npj Climate and Atmospheric Science最新文献

英文中文

Heatwave magnitude quantization and impact factors analysis over the Tibetan Plateau

IF 9 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2025-01-06 DOI: 10.1038/s41612-024-00877-x

Tongchang Zhang, Gang Deng, Xiuguo Liu, Yan He, Qikai Shen, Qihao Chen

More frequent and intense heatwave events (HWEs) on the Tibetan Plateau (TP) present substantial threats to the ecological and hydrological systems. However, understanding the changes in HWEs on the TP is limited, primarily from analyses at individual stations or single elements (glaciers, lakes). Here, using refined data, we quantify the heatwave magnitude by aggregating multiple indicators into a comprehensive index and explore the influence of environmental factors on the heatwave magnitude over the TP. Our findings indicate that the heatwave magnitude has significantly increased since the 21st century, especially in autumn. From 1979–2000 to 2001–2022, the heatwave magnitude hotspots migrated toward the northwestern TP, whereas the regions with the most rapid increase shifted in the opposite direction. During the inter-seasonal, from spring to winter, the migration direction of the heatwave magnitude hotspots changed from the northwest in the first 22 years (1979–2000) to the southeast in the recent 22 years (2001–2022). We also find that downward shortwave radiation plays a significant role in the spatial stratified heterogeneity (SSH) of the heatwave magnitude, while the trend of temperature plays a dominant role in the SSH of the trend of heatwave magnitude. Moreover, elevation is correlated with the heatwave magnitude variability. The elevation-dependence of the heatwave magnitude has become more pronounced in the recent 22 years, with a high-heatwave magnitude migrating to higher elevations. Furthermore, the difference in land cover type can also affect the intensity of the heatwave magnitude to some extent. Our findings underscore the migration patterns of the heatwave magnitude evolution around the 21st century and provide a scientific basis for understanding the interaction between environmental factors and the heatwave magnitude in different periods.

{"title":"Heatwave magnitude quantization and impact factors analysis over the Tibetan Plateau","authors":"Tongchang Zhang, Gang Deng, Xiuguo Liu, Yan He, Qikai Shen, Qihao Chen","doi":"10.1038/s41612-024-00877-x","DOIUrl":"https://doi.org/10.1038/s41612-024-00877-x","url":null,"abstract":"More frequent and intense heatwave events (HWEs) on the Tibetan Plateau (TP) present substantial threats to the ecological and hydrological systems. However, understanding the changes in HWEs on the TP is limited, primarily from analyses at individual stations or single elements (glaciers, lakes). Here, using refined data, we quantify the heatwave magnitude by aggregating multiple indicators into a comprehensive index and explore the influence of environmental factors on the heatwave magnitude over the TP. Our findings indicate that the heatwave magnitude has significantly increased since the 21st century, especially in autumn. From 1979–2000 to 2001–2022, the heatwave magnitude hotspots migrated toward the northwestern TP, whereas the regions with the most rapid increase shifted in the opposite direction. During the inter-seasonal, from spring to winter, the migration direction of the heatwave magnitude hotspots changed from the northwest in the first 22 years (1979–2000) to the southeast in the recent 22 years (2001–2022). We also find that downward shortwave radiation plays a significant role in the spatial stratified heterogeneity (SSH) of the heatwave magnitude, while the trend of temperature plays a dominant role in the SSH of the trend of heatwave magnitude. Moreover, elevation is correlated with the heatwave magnitude variability. The elevation-dependence of the heatwave magnitude has become more pronounced in the recent 22 years, with a high-heatwave magnitude migrating to higher elevations. Furthermore, the difference in land cover type can also affect the intensity of the heatwave magnitude to some extent. Our findings underscore the migration patterns of the heatwave magnitude evolution around the 21st century and provide a scientific basis for understanding the interaction between environmental factors and the heatwave magnitude in different periods.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":"28 1","pages":""},"PeriodicalIF":9.0,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142934915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Relating satellite NO2 tropospheric columns to near-surface concentrations: implications from ground-based MAX-DOAS NO2 vertical profile observations

IF 9 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2025-01-03 DOI: 10.1038/s41612-024-00891-z

