Forecasting dengue fever in Brazil: An assessment of climate conditions

• Published in: PloS one Vol. 14; no. 8; p. e0220106
• Main Authors: Stolerman, Lucas M, Maia, Pedro D, Kutz, J Nathan
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 08.08.2019; Public Library of Science (PLoS)
• Subjects: Aedes - metabolism; Aedes - pathogenicity; Aedes aegypti; Algorithms; Animals; Applied mathematics; Aquatic insects; Artificial intelligence; Biological warfare; Biology; Biology and Life Sciences; Brazil; Brazil - epidemiology; Chikungunya Fever - epidemiology; Chikungunya Fever - transmission; Cities; Cities - epidemiology; Cities and towns; Climate; Climate change; Climatic conditions; Data mining; Dengue; Dengue - epidemiology; Dengue - transmission; Dengue fever; Dengue Virus; Disease; Disease transmission; Early warning systems; Earth Sciences; Environment; Environmental aspects; Environmental assessment; Epidemics; Forecasting - methods; Forecasts and trends; Health aspects; Humans; Insect Vectors; Learning algorithms; Local climates; Machine Learning; Medicine and Health Sciences; Mosquito Vectors; Mosquitoes; People and places; Physical Sciences; Precipitation; Prediction models; Public health; Rain; Research and Analysis Methods; Seasons; Temperature; Time series; Tropical diseases; Urban areas; Urban environments; Vector-borne diseases; Viral diseases; Warning systems; Windows (intervals); Yellow fever; Yellow Fever - epidemiology; Yellow Fever - transmission; Zika Virus; Zika Virus Infection - epidemiology; Zika Virus Infection - transmission; Brazil; Cities; Rio de Janeiro Brazil; Thailand; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0220106

Local climate conditions play a major role in the biology of the Aedes aegypti mosquito, the main vector responsible for transmitting dengue, zika, chikungunya and yellow fever in urban centers. For this reason, a detailed assessment of periods in which changes in climate conditions affect the number of human cases may improve the timing of vector-control efforts. In this work, we develop new machine-learning algorithms to analyze climate time series and their connection to the occurrence of dengue epidemic years for seven Brazilian state capitals. Our method explores the impact of two key variables-frequency of precipitation and average temperature-during a wide range of time windows in the annual cycle. Our results indicate that each Brazilian state capital considered has its own climate signatures that correlate with the overall number of human dengue-cases. However, for most of the studied cities, the winter preceding an epidemic year shows a strong predictive power. Understanding such climate contributions to the vector's biology could lead to more accurate prediction models and early warning systems.