This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intellige...This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection techniques.Traditional models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical processes.However,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world applicability.In contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical knowledge.ML techniques have shown promise in addressing Earth science-related questions.Nevertheless,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into geoscience.The integration of physics-based and data-driven methodologies into hybrid models presents an alternative paradigm.These models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data requirements.This review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and geoscience.It examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in geoscience.The paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.展开更多
Environmental pollution is escalating due to rapid global development that often prioritizes human needs over planetary health.Despite global efforts to mitigate legacy pollutants,the continuous introduction of new su...Environmental pollution is escalating due to rapid global development that often prioritizes human needs over planetary health.Despite global efforts to mitigate legacy pollutants,the continuous introduction of new substances remains a major threat to both people and the planet.In response,global initiatives are focusing on risk assessment and regulation of emerging contaminants,as demonstrated by the ongoing efforts to establish the UN’s Intergovernmental Science-Policy Panel on Chemicals,Waste,and Pollution Prevention.This review identifies the sources and impacts of emerging contaminants on planetary health,emphasizing the importance of adopting a One Health approach.Strategies for monitoring and addressing these pollutants are discussed,underscoring the need for robust and socially equitable environmental policies at both regional and international levels.Urgent actions are needed to transition toward sustainable pollution management practices to safeguard our planet for future generations.展开更多
基金supported by National Natural Science Foundation of China(T2225019,41925007,62372470,U21A2013,42201415,42022054,42241109,42077156,52121006,42090014,and 42325107)the National Key R&D Programme of China(2022YFF0500)+2 种基金the Youth Innovation Promotion Association CAS(2023112)the Strategic Priority Research Program of CAS(XDA23090303)the RECLAIM Network Plus(EP/W034034/1).
文摘This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection techniques.Traditional models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical processes.However,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world applicability.In contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical knowledge.ML techniques have shown promise in addressing Earth science-related questions.Nevertheless,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into geoscience.The integration of physics-based and data-driven methodologies into hybrid models presents an alternative paradigm.These models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data requirements.This review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and geoscience.It examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in geoscience.The paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.
基金funded by the National Key Research and Development Program of China(2020YFC1807000)the Strategic Priority Research Program of the Chinese Academy of Sciences(no.XDA28030501)+9 种基金the National Natural Science Foundation of China(41991333,41977137,42090060)the International Atomic Energy Agency Research Project(D15022)the Youth Innovation Promotion Association of Chinese Academy of Sciences(2011225[Fang Wang],Y201859[H.Wang],2013201[J.Su],2021309[Y.Song],Y2022084[M.Ye])Chinese Academy of Sciences President’s International Fellowship Initiative(2020DC0005,2022DC0001,2024DC0009)the Institute of Soil Science,Chinese Academy of Sciences(ISSAS2419)the Research Group Linkage project from Alexander von Humboldt foundation,the Center for Health Impacts of Agriculture(CHIA)of Michigan State University,and the URI STEEP Superfund Center(grant#P42ES027706)Fang Wang was partly supported by the fellowship of Alexander von Humboldt for experienced researchers,and Shennong Young Talents of the Ministry of Agriculture and Rural Affairs,China(SNYCQN006-2022)J.P.and T.R.S.were supported by the Canada Research Chair program.B.W.B.was supported by a Royal Society of New Zealand Catalyst International Leaders fellowship.K.K.B.was supported by Innovation Fund Denmark and the European Commission Horizon 2020 financed under the ERA-NET Aquatic Pollutants Joint Transnational Call(REWA,GA no.869178)S.A.H.was partly supported by a grant from the National Institute of Environmental Health Sciences,National Institutes of Health grant number P42ES04911-29(Project 4)T.R.S.thanks CESAM by FCT/MCTES(UIDP/50017/2020+UIDB/50017/2020+LA/P/0094/2020)。
文摘Environmental pollution is escalating due to rapid global development that often prioritizes human needs over planetary health.Despite global efforts to mitigate legacy pollutants,the continuous introduction of new substances remains a major threat to both people and the planet.In response,global initiatives are focusing on risk assessment and regulation of emerging contaminants,as demonstrated by the ongoing efforts to establish the UN’s Intergovernmental Science-Policy Panel on Chemicals,Waste,and Pollution Prevention.This review identifies the sources and impacts of emerging contaminants on planetary health,emphasizing the importance of adopting a One Health approach.Strategies for monitoring and addressing these pollutants are discussed,underscoring the need for robust and socially equitable environmental policies at both regional and international levels.Urgent actions are needed to transition toward sustainable pollution management practices to safeguard our planet for future generations.