Antonio Vazquez Brust

arXiv2021

Mapping illegal waste dumping sites with neural-network classification of satellite imagery

Public health and habitat quality are crucial goals of urban planning. In recent years, the severe social and environmental impact of illegal waste dumping sites has made them one of the most serious problems faced by cities in the Global South, in a context of scarce information available for decision making. To help identify the location of dumping sites and track their evolution over time we adopt a data-driven model from the machine learning domain, analyzing satellite images. This allows us to take advantage of the increasing availability of geo-spatial open-data, high-resolution satellite imagery, and open source tools to train machine learning algorithms with a small set of known waste dumping sites in Buenos Aires, and then predict the location of other sites over vast areas at high speed and low cost. This case study shows the results of a collaboration between Dymaxion Labs and Fundación Bunge y Born to harness this technique in order to create a comprehensive map of potential locations of illegal waste dumping sites in the region.

cs.LG↗

arXiv2020

Detecting Areas of Potential High Prevalence of Chagas in Argentina

A map of potential prevalence of Chagas disease (ChD) with high spatial disaggregation is presented. It aims to detect areas outside the Gran Chaco ecoregion (hyperendemic for the ChD), characterized by high affinity with ChD and high health vulnerability. To quantify potential prevalence, we developed several indicators: an Affinity Index which quantifies the degree of linkage between endemic areas of ChD and the rest of the country. We also studied favorable habitability conditions for Triatoma infestans, looking for areas where the predominant materials of floors, roofs and internal ceilings favor the presence of the disease vector. We studied determinants of a more general nature that can be encompassed under the concept of Health Vulnerability Index. These determinants are associated with access to health providers and the socio-economic level of different segments of the population. Finally we constructed a Chagas Potential Prevalence Index (ChPPI) which combines the affinity index, the health vulnerability index, and the population density. We show and discuss the maps obtained. These maps are intended to assist public health specialists, decision makers of public health policies and public officials in the development of cost-effective strategies to improve access to diagnosis and treatment of ChD.

cs.SI↗