Integrated gravitational, electrical-magnetic surveys and data processing carried out in the Sanshandao-Jiaojia area, Eastern Shandong Province, northeast China, aim to illuminate the geological characteristics of thi...Integrated gravitational, electrical-magnetic surveys and data processing carried out in the Sanshandao-Jiaojia area, Eastern Shandong Province, northeast China, aim to illuminate the geological characteristics of this shallow-covered area and delineate deep-seated gold prospecting targets. In this region, altogether 12 faults exert critical control on distribution of three types of Early Precambrian metamorphic rock series, i.e. those in the metamorphic rock area, in the granitic rock area underlying the metamorphic rock, and in the remnant metamorphic rock area in granites, respectively. Additionally, the faults have major effects on distribution of four Mesozoic Linglong rock bodies of granite, i.e. the Cangshang, Liangguo, Zhuqiao-Miaojia and Jincheng granites. The Sanshandao and Jiaojia Faults are two well-known regional ore-controlling faults; they have opposite dip direction, and intersect at a depth of 4500 m. Fracture alteration zones have striking geophysical differences relative to the surrounding county rocks. The two faults extend down along dip direction in a gentle wave form, and appear at some steps with different dips. These steps comprise favorable gold prospecting areas, consistent with a step metallogenic model. Six deep-seated gold-prospecting targets are delineated, i.e. Jincheng-Qianchenjia, Xiaoxizhuang-Zhaoxian, Xiyou-Wujiazhuangzi, Xiangyangling-Xinlicun, Panjiawuzi and Miaojia-Pinglidian.展开更多
Characterized by self-monitoring and agile adaptation to fast changing dynamics in complex production environments,smart manufacturing as envisioned under Industry 4.0 aims to improve the throughput and reliability of...Characterized by self-monitoring and agile adaptation to fast changing dynamics in complex production environments,smart manufacturing as envisioned under Industry 4.0 aims to improve the throughput and reliability of production beyond the state-of-the-art.While the widespread application of deep learning(DL)has opened up new opportunities to accomplish the goal,data quality and model interpretability have continued to present a roadblock for the widespread acceptance of DL for real-world applications.This has motivated research on two fronts:data curation,which aims to provide quality data as input for meaningful DL-based analysis,and model interpretation,which intends to reveal the physical reasoning underlying DL model outputs and promote trust from the users.This paper summarizes several key techniques in data curation where breakthroughs in data denoising,outlier detection,imputation,balancing,and semantic annotation have demonstrated the effectiveness in information extraction from noisy,incomplete,insufficient,and/or unannotated data.Also highlighted are model interpretation methods that address the“black-box”nature of DL towards model transparency.展开更多
采用深度学习智能提取建设用地,对定量评价、监测和预测长江流域水土流失具有重要作用。本文基于开源数据,采用半自动标注方式标注建设用地,构建了面向长江流域水土流失监测的建设用地遥感数据集。该数据集在多个深度学习语义分割模型(...采用深度学习智能提取建设用地,对定量评价、监测和预测长江流域水土流失具有重要作用。本文基于开源数据,采用半自动标注方式标注建设用地,构建了面向长江流域水土流失监测的建设用地遥感数据集。该数据集在多个深度学习语义分割模型(FPN、PSPNet、DeepLabV3+、UN⁃et++、Swin-Transformer)测试中的总体精度(overall accu⁃racy,OA)均优于93.00%,均交并比(mean intersection over union,MIoU)优于70%,具有较高有效性,可推动遥感智能解译在水土流失监测中的应用。展开更多
Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data predic...Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.展开更多
基金the Geological Science and technology foundation of Shandong Provincial Bureau of Geology and Mineral Resources (Grant No. 20080037)
文摘Integrated gravitational, electrical-magnetic surveys and data processing carried out in the Sanshandao-Jiaojia area, Eastern Shandong Province, northeast China, aim to illuminate the geological characteristics of this shallow-covered area and delineate deep-seated gold prospecting targets. In this region, altogether 12 faults exert critical control on distribution of three types of Early Precambrian metamorphic rock series, i.e. those in the metamorphic rock area, in the granitic rock area underlying the metamorphic rock, and in the remnant metamorphic rock area in granites, respectively. Additionally, the faults have major effects on distribution of four Mesozoic Linglong rock bodies of granite, i.e. the Cangshang, Liangguo, Zhuqiao-Miaojia and Jincheng granites. The Sanshandao and Jiaojia Faults are two well-known regional ore-controlling faults; they have opposite dip direction, and intersect at a depth of 4500 m. Fracture alteration zones have striking geophysical differences relative to the surrounding county rocks. The two faults extend down along dip direction in a gentle wave form, and appear at some steps with different dips. These steps comprise favorable gold prospecting areas, consistent with a step metallogenic model. Six deep-seated gold-prospecting targets are delineated, i.e. Jincheng-Qianchenjia, Xiaoxizhuang-Zhaoxian, Xiyou-Wujiazhuangzi, Xiangyangling-Xinlicun, Panjiawuzi and Miaojia-Pinglidian.
