Mosqlimate
For 40 years, Brazil has witnessed the emergence of diseases transmitted by the mosquito Aedes aegypti: DENV-1 (1986), DENV-2 (1991), DENV-3 (2001), DENV-4 (2010), Chikungunya (2014), and Zika (2015), with severe human and economic costs. Viruses at risk of emergence are Nhong-nhong, Mayaro, and Oropouche. Misdiagnosis is common, and emergence of new viruses can go largely unnoticed. New tools are needed to increase the precision of arbovirus surveillance and control in preparation for climate change. Mosqlimate is a multi-disease tool with two main goals:
- estimate probabilities of change in pattern of disease transmission in response to climate and land use changes;
- identify circulating viruses during outbreaks when information is incomplete.
Mosqlimate will detect signs of expansion of arbovirus transmission areas, as well as signs of outbreaks potentially linked to new arboviruses. The tool will flexibly feed on climate and epidemiological data whenever available. OviCounter will fill in the mosquito data gap by providing digital technology to improve the use of eggtraps for mosquito surveillance at large scale. As output, Mosqlimate will deliver measures of risk to integrate into the Brazilian early warning system Infodengue and its mature community of practice. The ultimate goal of Mosqlimate is to improve the response to epidemiological challenges arising from climate change. Brazil is a continental country with a diversity of environmental and social conditions, all of them showing high vulnerability to the introduction of new viruses. But the frontier of expansion for these diseases do not respect country borders. Mosqlimate will seek to partner with similar initiatives in other countries, with particular emphasis on our South American neighbours.
Mosqlimate will feed on multiple data streams: Infodengue (incidence data), Climate forecasts and mosquito population density data (Ovicounter) and run multi-arboviruses risk assessment models. Mosqlimate has two main endpoints: probability of regime shift, that is, change in pattern of disease transmission from sporadic to epidemic to endemic patterns in response to climate and land use changes; and an alarm model for arbovirus outbreaks by known or new viruses, that will detect signs of expansion of arbovirus transmission areas as well as signs of non-identified outbreaks potentially linked to new arboviruses.
Team
Flávio Codeço Coelho
PI of the Mosqlimate and associate professor at the school of applied mathematics at FGV, Rio de Janeiro, Brazil. I am also part of the GRAPH network, based at the university of Geneva, where I am their data analysis coordinator. In Brazil, I am also one of the coordinators of the Infodengue project. My research interests revolve around the epidemiology of Infectious diseases from the point of view math, statistics and data-science.
Leo Bastos
Public health researcher at Scientific Computing Program (PROCC), Oswaldo Cruz Foundation (Fiocruz). He is a research fellow at FAPERJ and CNPq. His main research is on developing and applying (Bayesian) statistical methods for infectious diseases epidemiology. He is a co-lead on WP2.
Luiz Max Carvalho
Assistant Professor at the School of Applied Mathematics, Getulio Vargas Foundation. His interests are in Biostatistics, in particular Markov chain Monte Carlo, statistical phylogenetics and model combination. He's a co-lead on WP2, hoping to bring state-of-the-art model comparison and combination techniques to predict arboviral diseases.
Leon Alves
Professor at CEFET, Rio de Janeiro, Brazil. Developer of the Conta Ovos application, which aims to monitor the density of Aedes aegypti eggs in space and time. My interests are in image processing and application design.
Luã Bida Vacaro
Computer Science student and Open Source enthusiast. Software Developer & DevOps at Getulio Vargas Foundation, responsible for the development, deployment and maintenance of Mosqlimate's API along with the WP2 group.
Eduardo Corrêa Araujo
Bachelor's in control and automation engineering. He has experience in analyzing public health data and developing machine learning models applied to epidemiological contexts. His interests include data science applied to health, mathematical and computational modeling of diseases, development of tools in Python, and interdisciplinary collaboration in social impact projects. He works as a data scientist in the WP2 of the Mosqlimate project.
Iasmim Ferreira de Almeida
Doctoral student in public health epidemiology at ENSP/FIOCRUZ and a specialist in microbiology. Researcher for the Infodengue project and here at Mosqlimate I am a researcher for the WP2 group, where I will work with models involving arbovirus regimes and their epidemiological and climatic factors. My research interests focus on communicable diseases and their epidemiology.
Fabiana Ganem
A master 's and a doctorate in Epidemiology and Public Health from Universidade de Brasília and Universitat Autònoma de Barcelona. She is a postdoctoral researcher at FGV EMAp and a member of the Mosqlimate Team, doing research on dengue surveillance strategies and the relationship between socioeconomic, climatic, and environmental factors with arboviral diseases.