Bowen Chang, Haoran Liu, Chengxin Zhang, Chengzhi Xing, Wei Tan, Cheng Liu

Given the significant environmental and health risks associated with near-surface nitrogen dioxide (NO₂), machine learning is frequently employed to estimate near-surface NO₂ concentrations (S_NO2) from satellite-derived tropospheric NO₂ column densities (C_NO2). However, data-driven methods often face challenges in explaining the complex relationships between these variables. In this study, the correlation between C_NO2 and S_NO2 is examined using vertical profile observations from China’s MAX-DOAS network. Cloud cover and air convection substantially weaken (R = −0.68) and strengthen (R = 0.71) the C_NO2-S_NO2 correlation, respectively. Meteorological factors dominate the correlation (R² = 0.58), which is 31% stronger in northern regions than in the southwest. Additionally, anthropogenic emissions impact S_NO2, while topographical features shape regional climate patterns. At the Chongqing site, the negative impacts of unfavorable meteorological conditions, high emissions, and basin topography lead to significant contrasts and delays in daily C_NO2 and S_NO2 variations. This study enhances understanding of the spatial and temporal dynamics and influencing mechanisms of C_NO2 and S_NO2, supporting improved air quality assessments and pollution exposure evaluations.

{"title":"Relating satellite NO2 tropospheric columns to near-surface concentrations: implications from ground-based MAX-DOAS NO2 vertical profile observations","authors":"Bowen Chang, Haoran Liu, Chengxin Zhang, Chengzhi Xing, Wei Tan, Cheng Liu","doi":"10.1038/s41612-024-00891-z","DOIUrl":"https://doi.org/10.1038/s41612-024-00891-z","url":null,"abstract":"Given the significant environmental and health risks associated with near-surface nitrogen dioxide (NO2), machine learning is frequently employed to estimate near-surface NO2 concentrations (SNO2) from satellite-derived tropospheric NO2 column densities (CNO2). However, data-driven methods often face challenges in explaining the complex relationships between these variables. In this study, the correlation between CNO2 and SNO2 is examined using vertical profile observations from China’s MAX-DOAS network. Cloud cover and air convection substantially weaken (R = −0.68) and strengthen (R = 0.71) the CNO2-SNO2 correlation, respectively. Meteorological factors dominate the correlation (R2 = 0.58), which is 31% stronger in northern regions than in the southwest. Additionally, anthropogenic emissions impact SNO2, while topographical features shape regional climate patterns. At the Chongqing site, the negative impacts of unfavorable meteorological conditions, high emissions, and basin topography lead to significant contrasts and delays in daily CNO2 and SNO2 variations. This study enhances understanding of the spatial and temporal dynamics and influencing mechanisms of CNO2 and SNO2, supporting improved air quality assessments and pollution exposure evaluations.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":"23 1","pages":""},"PeriodicalIF":9.0,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142924453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Contributions of climatic factors and vegetation cover to the temporal shift in Asian dust events

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-28 DOI: 10.1038/s41612-024-00887-9

Wencun Zhou, Huanjiong Wang, Quansheng Ge

Asia is one of the largest dust source regions in the world. However, the temporal variations and drivers of different types of dust events in this region remain unclear. Based on surface observation data, we explored spatiotemporal changes in three types of dust events and their driving factors in Asia by using machine learning methods. Results indicated that the frequency of moderate dust events (MDE) and severe dust events (SDE) decreased significantly from 2000 to 2022, which could be primarily attributed to a decrease in strong wind days (contribution >50%), and to a lesser extent to increases in soil moisture, precipitation, and leaf area index (LAI). When the daily maximum wind speed exceeds 13.0 m/s, the probability of MDE tends to decrease, while the probability of SDE tends to increase. These findings enhance our understanding of the variation in frequency and intensity of dust events in response to climate change.

引用次数: 0

Enhancing accuracy of air quality sensors with machine learning to augment large-scale monitoring networks

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-27 DOI: 10.1038/s41612-024-00833-9

Khaiwal Ravindra, Sahil Kumar, Abhishek Kumar, Suman Mor

Low-cost sensors have revolutionized air quality monitoring, however, precision is questioned compared to reference instruments. Hence, the performance of two widely used PM2.5 Sensors, Purple Air (PA) and ATMOS, were evaluated over a 10-month period in the North Western-Indo Gangetic Plains (NW-IGP). In-field collocation with Beta Attenuation Monitor found low R2 values; 0.40 for ATMOS and 0.43 for PA. To calibrate and improve the accuracy of sensors, five Machine Learning (ML) models and an empirical relative humidity correction methodology were used separately for both sensors. Out of these, the Decision Tree outperformed others, and R2 values improved to 0.996 for ATMOS and 0.999 for PA. Root mean square error reduced from 34.6 µg/m3 to 0.731 µg/m3 for ATMOS and from 77.7 µg/m3 to 0.61 µg/m3 for PA, while using DT as a calibrating model. The study reveals the best-performing ML model for correcting PM2.5 sensor data, enhancing the accuracy of air quality monitoring systems.

