Integrated risk mapping and targeted snail control to support schistosomiasis elimination in Brazil and Cote d’Ivoire under future climate change

This highly interdisciplinary, transnational team has three main goals: FIRST, we intend to investigate the effect of increasing temperatures, temperature variability and shift in precipitation patterns due to climate change on the dynamics of snail-born schistosomiasis, a debilitating parasitic disease of poverty affecting more than 200 million people worldwide. We will focus on Brazil and Cote d'Ivoire for these compelling reasons: Brazil suffers the highest schistosomiasis burden in the Americas, with an estimated 2-6 million people infected by the S.mansoni worm. Cote d'Ivoire has a high disease prevalence with an estimated 4 million people infected by S.hameatobium and S.mansoni. Projected climate change - along with growing human population, deforestation, expansion of agriculture and of marginal urban settings and the development of dams and irrigation canals known to be associated with increased schistosomiasis risk caused by habitat expansion for, and extirpation of natural predators of, the snail intermediate host - make these two countries particularly vulnerable to this parasitic disease. We will use a hybrid approach integrating species distribution models accounting for the most relevant socio-economic and environmental drivers of schistosomiasis with temperature-driven, process-based mathematical models of the parasite and its intermediate snail hosts to produce maps of present and future risk for schistosomiasis under climate change. SECOND, we intend to conduct initial feasibility and nutritional studies and market analyses of aquaculture of freshwater prawns native of Brazil and of Cote d'Ivoire with the goal of using them as novel biological control agents of schistosome's snail host while, at the same time, promoting the development of small-scale aquaculture businesses. THIRD, to track future changes in the distribution and abundance of the snail hosts, we will develop machine learning algorithms that enable computer vision as an environmental diagnosis tool for the quick and accurate identification of potential schistosome-host snails and parasites from field-acquired cellphone images, trained on thousands of images that have been identified to species by the gold standard of DNA barcoding and PCR-RFLP.