As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate unders...As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.展开更多
Within the context of the Belt and Road Initiative(BRI)and the China-Myanmar Economic Corridor(CMEC),the Dulong-Ir-rawaddy(Ayeyarwady)River,an international river among China,India and Myanmar,plays a significant role...Within the context of the Belt and Road Initiative(BRI)and the China-Myanmar Economic Corridor(CMEC),the Dulong-Ir-rawaddy(Ayeyarwady)River,an international river among China,India and Myanmar,plays a significant role as both a valuable hydro-power resource and an essential ecological passageway.However,the water resources and security exhibit a high degree of vulnerabil-ity to climate change impacts.This research evaluates climate impacts on the hydrology of the Dulong-Irrawaddy River Basin(DIRB)by using a physical-based hydrologic model.We crafted future climate scenarios using the three latest global climate models(GCMs)from Coupled Model Intercomparison Project 6(CMIP6)under two shared socioeconomic pathways(SSP2-4.5 and SSP5-8.5)for the near(2025-2049),mid(2050-2074),and far future(2075-2099).The regional model using MIKE SHE based on historical hydrologic processes was developed to further project future streamflow,demonstrating reliable performance in streamflow simulations with a val-idation Nash-Sutcliffe Efficiency(NSE)of 0.72.Results showed that climate change projections showed increases in the annual precip-itation and potential evapotranspiration(PET),with precipitation increasing by 11.3%and 26.1%,and PET increasing by 3.2%and 4.9%,respectively,by the end of the century under SSP2-4.5 and SSP5-8.5.These changes are projected to result in increased annual streamflow at all stations,notably at the basin’s outlet(Pyay station)compared to the baseline period(with an increase of 16.1%and 37.0%at the end of the 21st century under SSP2-4.5 and SSP5-8.5,respectively).Seasonal analysis for Pyay station forecasts an in-crease in dry-season streamflow by 31.3%-48.9%and 22.5%-76.3%under SSP2-4.5 and SSP5-8.5,respectively,and an increase in wet-season streamflow by 5.8%-12.6%and 2.8%-33.3%,respectively.Moreover,the magnitude and frequency of flood events are pre-dicted to escalate,potentially impacting hydropower production and food security significantly.This research outlines the hydrological response to future climate change during the 21st century and offers a scientific basis for the water resource management strategies by decision-makers.展开更多
A set of organic-rich shales of the upper Permian Longtan Formation,which is widely developed in the northeastern part of the Sichuan Basin,is a key formation for the next step of exploration and development.At presen...A set of organic-rich shales of the upper Permian Longtan Formation,which is widely developed in the northeastern part of the Sichuan Basin,is a key formation for the next step of exploration and development.At present,most studies on this set of formations have focused on the reservoir characteristics and reservoir formation mechanism of the shales,and basic studies on the palaeoenvironment and organic matter(OM)enrichment mechanism have not been fully carried out.In this paper,we recovered the sedimentary palaeoenvironment by mineralogical,elemental geochemical and organic geochemical analyses,and explored the enrichment mechanism of OM under the constraints of palaeoenvironmental evolution.The shales can be divided into two stages of sedimentary evolution:compared with the shales of the Lower Longtan Formation,the shales of the Upper Longtan Formation are relatively rich in quartz,poor in clay and carbonate minerals,and the OM type changes from typeⅢto typeⅡ_(2).The depositional environment has undergone a change from sea level rise,from warm and wet climate to dry and cold climate,and from oxygen-poor condition restricted to open reduction environment;the land source input has decreased,the siliceous mineral content has increased,the biological productivity has improved,and the deposition rate has changed from high to low.A depositional model was established for the shales of the Longtan Formation,reflecting the differential reservoir formation pattern of organic matter.For the Lower Longtan Formation shales,the most important factors controlling OM content are terrestrial source input and deposition rate,followed by paleoclimate and paleooxygen conditions.For the Upper Longtan Formation shales,the most important controlling factor is paleo-productivity,followed by sedimentation rate.The depositional model constructed for the Upper and Lower Longtan Formation shales can reproduce the enrichment of organic matter and provide a basis for later exploration and development.展开更多
基金financially supported by the Natural Science Foundation of China(Grant No.42301492)the National Key R&D Program of China(Grant Nos.2022YFF0711600,2022YFF0801201,2022YFF0801200)+3 种基金the Major Special Project of Xinjiang(Grant No.2022A03009-3)the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources(Grant No.KF-2022-07014)the Opening Fund of the Key Laboratory of the Geological Survey and Evaluation of the Ministry of Education(Grant No.GLAB 2023ZR01)the Fundamental Research Funds for the Central Universities。
文摘As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.
