AI for Remote Sensing: A Chance for Global Climate Change and Sustainable Development of Intelligent Earth

This Research Topic addresses critical limitations in conventional remote sensing for monitoring terrestrial ecosystems especially for vegetation and forests, and limitation in applications of global climate change, as well as for supporting the Sustainable Development Goals (SDGs) and the Intelligent Earth initiative. Current approaches of remote sensing related suffer from inefficient processing of long-term time-series data, struggle with generalization and roughness among heterogeneous regions, lack robust integration with ecological and climate mechanisms, and low accuracy in mapping essential forest attributes (e.g., type, age, carbon storage, and so on). New technologies create a wide range of viable opportunities for these research and bridge several gaps in some research, including a critical absence of physics-informed AI models, interpretable frameworks for multi-source remote sensing fusion, and scalable tools linking forest dynamics to climate feedbacks. We aim to collect some advance research on AI-driven remote sensing methodologies to enable high-precision, large-scale monitoring of forest carbon sinks, ecosystem degradation, and climate-driven disturbances. These breakthroughs will provide robust data foundations essential for climate change mitigation, ecological restoration, and the sustainable development of the Intelligent Earth.Global climate change intensifies forest degradation, biodiversity loss, and carbon cycle imbalance, while terrestrial ecosystems, especially for forests ecosystem play as core regulators of climate stability and vital pillars of sustainable development. Remote sensing provides the only feasible way to monitor global terrestrial ecosystems. However, stack of long time series remote sensing data increase the difficulty of data processing and analysis and it is a challenges for application of remote sensing technology. And traditional methods struggle to capture long-term forest succession, fine-scale disturbances, and non-linear climate responses. Artificial intelligence offers potential way to mine multi-source, multi-temporal remote sensing big data. However, technical challenges (e.g., model interpretability, cross-regional transfer) and practical gaps (e.g., disconnection from forest management and climate policy) hinder real-world impact, creating an urgent need for integrated AI–driven remote sensing solutions.This Research Topic focuses on AI-driven remote sensing application for terrestrial ecosystem and forest monitoring, climate change adaptation, and sustainable development. We welcome original research, reviews articles, methodological papers, dataset papers. Core themes include: physics-informed AI for forest attribute mapping (type, age, biomass/carbon, and so on); time-series AI for detecting forest disturbance and succession; multi-source remote sensing fusion for ecosystem climate response; and AI–remote sensing tools for SDG indicators and Intelligent Earth construction. Preference is given to large-scale, transferable, and practically applicable studies that advance climate mitigation, forest conservation, and sustainable development. We also encourage the research of the technologies of big data mining of remote sensing long time series data and related work.Potential topics of interest include, but are not limited to:- AI-enabled intelligent interpretation of remote sensing, foundation models and advanced earth observation technologies- Big data-driven mechanism analysis and dynamic monitoring of global climate change- Digital technologies for carbon accounting, carbon sink estimation and carbon neutrality implementation- Smart monitoring of ecological protection, biodiversity conservation and restoration assessment- Integrated application of AI & remote sensing to support the UN Sustainable Development Goals (SDGs)- Theory, method, algorithms of Environment monitoring and catastrophic analysis, forecasting and warning Topic editors: Xiguang Yang, Jia Wang, Celso H. L. Silva-Junior Source: https://www.frontiersin.org/research-topics/81603/ai-for-remote-sensing-a-chance-for-global-climate-change-and-sustainable-development-of-intelligent-earth