64th ISI World Statistics Congress - Ottawa, Canada

64th ISI World Statistics Congress - Ottawa, Canada

Collaborative Groups for Modeling Mosquito Abundance Dynamics and Malaria Case Fluctuations in Remote Amerindian Regions

Author

LB
Lelys I. Bravo de Guenni

Co-author

  • Y
    Yasmin Rubio-Palis
  • C
    Cheng Song
  • S
    Songyuan Wang
  • L
    Linjia Feng
  • X
    Xiao Zhang
  • D
    Duchnicki Tymon

Conference

64th ISI World Statistics Congress - Ottawa, Canada

Format: IPS Abstract

Keywords: machine learning, missing-data, missingness

Session: IPS 192 - Advancing environmental statistics through online collaborative groups

Monday 17 July 2 p.m. - 3:40 p.m. (Canada/Eastern)

Abstract

Entomological surveillance in remote locations for malaria control presents significant challenges. Collecting mosquito data over sustained periods is crucial for understanding species population dynamics and their biting behavior in the transmission of malaria parasites to humans. However, a high proportion of missing data and poor data quality may hinder the usability of available information. To address this issue, a multidisciplinary collaborative group of entomology and data science students and researchers was formed. The group investigated various strategies for handling missing data and compared machine learning approaches and statistical methods. Environmental factors influencing mosquito life cycles were utilized to enhance prediction accuracy and explicability in machine learning methods. The study also discusses the application of generalized time series models and machine learning approaches for predicting malaria cases. This example demonstrates the effectiveness of collaborative online networking in solving complex data science problems in environmental and epidemiological applications.