基金Under the auspices of the Yunnan Scientist Workstation on International River Research of Daming He(No.KXJGZS-2019-005)National Natural Science Foundation of China(No.42201040)+1 种基金National Key Research and Development Project of China(No.2016YFA0601601)China Postdoctoral Science Foundation(No.2023M733006)。
文摘Within the context of the Belt and Road Initiative(BRI)and the China-Myanmar Economic Corridor(CMEC),the Dulong-Ir-rawaddy(Ayeyarwady)River,an international river among China,India and Myanmar,plays a significant role as both a valuable hydro-power resource and an essential ecological passageway.However,the water resources and security exhibit a high degree of vulnerabil-ity to climate change impacts.This research evaluates climate impacts on the hydrology of the Dulong-Irrawaddy River Basin(DIRB)by using a physical-based hydrologic model.We crafted future climate scenarios using the three latest global climate models(GCMs)from Coupled Model Intercomparison Project 6(CMIP6)under two shared socioeconomic pathways(SSP2-4.5 and SSP5-8.5)for the near(2025-2049),mid(2050-2074),and far future(2075-2099).The regional model using MIKE SHE based on historical hydrologic processes was developed to further project future streamflow,demonstrating reliable performance in streamflow simulations with a val-idation Nash-Sutcliffe Efficiency(NSE)of 0.72.Results showed that climate change projections showed increases in the annual precip-itation and potential evapotranspiration(PET),with precipitation increasing by 11.3%and 26.1%,and PET increasing by 3.2%and 4.9%,respectively,by the end of the century under SSP2-4.5 and SSP5-8.5.These changes are projected to result in increased annual streamflow at all stations,notably at the basin’s outlet(Pyay station)compared to the baseline period(with an increase of 16.1%and 37.0%at the end of the 21st century under SSP2-4.5 and SSP5-8.5,respectively).Seasonal analysis for Pyay station forecasts an in-crease in dry-season streamflow by 31.3%-48.9%and 22.5%-76.3%under SSP2-4.5 and SSP5-8.5,respectively,and an increase in wet-season streamflow by 5.8%-12.6%and 2.8%-33.3%,respectively.Moreover,the magnitude and frequency of flood events are pre-dicted to escalate,potentially impacting hydropower production and food security significantly.This research outlines the hydrological response to future climate change during the 21st century and offers a scientific basis for the water resource management strategies by decision-makers.
基金the General Fund of the National Natural Science Foundation of China(Grant No.42272184)National Natural Science Foundation of China(Grant Nos.42230311 and 91755215)for their support of this paper。
文摘A set of organic-rich shales of the upper Permian Longtan Formation,which is widely developed in the northeastern part of the Sichuan Basin,is a key formation for the next step of exploration and development.At present,most studies on this set of formations have focused on the reservoir characteristics and reservoir formation mechanism of the shales,and basic studies on the palaeoenvironment and organic matter(OM)enrichment mechanism have not been fully carried out.In this paper,we recovered the sedimentary palaeoenvironment by mineralogical,elemental geochemical and organic geochemical analyses,and explored the enrichment mechanism of OM under the constraints of palaeoenvironmental evolution.The shales can be divided into two stages of sedimentary evolution:compared with the shales of the Lower Longtan Formation,the shales of the Upper Longtan Formation are relatively rich in quartz,poor in clay and carbonate minerals,and the OM type changes from typeⅢto typeⅡ_(2).The depositional environment has undergone a change from sea level rise,from warm and wet climate to dry and cold climate,and from oxygen-poor condition restricted to open reduction environment;the land source input has decreased,the siliceous mineral content has increased,the biological productivity has improved,and the deposition rate has changed from high to low.A depositional model was established for the shales of the Longtan Formation,reflecting the differential reservoir formation pattern of organic matter.For the Lower Longtan Formation shales,the most important factors controlling OM content are terrestrial source input and deposition rate,followed by paleoclimate and paleooxygen conditions.For the Upper Longtan Formation shales,the most important controlling factor is paleo-productivity,followed by sedimentation rate.The depositional model constructed for the Upper and Lower Longtan Formation shales can reproduce the enrichment of organic matter and provide a basis for later exploration and development.
