Over the past decades, the ease of use of the Earth Observation (EO) data has increased rapidly through the advent of cloud technologies, common standards, and an integrated knowledge base. This has caused spatial decision support systems (SDSS) for disaster preparedness and mitigation to evolve significantly. This chapter outlines several advancements in the field of modern SDSS through the incorporation of new big data platforms, simplified implementation of cutting-edge technology, and approaches such as theory of change (ToC) frameworks and machine learning (ML) to vastly improve end-users decision-making efficiency. Specifically, in this chapter two SDSS approaches, which have been codeveloped and are actively utilized by decision-makers, are highlighted at a regional and national level. The HYDrologic Remote Sensing and Analysis for Floods (HYDRAFloods) and HydroSAR approaches underscore the advancements, integration, and customization of cloud-based EO and applied ML and deep learning (DL) approaches for informing elements of disaster mitigation. An array of EO, statistical, and ML methods are outlined centering on rapid near real-time flood inundation mapping via two distinctive cloud technology platforms. With two specific use cases set in South and South East Asia, coupling these technological and methodological advances results in real-world examples of streamlined decision-making through a ToC approach resulting in customized SDSS information platforms.