引用次数: 0

Sub-daily scale rainfall extremes in India and incongruity between hourly rain gauges data and CMIP6 models

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-27 DOI: 10.1038/s41612-024-00885-x

Kadiri Saikranthi, Basivi Radhakrishna, Madhavan Nair Rajeevan

Self-recording rain gauges hourly rainfall data from 1969 to 2010 have been utilized to identify rain events at a sub-daily scale. At the sub-daily scale, a significant decrease in the frequency of heavy rainfall events (HREs) is observed over central India and northeast India, while an increase is observed over the northern west coast of India. Frequency of short-duration HREs over central India and long duration HREs over northern west coast of India is increased in the recent decades than in earlier decades. Incongruity with the observations, CMIP6 historical and AMIP high temporal resolution models are not able to simulate the short-duration HREs and, in turn, the observed trends at a sub-daily scale over the India landmass. The inability of CMIP6 models to predict short-duration HREs suggests caution in predicting future projections of extreme precipitation at a sub-daily scale and highlights the need for further improvements in climate models.

引用次数: 0

Mechanism underlying the correlation between the warming-wetting of the Qinghai-Tibet Plateau and atmospheric energy changes in high-impact oceanic areas

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-26 DOI: 10.1038/s41612-024-00849-1

Na Dong, Xiangde Xu, Renhe Zhang, Chan Sun, Wenyue Cai, Runze Zhao

The powerful thermal driving force of the Qinghai-Tibet Plateau (QTP) exerts a significant influence on weather, climate, and environmental processes in Asia and across the globe. This paper investigates the causes of climate change on the QTP from the perspective of global atmospheric energy transport and water cycle. During summer, a “hollow energy pool” has been discovered in the troposphere, with its energy center located above the QTP, the “Asian water tower”. Our study indicates that the QTP serves as a critical “window” for the global transport of water vapor and energy. Since 1991, the total atmospheric energy (TAE) and precipitation in the warming-wetting region of the QTP (central and northern plateau) have exhibited interdecadal growth. Furthermore, the TAE of the plateau is closely linked to the TAE and water vapor of oceans at mid-low latitudes, and even in the southern hemisphere, the increased precipitation in the warming-wetting region of the plateau has been mainly regulated by the atmospheric energy and water vapor transport structures over the equatorial western Pacific, southwestern Pacific, and southern Indian Ocean, we further reveal the energy transport channel from the warming oceanic areas of the southern and northern hemispheres to the QTP. This study deepens the novel understanding of atmospheric energy accompanying water vapor transport in the southern and northern hemispheres, which is of significant importance for understanding the responses of energy and water cycle in the warming-wetting of the QTP and global climate change.

{"title":"Mechanism underlying the correlation between the warming-wetting of the Qinghai-Tibet Plateau and atmospheric energy changes in high-impact oceanic areas","authors":"Na Dong, Xiangde Xu, Renhe Zhang, Chan Sun, Wenyue Cai, Runze Zhao","doi":"10.1038/s41612-024-00849-1","DOIUrl":"10.1038/s41612-024-00849-1","url":null,"abstract":"The powerful thermal driving force of the Qinghai-Tibet Plateau (QTP) exerts a significant influence on weather, climate, and environmental processes in Asia and across the globe. This paper investigates the causes of climate change on the QTP from the perspective of global atmospheric energy transport and water cycle. During summer, a “hollow energy pool” has been discovered in the troposphere, with its energy center located above the QTP, the “Asian water tower”. Our study indicates that the QTP serves as a critical “window” for the global transport of water vapor and energy. Since 1991, the total atmospheric energy (TAE) and precipitation in the warming-wetting region of the QTP (central and northern plateau) have exhibited interdecadal growth. Furthermore, the TAE of the plateau is closely linked to the TAE and water vapor of oceans at mid-low latitudes, and even in the southern hemisphere, the increased precipitation in the warming-wetting region of the plateau has been mainly regulated by the atmospheric energy and water vapor transport structures over the equatorial western Pacific, southwestern Pacific, and southern Indian Ocean, we further reveal the energy transport channel from the warming oceanic areas of the southern and northern hemispheres to the QTP. This study deepens the novel understanding of atmospheric energy accompanying water vapor transport in the southern and northern hemispheres, which is of significant importance for understanding the responses of energy and water cycle in the warming-wetting of the QTP and global climate change.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":" ","pages":"1-11"},"PeriodicalIF":8.5,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41612-024-00849-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142886853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Novel perspectives on multiple-peak diurnal convection over a tropical mountainous island from idealized large-eddy simulations

