Supporting sanitation infrastructure planning in low-income areas with URBANUS

• Maria do Carmo O. Correia Universidade de São Paulo (USP)
• Erick P. A. Barcelos Universidade de São Paulo (USP)
• Augusto C. B. Pereira Universidade de São Paulo (USP)
• Gerson Seluque Ferreira SELCO Arquitetura e Engenharia Ltda
• Mirela T. Cazzolato Universidade de São Paulo (USP) https://orcid.org/0000-0002-4364-010X

DOI: https://doi.org/10.5753/sbbd_estendido.2026.249694

Resumo

Access to sanitation infrastructure remains a critical challenge in low-income urban areas, with direct consequences for public health and social equity. We propose URBANUS, a web-based decision-support platform that automates the preliminary design of sanitary sewer collection networks using publicly available geospatial data. The system models the urban street network as a graph, enriches vertices with topographic elevation, and applies a gravitational routing heuristic (RSPH) to generate a directed sewer network aligned with terrain constraints. An interactive editor allows specialists to inspect and adjust the graph before processing, keeping human expertise inside the computational workflow. A deep learning module for building detection from satellite imagery, based on fine-tuned models, enables accurate sewage contribution estimates per lot. A use case with a Brazilian municipality reduced the domain expert work from days to seconds. URBANUS aims to support engineers, municipalities, and policymakers in expanding coverage to underserved communities.

Palavras-chave: Urban planning, sanitation, directed graph, urban network, satellite image

Referências

Alidoost, F. and Arefi, H. (2018). A CNN-based approach for automatic building detection and recognition of roof types using a single aerial image. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 86(5–6):235–248.

Bentley Systems, Incorporated (2024). OpenFlows Sewer: Wastewater collection system modeling and management. Accessed: 2025-12-08.

Boeing, G. (2017). OSMnx: New methods for acquiring, constructing, analyzing, and visualizing complex street networks. Computers, Environment and Urban Systems, 65:126–139.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.

Haghighi, A. and Bakhshipour, A. E. (2012). Optimization of sewer networks using an adaptive genetic algorithm. Water Resources Management, 26(12):3441–3456.

Haydar, B., Chahinian, N., and Pasquier, C. (2026). Reconstructing sewer network topology using graph theory. Water, 18(2):222.

Instituto Brasileiro de Geografia e Estatística (2024). Censo demográfico 2022: Características dos domicílios – resultados do universo. Technical report, IBGE, Rio de Janeiro. Accessed: 2026-05-25.

Mnih, V. (2013). Machine Learning for Aerial Image Labeling. PhD thesis, University of Toronto. Introduces the Massachusetts Buildings Dataset. Accessed: 2026-03-29.

Motta, O. M., Quelhas, O. L. G., and Farias Filho, J. R. (2011). Alinhando os objetivos tecnicos do projeto as estrategias de negocio: contribuicao da metodologia FEL no pre-planejamento de grandes empreendimentos. Revista Gestao Industrial, 7(4):99–117.

OpenStreetMap contributors (2026). OpenStreetMap. Accessed: 2026-05-19.

OpenTopography (2026). OpenTopography: High-resolution topography data and tools. Accessed: 2026-05-19.

Peterschinegg GesmbH (2025). Urbano Hydra: Infrastructure pipe network design. Accessed: 2025-12-08.

Prüss-Ustün, A., Wolf, J., Bartram, J., Clasen, T., Cumming, O., Freeman, M. C., Gordon, B., Hunter, P. R., Medlicott, K., and Johnston, R. (2019). Burden of disease from inadequate water, sanitation and hygiene for selected adverse health outcomes: An updated analysis with a focus on low- and middle-income countries. International Journal of Hygiene and Environmental Health, 222(5):765–777.

Rodrigues, G. P. W., Farias, G. M., Costa, L. H. M., and Castro, M. A. H. d. (2020). Otimização do traçado de redes coletoras de esgoto sanitário via algoritmo genético. Revista DAE, 68(222):164–177.

Software Público Brasileiro (2014). GSAN/GeoSan: Sistema integrado de gestão de serviços de saneamento e GeoSan – módulo GIS. Accessed: 2026-05-05.

Turan, M. E., Bacak-Turan, G., Cetin, T., and Aslan, E. (2019). Feasible sanitary sewer network generation using graph theory. Advances in Civil Engineering, 2019:8527180.

Weng, H. T. and Liaw, S. L. (2005). Establishing an optimization model for sewer system layout with applied genetic algorithm. Journal of Environmental Informatics, 5(1):26–35.

Zhang, S., Li, M., Zhao, W., Wang, X., and Wu, Q. (2025). Building type classification using CNN-Transformer cross-encoder adaptive learning from very high resolution satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18:976–994.

Zhou, W., Persello, C., and Stein, A. (2024). Hierarchical building use classification from multiple modalities with a multi-label multimodal transformer network. International Journal of Applied Earth Observation and Geoinformation, 132:104038.