Despite the efforts made towards the Millennium Development Goals targets during the last
decade, still millions of people across the world lack of improved access to water supply or
basic sanitation. The increasing complexity of the context in which these services are delivered
is not properly captured by the conventional approaches that pursue to assess water, sanitation
and hygiene (WaSH) interventions. Instead, a holistic framework is required to integrate the
wide range of aspects which are influencing sustainable and equitable provision of safe water
and sanitation, especially to those in vulnerable situations.
In this context, the WaSH Poverty Index (WaSH-PI) was adopted, as a multi-dimensional policy
tool that tackles the links between access to basic services and the socio-economic drivers of
poverty. Nevertheless, this approach does not fully describe the increasing interdependency of
the reality. For this reason, appropriate Decision Support Systems (DSS) are required to i)
inform about the results achieved in past and current interventions, and to ii) determine expected
impacts of future initiatives, particularly taking into account envisaged investments to reach the
targets set by the Sustainable Development Goals (SDGs). This would provide decision-makers
with adequate information to define strategies and actions that are efficient, effective, and
sustainable. This master thesis explores the use of object-oriented Bayesian networks (ooBn) as
a powerful instrument to support project planning and monitoring, as well as targeting and
prioritization. Based on WaSH-PI theoretical framework, a simple ooBn model has been
developed and applied to reflect the main issues that determine access to safe water, sanitation
and hygiene.
A case study is presented in Kenya, where the Government launched in 2008 a national program
aimed to increase the access to improved water, sanitation and hygiene in 22 of the 47 existing
districts. Main impacts resulted from this initiative are assessed and compared against the initial
situation. This research concludes that the proposed approach is able to accommodate the
conditions at different scales, at the same time that reflects the complexities of WaSH-related
issues. Additionally, this DSS represents an effective management tool to support decisionmakers
to formulate informed choices between alternative actions.
gmail.com
