Geospatial variation and machine learning approaches to predict open defecation practice in Zambia

Andualem Addisu Birlie, Nega Abebe Meshesha, Sefefe Birhanu Tizie, Smegnew Gichew Wondie, Selamawit Gashaw Teshome, Tesfaye Deribe Bedada, Ayana Alebachew Muluneh, Biruktawit Lelisa Eticha · 2026

Read Geospatial variation and machine learning approaches to predict open defecation practice in Zambia by Andualem Addisu Birlie, Nega Abebe Meshesha, Sefefe Birhanu Tizie, Smegnew Gichew Wondie, Selamawit Gashaw Teshome, Tesfaye Deribe Bedada, Ayana Alebachew Muluneh, Biruktawit Lelisa Eticha (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0350923.txt.

Description

Andualem Addisu Birlie and colleagues mapped open defecation across Zambia and trained models to predict where it persists. Going outdoors instead of using a toilet spreads gut disease and pollutes water. A 2024 national survey covered close to thirteen thousand households. Map tools found clusters, while seven learning models raced to predict household practice from survey traits.

About twelve percent of households still practised open defecation. Hot spots clustered in southern, western, and eastern regions. A light boosting model predicted best among the seven. Maps plus prediction, the team argues, let sanitation programmes spend first where need and risk run highest, rather than spreading thin funds evenly.

Catalog record

CREATORAndualem Addisu Birlie, Nega Abebe Meshesha, Sefefe Birhanu Tizie, Smegnew Gichew Wondie, Selamawit Gashaw Teshome, Tesfaye Deribe Bedada, Ayana Alebachew Muluneh, Biruktawit Lelisa Eticha
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE48706
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350923

Browse the full library · About the Tower of Babel