Learning invention using satellite observations to support sustainable development goals (SDG): A use case on disaster risk reduction in Sei Serelo Indonesia

Abstract

The morphological pattern of the Sei Serelo was investigated to infer the impact of land use and climate change. Two sets of areal Landsat (1990 and 2019) identified the morphological changes to reduce the disaster risk and ideally reverse this prevailing situation. This paper presents a scalable and flexible approach to monitoring land-use change at the local level using various components of the Global Earth Observation System of Systems (GEOSS) platform. Increasing mining area has contributed to land-use change and the loss of agricultural land in many rural areas. In many cases, it worsens the poverty levels of smallholder farmers who depend on subsistence farming – an issue that Sustainable Development Goals number one seeks to address. A multi-criteria evaluation is applied using morphometric indicators, geology, and contours to identify the areas vulnerable to drainage and relief conditions. This learning invention has developed decision tools to apply GIS utilization to support disaster risk reduction. The devices are iterative and can be updated as new events occur to maximize GIS benefit, reducing disaster risk reduction and their potential consequences.