WILL MACHINE LEARNING HELP PROVIDE SOLUTIONS TO LAND GOVERNANCE AND POVERTY?
Roger Child et all
Department of Urban Planning, University of Utah, USA
The purpose of this paper is to provide a futurist view of technology available today that can be used to simplify and accelerate the development of land-governance policies, to increase tax revenues, maximize GDP, and reduce poverty. This technology can be used to facilitate financing of infrastructure development, monitor and minimize land-related corruption, and facilitate fair and equitable land-use policies. The paper explores the integration of geospatial data (including topographical, hydrological, agricultural, mineralogical, soils, and energy-related data) layered over Google Earth images and combined with local land-parcel data and analyzed to show how land values can be calculated using pre- and post-development residual land-valuation techniques (see page 12). The paper first applies these methods to the State of Utah where they can be tested against existing alternative-valuation techniques and scenarios. The paper then explores how these same techniques might be applied in developing countries.
Event: Land Governance in an Interconnected World_Annual World Bank Conference on Land and Poverty_2018
Only personal, non-commercial use of this document is allowed.