Team:Lambert GA/Software

CALM ELECTROPEN
BACKGROUND DATA & METHODS RESULTS DISCUSSION COLOR Q SUPPLEMENTARY REFERENCES
COLOR Q CHROME Q REFERENCES
PRINCIPLES & DESIGN MODEL & THEORY PRODUCT DESIGN REFERENCES
INTEGRATED HUMAN PRACTICES EDUCATION & ENGAGEMENT COLLABORATIONS
BASIC PARTS COMPOSITE PARTS
DESCRIPTION BACKGROUND DESIGN EXPERIMENTS LAB NOTEBOOK INTERLAB RESULTS DEMONSTRATE THE VISION
TEAM MEMBERS ATTRIBUTIONS

C A L M O V E R V I E W



































OVERVIEW


The ongoing Yemeni cholera outbreak has been deemed one of the worst cholera outbreaks in history, resulting in thousands of deaths. Triggered by a civil war, the outbreak has been shaped by various political, environmental, and epidemiological factors and has impacted to over a million Yemenis. Limited access to healthcare infrastructure deters citizens from receiving widely available treatments for the disease. To solve this issue, various mathematical models have been made to track the Yemeni outbreak and identify governorates (administrative divisions) at risk of an outbreak by providing advance notice of incidence. These models, while useful, are not powerful enough to accurately and consistently forecast exact cholera cases per governorate over multiple timeframes. To address the need for a complex, reliable model, the Lambert iGEM team presents CALM, the Cholera Artificial Learning Model; a system of four extreme-gradient-boosting (XGBoost) machine learning models that forecast the exact number of cholera cases a Yemeni governorate will experience from a time range of 2 weeks to 2 months. CALM provides a novel machine learning approach that makes use of rainfall data, past cholera cases and deaths data, civil war fatalities, and inter-governorate interactions represented across multiple timeframes. Additionally, the use of machine learning, along with extensive feature engineering, allows CALM to easily learn complex non-linear relations apparent in an epidemiological phenomenon.