文摘Characterized by self-monitoring and agile adaptation to fast changing dynamics in complex production environments,smart manufacturing as envisioned under Industry 4.0 aims to improve the throughput and reliability of production beyond the state-of-the-art.While the widespread application of deep learning(DL)has opened up new opportunities to accomplish the goal,data quality and model interpretability have continued to present a roadblock for the widespread acceptance of DL for real-world applications.This has motivated research on two fronts:data curation,which aims to provide quality data as input for meaningful DL-based analysis,and model interpretation,which intends to reveal the physical reasoning underlying DL model outputs and promote trust from the users.This paper summarizes several key techniques in data curation where breakthroughs in data denoising,outlier detection,imputation,balancing,and semantic annotation have demonstrated the effectiveness in information extraction from noisy,incomplete,insufficient,and/or unannotated data.Also highlighted are model interpretation methods that address the“black-box”nature of DL towards model transparency.
文摘采用深度学习智能提取建设用地,对定量评价、监测和预测长江流域水土流失具有重要作用。本文基于开源数据,采用半自动标注方式标注建设用地,构建了面向长江流域水土流失监测的建设用地遥感数据集。该数据集在多个深度学习语义分割模型(FPN、PSPNet、DeepLabV3+、UN⁃et++、Swin-Transformer)测试中的总体精度(overall accu⁃racy,OA)均优于93.00%,均交并比(mean intersection over union,MIoU)优于70%,具有较高有效性,可推动遥感智能解译在水土流失监测中的应用。
基金the National Natural Science Foundation of China(22108307)the Natural Science Foundation of Shandong Province(ZR2020KB006)the Outstanding Youth Fund of Shandong Provincial Natural Science Foundation(ZR2020YQ17).
文摘Acquiring accurate molecular-level information about petroleum is crucial for refining and chemical enterprises to implement the“selection of the optimal processing route”strategy.With the development of data prediction systems represented by machine learning,it has become possible for real-time prediction systems of petroleum fraction molecular information to replace analyses such as gas chromatography and mass spectrometry.However,the biggest difficulty lies in acquiring the data required for training the neural network.To address these issues,this work proposes an innovative method that utilizes the Aspen HYSYS and full two-dimensional gas chromatography-time-of-flight mass spectrometry to establish a comprehensive training database.Subsequently,a deep neural network prediction model is developed for heavy distillate oil to predict its composition in terms of molecular structure.After training,the model accurately predicts the molecular composition of catalytically cracked raw oil in a refinery.The validation and test sets exhibit R2 values of 0.99769 and 0.99807,respectively,and the average relative error of molecular composition prediction for raw materials of the catalytic cracking unit is less than 7%.Finally,the SHAP(SHapley Additive ExPlanation)interpretation method is used to disclose the relationship among different variables by performing global and local weight comparisons and correlation analyses.