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-26 DOI: 10.1038/s41612-024-00884-y

Yu-Hsiu Wang, Wei-Ting Chen, Chien-Ming Wu

Two robust peaks in the diurnal evolution of orographically-locked precipitation are simulated in large-eddy simulations with an idealized ocean-plain-mountain topography. The ensemble experiment design is guided by sounding statistics from summertime afternoon thunderstorms in Taiwan to obtain realistic variability of free-tropospheric moisture associated with the intensity of the summertime subtropical high. The convection in the first peak is directly modulated by convective available potential energy, while the convection in the second peak is associated with low-level moist static energy (MSE) transport by the island-scale (40-km) local circulation, producing more extreme rainfall. When the initial free troposphere is drier, the convection in the second peak is strengthened. Both the environmental adjustments by the first peak and local circulation development contribute to the sensitivity of the second peak to free-tropospheric moisture. This work highlights the critical roles of convection-environment interaction and upstream MSE supply in enhancing extreme diurnal precipitation over complex topography.

{"title":"Novel perspectives on multiple-peak diurnal convection over a tropical mountainous island from idealized large-eddy simulations","authors":"Yu-Hsiu Wang, Wei-Ting Chen, Chien-Ming Wu","doi":"10.1038/s41612-024-00884-y","DOIUrl":"10.1038/s41612-024-00884-y","url":null,"abstract":"Two robust peaks in the diurnal evolution of orographically-locked precipitation are simulated in large-eddy simulations with an idealized ocean-plain-mountain topography. The ensemble experiment design is guided by sounding statistics from summertime afternoon thunderstorms in Taiwan to obtain realistic variability of free-tropospheric moisture associated with the intensity of the summertime subtropical high. The convection in the first peak is directly modulated by convective available potential energy, while the convection in the second peak is associated with low-level moist static energy (MSE) transport by the island-scale (40-km) local circulation, producing more extreme rainfall. When the initial free troposphere is drier, the convection in the second peak is strengthened. Both the environmental adjustments by the first peak and local circulation development contribute to the sensitivity of the second peak to free-tropospheric moisture. This work highlights the critical roles of convection-environment interaction and upstream MSE supply in enhancing extreme diurnal precipitation over complex topography.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":" ","pages":"1-14"},"PeriodicalIF":8.5,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41612-024-00884-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142888659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unraveling the roles of jet streams on the unprecedented hot July in Western Europe in 2022

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-24 DOI: 10.1038/s41612-024-00880-2

Xinhui Li, Jiayu Zheng, Chunzai Wang, Xiayan Lin, Zhixiong Yao

Western Europe experienced an unprecedentedly hot July in 2022, which significantly impacted ecosystems and society. Our observational and numerical modeling study reveals that this event was influenced by anomalous North Atlantic and Eurasian jet streams. The northeastward shift of the North Atlantic jet stream, driven by sea surface temperature gradients, and the curving of the Eurasian jet stream, affected by rainfall anomalies in Pakistan, enhanced atmospheric subsidence over western Europe. This research highlights the crucial role of the synergistic behavior of the North Atlantic and Eurasian jet streams in driving extreme heat over Western Europe. Furthermore, CMIP6 climate model projections suggest that under the SSP585 scenario, similar jet stream configurations could lead to even more intense extreme temperatures (~7.02 ± 0.61 °C) compared to the current climatological mean.

引用次数: 0

Seasonal phase change of the North Atlantic Tripole Sea surface temperature predicted by air-sea coupling

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-24 DOI: 10.1038/s41612-024-00882-0

Haipeng Yu, Shanling Cheng, Jianping Huang, Zeyong Hu, Haojie Wu, Xin Wang

The North Atlantic Tripole sea surface temperature anomaly (NAT SSTA) is critical for predicting climate in Eurasia. Predictions for summer climate anomalies currently assume the NAT SSTA phase persists from boreal winter through summer. When NAT phase switches, predictions become unreliable. However, the NAT phase sustained/reversal mechanism from boreal winter to spring remains unclear. This study demonstrates that the evolution of the NAT phase could be driven by the North Atlantic Oscillation (NAO). When NAO phase persists (switches) during preceding boreal winter, the NAO-driven wind anomalies favor maintenance (transition) of NAT phase by causing sea surface heat flux anomalies. Meanwhile, NAT SSTA causes eddy-mean flow interaction by increasing atmospheric baroclinity, thereby generating positive feedback on the former NAO phase. The NAO phase change is leading 1–3 months for the NAT phase. These findings deepen our understanding of the interaction between NAO and NAT and provide implications for seasonal prediction in Eurasia.

