Volunteered Geographic Information, Citizen Science and Machine Learning in the Service of Sustainable Development Goals and the Sendai Framework

Abstract

This paper focuses on two prominent efforts tackling global problems, namely the UN Sustainable Development Goals (SDGs) and the Sendai Framework (SF). To achieve the aims sought by these initiatives or to observe and measure their effectiveness and progress, accurate and up-to-date information is needed. An important part of this information refers to geographic information (GI). GI is the fundamental underpinning element that spans the globe, captures time, and functions as the common denominator of many variables and data from other domains. Herein, several enabling factors related to GI are highlighted, and their intertwining impact is examined relative to the aims of SDGs and SF. These factors are Earth observation (EO) imagery enhanced with the advances in machine learning (ML), citizen science (CS), and volunteered geographic information (VGI). The synergy of these factors can be used to bring, on the one hand, the high-level policies and discourse from a theoretical level down to more practical implementations, and on the other hand, enable individual and localized efforts to scale up easily in both developed and developing countries and produce the desired results.