Raquel Martins Lana
Marie Curie fellow at the Barcelona Supercomputing Center in the Global Health Resilience group. Her background is in quantitative epidemiology and her research focuses on infectious disease dynamics and their association with environmental, climate, and social factors. She is a collaborator in the Mosqlimate project.
Laís Picinini Freitas
Researcher at the Scientific Computing Program (PROCC) of the Oswaldo Cruz Foundation (Fiocruz), Brazil. She holds a master's and a doctorate in Epidemiology in Public Health by the Sergio Arouca National School of Public Health (ENSP/Fiocruz), and completed a year of postdoctoral research at PROCC and three years at the Centre de recherche en santé publique (CReSP), Université de Montréal (UdeM), Canada. Her research focuses on the use of innovative Bayesian models to study the spatial and spatio-temporal distribution of infectious diseases, in particular arboviral diseases, and their relationship with socioeconomic, climatic, and environmental factors.
Thais Riback
Biologist with a MSc and PhD in Zoology. I am interested in studies on ecology and population dynamics of arbovirus vectors and their impact on the dynamics of disease transmission. I currently work as an analyst at the Epidemiological Intelligence Center of the Secretariat of Health of Rio de Janeiro City and as a collaborating researcher in the Infodengue system.
Sandro Loch
BIG DATA and AI student, with a focus on backend development and a commitment to collaborating on Open Source projects. My journey aims to combine technical expertise with meaningful contributions to projects that have a tangible impact on society. I work as a developer and maintainer of the Infodengue project, where I contribute to enhancing the visualization and analysis of data related to arboviruses.
Bruno Carvalho
Postdoctoral researcher at the Barcelona Supercomputing Center in the Global Health Resilience group, where he develops infectious disease models for early warning and decision support. He builds indicators to track the impacts of climate change on health using open-access and reproducible digital toolkits. He is a biologist, PhD in Ecology and Evolution, and MSc in Parasitology. As a collaborator in Mosqlimate, Bruno is developing deep learning models to predict dengue in Brazil using data from the Infodengue system.
Marcio Maciel Bastos
Physics PhD candidate, holds a profound affinity for dynamic systems, statistical mechanics, Bayesian inference, and machine learning. Currently contributing his insights as a collaborative researcher to the Mosqlimate project.
Lucas Monteiro Bianchi
Statistician and data scientist, holding a PhD in Epidemiology in Public Health from ENSP/FIOCRUZ. My professional experience includes applying statistical and machine learning methodologies to diverse fields such as agriculture and healthcare, as well as contributing to public health initiatives and data analysis for international organizations.
Beatriz Laiate
Postdoctoral researcher at FGV EMAp and a member of the Mosqlimate Team doing research on Bayesian inference, Mathematical modeling of Dengue fever, and Possibility Theory. Holds a master's and a Ph.D. in Applied Mathematics from the University of Campinas. She is curious about hybrid models of infectious diseases involving dynamical fuzzy systems, neural networks, and statistical methods of uncertainty quantification.
Davi Sales Barreira
Postdoctoral researcher at FGV EMAp and a member of the Mosqlimate Team, where he focuses on dengue forecasting using machine learning and optimal transport methods within spatio-temporal modelling. Holds a PhD in Applied Mathematics and Data Science from FGV EMAp.
Julie Souza
Postdoctoral researcher at FGV EMAp. She is an applied mathematician, physicist, and data scientist with a PhD in Applied Mathematics and Data Science. She holds a master’s and a bachelor’s degree in Physics. Her research focuses on mathematical modeling of epidemics, emphasizing using epidemiological model-informed neural networks (PINNs) to capture complex dengue dynamics. She also has expertise in machine learning, causal inference, and developing data pipelines for epidemiological analysis. Her work seeks to integrate advanced computing and artificial intelligence methods for understanding and controlling infectious diseases.
Ezequiel Braga
Master's student in Applied Mathematics and Data Science at FGV EMAp. His work focuses on Bayesian modeling, particularly in power priors. He currently serves as a research assistant on the hdbayes R package project and Mosqlimate. His primary research interests lie in biostatistics, especially in Bayesian and computational statistics.
Zuilho Segundo
Undergraduate student in Data Science and Artificial Intelligence at FGV EMAp. I'm particularly interested in Machine Learning and Reinforcement Learning. Currently, I'm working on reinforcement learning models where agents are designed to optimize testing distribution for arboviral diseases such as dengue and chikungunya across different regions.
Sillas Rocha
Undergraduate student in Data Science and Artificial Intelligence at FGV EMAp. He is currently working on integrating an AI assistant into the Mosqlimate platform. His interests focus on Machine Learning, particularly Deep Learning models.
