Sustainability-driven intelligence, design and choice: Strengthening public policy design and implementation in developing countries through decision support systems

Abstract

Sustainability has emerged as a critical global concern, necessitating coordinated efforts among governments, industries, academia, and civil society to address multifaceted challenges such as climate change, water scarcity, and environmental degradation. While developed nations have made significant strides in sustainability-focused policies, developing countries face unique obstacles, including limited financial and technical resources, governance weaknesses, and fragmented data management. This thesis addresses these challenges by developing and implementing Sustainability-Driven Decision Support Systems (SDSS) tailored to the needs of developing regions, with a focus on optimizing resource allocation, enhancing policy design, and improving environmental management. The research is structured around three main objectives: (1) developing replicable, data-driven prioritization methodologies to optimize public resource allocation for climate change mitigation and adaptation; (2) evaluating the effectiveness of SDSS in integrating complex datasets from multiple stakeholders to generate actionable insights; and (3) creating cost-efficient, machine learning-based DSS using open-source and remote sensing data to support sustainability efforts. These objectives are explored through three case studies in the state of Jalisco, Mexico, each addressing distinct sustainability challenges. This thesis explores the development and application of sustainability-driven decision support systems (SDSS) in developing regions, with a focus on the Metropolitan Area of Guadalajara. Chapter 1 presents the introduction and thesis structure. Chapter 2 presents a systematic review of SDSS implementations in developing countries, identifying prevailing trends, key barriers such as data scarcity and limited stakeholder engagement, and highlighting the potential for improving governance, data integration, and cross-sectoral collaboration. Chapter 3 develops a multicriteria prioritization framework to mitigate water scarcity through a rainwater harvesting program, significantly improving access to water and public health outcomes. Chapter 4 addresses environmental degradation in the Santiago River Basin by applying a GIS-based methodology to integrate heterogeneous datasets and identify critical microbasins for targeted infrastructure and policy interventions. Chapter 5 introduces a remote sensing-based fire risk prediction model that employs machine learning and open-access data to provide accurate and cost-effective risk assessments suitable for resource-limited contexts. Finally, Chapter 6 synthesizes the main findings and underscores the relevance of systemic, adaptive, and participatory approaches to sustainability governance, advocating for the incorporation of advanced technologies to enhance the effectiveness, scalability, and resilience of SDSS in the context of developing countries.