A Bayesian machine learning model for estimating building occupancy from open source data

Abstract

Understanding building occupancy is critical to a wide array of applications including natural hazards loss analysis, green building technologies, and population distribution modeling. Due to the expense of directly monitoring buildings, scientists rely in addition on a wide and disparate array of ancillary and open source information including subject matter expertise, survey data, and remote sensing information. These data are fused using data harmonization methods, which refer to a loose collection of formal and informal techniques for fusing data together to create viable content for building occupancy estimation. In this paper, we add to the current state of the art by introducing the population data tables (PDT), a Bayesian model and informatics system for systematically arranging data and harmonization techniques into a consistent, transparent, knowledge learning framework that retains in the final estimation uncertainty emerging from data, expert judgment, and model parameterization. PDT aims to estimate ambient occupancy in units of people/1000 ft 2 for a number of building types at the national and sub-national level with the goal of providing global coverage. We present the PDT model, situate the work within the larger community, and report on the progress of this multi-year project.

Census-independent population mapping in northern Nigeria

“…An occupancy-based model (people per structure) was found to be more accurate than a rooftop area-based model, but the authors stressed the importance of practical considerations when choosing a density denominator. A third study ( Stewart et al, 2016 ) estimated daytime and nighttime population using population density models derived from literature and internet sources and linked to specific facility types. Again, building footprints and classifications were identified manually from satellite and street-level imagery.…”

National population mapping from sparse survey data: A hierarchical Bayesian modeling framework to account for uncertainty

“…Advances in Bayesian statistics ( 6 ) provide the building blocks necessary to customize models for specific microcensus or other population data. Specifically, hierarchical population models that are commonly used in ecology ( 7 , 8 ) provide a methodological foundation for mapping populations in data-poor environments and accounting for uncertainty ( 9 , 10 ). These models can include geospatial covariates as predictors of population density and can easily be extended to accommodate complex relationships such as non-Gaussian error structures, random effects, age structure, observer error, spatial and temporal autocorrelation, and nonlinear models.…”

Introducing IEA EBC annex 79: Key challenges and opportunities in the field of occupant-centric building design and operation

“…Firstly, given the costs and uncertainties associated with measuring the total number of occupants in buildings through traditional methods [94,95], availability of social media data can provide alternative solutions. Social media data has been researched for urban mobility and disaster evacuation, for example, to provide new insights in areas including travel recommendation, industrial competitive analysis and activeness identification [96][97][98].…”