Shirui Luo

Dr. Shirui Luo


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2020
Verified
Book Chapter
Closed access
PDF file
SLShirui Luo
Shirui Luo
MVMadhu Vellakal
Madhu Vellakal
SKSeid Koric
Seid Koric
VKVolodymyr Kindratenko
Volodymyr Kindratenko
JCJiahuan Cui
Jiahuan Cui

31 August 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Open access
SLShirui Luo
Shirui Luo
ASAaron Saxton
Aaron Saxton
ABAlbert Bode
Albert Bode
PMPriyam Mazumdar
Priyam Mazumdar
VKVolodymyr Kindratenko
Volodymyr Kindratenko
Critical minerals play a significant role in various areas such as national security, economic growth, renewable energy development, and infrastructure. The assessment of critical minerals requires examining historical scanned maps. The traditional processes of analyzing these scanned maps are labor-intensive, time-consuming, and prone to errors. In this study, we introduce a deep learning technique to help assess critical minerals by automatically extracting digital features from scanned maps. The polygon features extraction is essential for evaluating the concentration and abundance of critical minerals. The extracted polygon features can be used to update existing geospatial databases, conduct further analysis, and support decision-making processes. The proposed U-Net model takes a 6-channel array as input, where legend feature is concatenated with the map image and serves as a prompt, and the model can generate image segmentation based on arbitrary prompts at test time. Our study shows that the modified U-Net model can effectively extract the mining-related polygon regions based on features listed in legends from historic topographic maps. The model achieves a median F1-score of 0.67. This study has the potential to significantly reduce the time and effort involved in manually digitizing geospatial data from historical topographic maps, thus streamlining the overall assessment process.

11 November 2023
Verified
Conference Paper
Open access
YFYuhang Fu
Yuhang Fu
WSWeiqi Shen
Weiqi Shen
JCJIAHUAN CUI
JIAHUAN CUI
Yao ZhengYao Zheng
Yao Zheng
GYGuangwen Yang
Guangwen Yang
WZWeimin Zheng
Weimin Zheng
A state-of-the-art large eddy simulation code has been developed to solve compressible flows in turbomachinery. The code has been engineered with a high degree of scalability, enabling it to effectively leverage the many-core architecture of the new Sunway system. A consistent performance of 115.8 DP-PFLOPs has been achieved on a high-pressure turbine cascade consisting of over 1.69 billion mesh elements and 865 billion Degree of Freedoms (DOFs). By leveraging a high-order unstructured solver and its portability to large heterogeneous parallel systems, we have progressed towards solving the grand challenge problem outlined by NASA [1], which involves a time-dependent simulation of a complete engine, incorporating all the aerodynamic and heat transfer components.

13 November 2024 in Geosciences
Verified
Journal Article
Open access
PDF file
ASAaron Saxton
Aaron Saxton
JDJiahua Dong
Jiahua Dong
ABAlbert Bode
Albert Bode
NJNATTAPON JAROENCHAI
NATTAPON JAROENCHAI
RKRob Kooper
Rob Kooper
SLShirui Luo
Shirui Luo
This study presents a novel AI method for extracting polygon and point features from historical geologic maps, representing a pivotal step for assessing the mineral resources needed for energy transition. Our innovative method involves using map units in the legends as prompts for one-shot segmentation and detection in geological feature extraction. The model, integrated with a human-in-the-loop system, enables geologists to refine results efficiently, combining the power of AI with expert oversight. Tested on geologic maps annotated by USGS and DARPA for the AI4CMA DARPA Challenge, our approach achieved a median F1 score of 0.91 for polygon feature segmentation and 0.73 for point feature detection when such features had abundant annotated data, outperforming current benchmarks. By efficiently and accurately digitizing historical geologic map, our method promises to provide crucial insights for responsible policymaking and effective resource management in the global energy transition.

14 August 2020 in Computing in Science & Engineering
Verified
Journal Article
Closed access
SLShirui Luo
Shirui Luo
VKVolodymyr Kindratenko
Volodymyr Kindratenko
Deep learning (DL) has emerged as a powerful tool to solve a variety of complex problems that have been difficult to solve with traditional methods. However, domain experts attempting to apply DL methodology have to learn to code in order to use it. Numerous frameworks have been developed, such as TensorFlow, that simplify the task of building and training complex DL models, yet their efficient use requires a good working knowledge of Python language. Consequently, a variety of tools have been developed that provide easier to use DL models, ranging from the Keras API built on top of TensorFlow that still requires coding, to tools such as H2O that provide a point-and-click web-based interface to configure and train pre-built models. Among this new breed of tools, IBM Visual Insights (formerly IBM PowerAI Vision) (IBM Visual Insights Version 1.2.0, n.d.) has taken this concept further by providing a web-based graphical user interface (GUI) for configuring and training a variety of models, as well as tools and APIs for deploying these models on a variety of platform. The tool empowers domain experts without any knowledge of coding or underlying hardware to take advantage of complex DL models trained on large datasets. We use classification of COVID-19 chest X-ray images as an example application to demonstrate the IBM Visual Insights streamlined processes for image labeling, model training, and model deployment.

23 May 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ASAiman Soliman
Aiman Soliman
YCYifan Chen
Yifan Chen
SLShirui Luo
Shirui Luo
RMRauf Makharov
Rauf Makharov
VKVolodymyr Kindratenko
Volodymyr Kindratenko
The lack of quality label data is considered one of the main bottlenecks for training machine and deep learning models. Weakly supervised learning using incomplete, coarse, or inaccurate data is an alternative strategy to overcome the scarcity of training data. We trained a U-Net model for segmenting Buildings’ footprints from a high-resolution digital elevation model, using existing label data from the open-access Microsoft building footprints data set. Comparison using an independent, manually labeled benchmark indicated the success of the weak supervision learning as the quality of the model prediction (IoU: 0.876) surpassed that of the original Microsoft data quality (IoU: 0.672) by approximately 20 percent. Moreover, adding extra channels such as elevation derivatives, slope, aspect, and profile curvatures did not enhance the weak learning process as the model learned directly from the original elevation data. Our results demonstrate the value of using existing data for training deep learning models even if they are noisy and incomplete.