Charting the Future of Earth Observation: Technology Innovation for Climate Intelligence4Executive summary Systemic challenges have historically prevented EO data from being fully integrated into climate solutions, primarily due to its large volume and complexity. Rapid technological advancements in satellite and sensor technologies are addressing these systematic issues alongside new and open artificial intelligence (AI) algorithms, machine learning (ML) techniques and advanced data visualization platforms. These synergistic technologies have allowed the processing of an immense volume of data in almost real time, transforming raw satellite imagery into actionable climate insights in minutes. These advancements are driven by: More insightful data than ever before: Recent advancements in satellite EO sensors drive improved global coverage, resolution, accuracy and a wider array of observable measurements. This enables monitoring of larger swaths of land and more frequent revisit rates. These advancements assist the detection and analysis of climate-related events in regions that were traditionally hard to map in detail. Unprecedented data processing speeds: Sophisticated AI and ML algorithms enable more detailed climate impact assessments (such as those used in post-disaster management) in hours or minutes. This task can take weeks when using traditional models or on-site inspections. Climate ML-based models trained on existing data can produce the same predictions at approximately 1,000 times the speed of traditional models. These improvements in data processing speeds enable timely decision-making, which is particularly relevant in situations requiring real or near-real-time insights, such as rapidly changing weather conditions. Evolution of large and small EO satellites: EO satellite systems have advanced on two opposite fronts. The rise of small satellites and miniaturization of EO sensor technology have enabled more nations and small- and medium-sized enterprises (SMEs) to launch their own satellites, increasing the volume of publicly available EO data. At the same time, there is an increase in the development of larger, more sophisticated satellite platforms. These platforms can host larger sensor instruments and power facilities to meet the growing demand for reliable and continuous EO data transmission. Higher resolution climate forecasting: Climate ML-based models and foundation models are increasing the resolution of climate and weather forecast models twelvefold. These enhanced weather predictions help communities and policy- makers plan targeted mitigation and adaptation strategies to improve climate resilience. Contextual data for end-user needs: Data immersion through augmented reality (AR) and virtual reality (VR) are transforming complex EO datasets into interactive models that help users understand the data and intuitive visual insights that improve decision-making. Digital twins use advanced analytics, ML and AI to analyse data from multiple sources and simulate complex “what if” scenarios. These intuitive technologies allow users to explore and interpret climate data more effectively in a way customized to their needs. Key next steps include: –Expanding EO data access for climate- vulnerable communities –Investing in technology pipelines to drive further innovation in EO-derived climate insights –Integrating EO data into decision-support systems and climate policies to enable informed, actionable and accountable climate strategies. –Enabling cross-sector collaboration Earth observation technologies and advanced data processing are revolutionizing climate intelligence, offering unprecedented insights for proactive action.

Charting the Future of Earth Observation 2024