation. Final analytical sample: N = 7,327.

6.5 Data quality and limitations

  • HMIS under-reporting — HMIS captures only outpatient cases at public health facilities. Under-reporting is likely most severe in Karnali and Sudurpashchim Provinces where facility density is lowest. Reported counts should be interpreted as indices of relative burden rather than absolute incidence.
  • Diagnostic misclassification — HMIS enteric-fever data are based primarily on clinical diagnosis; may include cases of malaria, dengue, leptospirosis without lab confirmation (Parry et al., 2002).
  • Spatial aggregation — District-level CHIRPS and ERA5-Land aggregation averages over intra-district topographic and climatic heterogeneity.
  • Flood-event underregistration — DRR Portal may undercount small-scale localized flooding events.
  • Ecological fallacy — Findings describe population-level associations and cannot be applied to individual-level risk.

6.6 Reproducibility

All preprocessing, feature engineering, model training, and figure generation are executed by the open-source Python pipeline:

cd manuscript
python3 main.py

The pipeline reads four CSV source files (climate, flood, typhoid 1 & 2) from manuscript/data/; supporting modules live in manuscript/src/. Trained model artifacts and figures are emitted to manuscript/output/figures/ and manuscript/output/analysis/.

← Back: 5 — Discussion · → Next: 7 — Sources

References

Central Bureau of Statistics. (2021). National population and housing census 2021: Preliminary results. Government of Nepal. https://cbs.gov.np
Funk, C., Peterson, P., Landsfeld, M., Pedreros, D., Verdin, J., Shukla, S., Husak, G., Rowland, J., Harrison, L., Hoell, A., & Michaelsen, J. (2015). The climate hazards infrared precipitation with stations—a new environmental record for monitoring extremes. Scientific Data, 2, 150066. https://doi.org/10.1038/sdata.2015.66
Ministry of Health and Population, Government of Nepal. (2023). Annual report of the department of health services 2022/23. Government of Nepal.
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., & Thépaut, J.-N. (2021). ERA5-Land: A state-of-the-art global reanalysis dataset for land applications. Earth System Science Data, 13(9), 4349–4383. https://doi.org/10.5194/essd-13-4349-2021
NPDRR Nepal. (2025). Nepal disaster statistics 2012–2024. https://www.drrportal.gov.np/
Parry, C. M., Hien, T. T., Dougan, G., White, N. J., & Farrar, J. J. (2002). Typhoid fever. New England Journal of Medicine, 347(22), 1770–1782. https://doi.org/10.1056/NEJMra020201