{"title":"Seasonal phase change of the North Atlantic Tripole Sea surface temperature predicted by air-sea coupling","authors":"Haipeng Yu, Shanling Cheng, Jianping Huang, Zeyong Hu, Haojie Wu, Xin Wang","doi":"10.1038/s41612-024-00882-0","DOIUrl":"10.1038/s41612-024-00882-0","url":null,"abstract":"The North Atlantic Tripole sea surface temperature anomaly (NAT SSTA) is critical for predicting climate in Eurasia. Predictions for summer climate anomalies currently assume the NAT SSTA phase persists from boreal winter through summer. When NAT phase switches, predictions become unreliable. However, the NAT phase sustained/reversal mechanism from boreal winter to spring remains unclear. This study demonstrates that the evolution of the NAT phase could be driven by the North Atlantic Oscillation (NAO). When NAO phase persists (switches) during preceding boreal winter, the NAO-driven wind anomalies favor maintenance (transition) of NAT phase by causing sea surface heat flux anomalies. Meanwhile, NAT SSTA causes eddy-mean flow interaction by increasing atmospheric baroclinity, thereby generating positive feedback on the former NAO phase. The NAO phase change is leading 1–3 months for the NAT phase. These findings deepen our understanding of the interaction between NAO and NAT and provide implications for seasonal prediction in Eurasia.","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":" ","pages":"1-13"},"PeriodicalIF":8.5,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41612-024-00882-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing symbolic regression for earth science with a focus on evapotranspiration modeling

IF 8.5 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

npj Climate and Atmospheric Science

Pub Date : 2024-12-24 DOI: 10.1038/s41612-024-00861-5

Qingliang Li, Cheng Zhang, Zhongwang Wei, Xiaochun Jin, Wei Shangguan, Hua Yuan, Jinlong Zhu, Lu Li, Pingping Liu, Xiao Chen, Yuguang Yan, Yongjiu Dai

Artificial Intelligence (AI) assumes a pivotal role in Earth science, leveraging deep learning’s predictive capabilities. Despite its prevalence, the impact of AI on scientific discovery remains uncertain. In Earth sciences, the emphasis extends beyond mere accuracy, striving for groundbreaking discoveries with distinct physical properties essential for driving advancements through thorough analysis. Here, we introduce a novel knowledge-guided deep symbolic regression model (KG-DSR) incorporating prior knowledge of physical process interactions into the network. Using KG-DSR, we successfully derived the Penman-Monteith (PM) equation and generated a novel surface resistance parameterization. This new parameterization, grounded in fundamental cognitive principles, surpasses the conventional theory currently accepted in surface resistance parameterization. Importantly, the explicit physical processes generated by AI can generalize to future climate scenarios beyond the training data. Our results emphasize the role of AI in unraveling process intricacies and ushering in a new paradigm in tasks related to “AI for Land Surface Modeling.”

{"title":"Advancing symbolic regression for earth science with a focus on evapotranspiration modeling","authors":"Qingliang Li, Cheng Zhang, Zhongwang Wei, Xiaochun Jin, Wei Shangguan, Hua Yuan, Jinlong Zhu, Lu Li, Pingping Liu, Xiao Chen, Yuguang Yan, Yongjiu Dai","doi":"10.1038/s41612-024-00861-5","DOIUrl":"10.1038/s41612-024-00861-5","url":null,"abstract":"Artificial Intelligence (AI) assumes a pivotal role in Earth science, leveraging deep learning’s predictive capabilities. Despite its prevalence, the impact of AI on scientific discovery remains uncertain. In Earth sciences, the emphasis extends beyond mere accuracy, striving for groundbreaking discoveries with distinct physical properties essential for driving advancements through thorough analysis. Here, we introduce a novel knowledge-guided deep symbolic regression model (KG-DSR) incorporating prior knowledge of physical process interactions into the network. Using KG-DSR, we successfully derived the Penman-Monteith (PM) equation and generated a novel surface resistance parameterization. This new parameterization, grounded in fundamental cognitive principles, surpasses the conventional theory currently accepted in surface resistance parameterization. Importantly, the explicit physical processes generated by AI can generalize to future climate scenarios beyond the training data. Our results emphasize the role of AI in unraveling process intricacies and ushering in a new paradigm in tasks related to “AI for Land Surface Modeling.”","PeriodicalId":19438,"journal":{"name":"npj Climate and Atmospheric Science","volume":" ","pages":"1-16"},"PeriodicalIF":8.5,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s41612-024-00861-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

npj Climate and Atmospheric Science

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