Farshad Sadeghpour | Data prediction | Best Researcher Award

Posted on by sciencefather

Dr. Farshad Sadeghpour | Data prediction | Best Researcher Award

Farshad Sadeghpour (b. 1996) šŸ‡®šŸ‡· is a Petroleum Engineer and Data Scientist šŸ’»šŸ›¢ļø with expertise in reservoir engineering, petrophysics, and AI applications in the energy sector. Based in Tehran, Iran šŸ“, he holds a Masterā€™s and Bachelorā€™s in Petroleum Exploration. With extensive experience in EOR, SCAL/RCAL analysis, and machine learning, Farshad has contributed to both academic and industrial R&D at RIPI, NISOC, and PVP. He has published multiple research articles šŸ“š, won international awards šŸ†, and participated in key petroleum projects. He served in the military šŸŖ– and actively collaborates with academia and industry on AI-driven energy solutions.

Profile

Education šŸŽ“

šŸ§‘ā€šŸŽ“ Master’s in Petroleum Engineering (Petroleum Exploration), Petroleum University of Technology, Abadan šŸ‡®šŸ‡· (2019ā€“2022) | GPA: 18.82/20
šŸŽ“ Bachelorā€™s in Petroleum Engineering, Islamic Azad University (Science & Research Branch), Tehran šŸ‡®šŸ‡· (2015ā€“2019) | GPA: 19.14/20
šŸ“š Courses covered include reservoir engineering, geomechanics, well-logging, and advanced data analytics.
šŸ› ļø Projects include COā‚‚ storage modeling, permeability prediction via AI, and LWD-based mud loss forecasting.
šŸ“Š Developed key industry collaborations with NISOC, RIPI, and OEID through thesis, internships, and military service projects.
šŸ’” Honed computational and simulation skills using MATLAB, Python, COMSOL, Petrel, and ECLIPSE.
šŸ›ļø Academic mentors: Dr. Seyed Reza Shadizadeh, Dr. Bijan Biranvand, Dr. Majid Akbari.

Experience šŸ‘Øā€šŸ«


šŸ”¬ Computer Aided Process Engineering (CAPE) ā€“ Petroleum Reservoir Engineer (Nov 2024ā€“Present)
šŸ›¢ļø Petro Vision Pasargad ā€“ Reservoir Engineer & Lab Operator (Sep 2023ā€“May 2024)
šŸ§  Research Institute of Petroleum Industry (RIPI) ā€“ Petroleum Engineer, Data Scientist (Mar 2023ā€“Apr 2024)
šŸ­ National Iranian South Oil Company (NISOC) ā€“ Petroleum Engineer, Petrophysicist (Mar 2021ā€“Nov 2024)
šŸ§Ŗ Internships: NIOC – Exploration Management, Oil & Energy Industries Development (OEID)
šŸ“Š Key contributions include EOR analysis, SCAL/RCAL lab testing, permeability modeling, machine learning pipelines, and field data analysis.
šŸ§¾ Delivered reports, simulations, and AI models supporting production optimization and reservoir characterization.

Awards & Recognitions šŸ…

šŸ„‰ 3rd Prize Winner ā€“ EAGE Laurie Dake Challenge 2022 (Madrid, Spain) šŸŒ
šŸŽ–ļø Recognized for thesis excellence in AI-driven mud loss prediction with NISOC collaboration
šŸ“Œ Acknowledged during military service project with RIPI for developing ANN-based well log models
šŸ… Published in high-impact journals such as Energy, Geoenergy Science and Engineering, and JRMGE
āœļø Co-author of multiple peer-reviewed papers and under-review articles across petroleum engineering disciplines
šŸ”¬ Worked alongside top researchers including Dr. Ostadhassan, Dr. Gao, and Dr. Hemmati-Sarapardeh
šŸ› ļø Actively participated in multidisciplinary teams combining AI, geomechanics, and petrophysics
šŸ“¢ Regular presenter and contributor at petroleum conferences and AI-in-energy seminars.

Research Interests šŸ”¬

šŸ“Œ AI & ML applications in petroleum engineering šŸ§ šŸ›¢ļø ā€“ including ANN, genetic algorithms, and deep learning
šŸ“Š Mud loss zone prediction, formation permeability modeling, COā‚‚ storage feasibility using ML
šŸ§Ŗ Experimental rock mechanics: nanoindentation, geomechanical upscaling, SCAL/RCAL testing
šŸ“ˆ Petrophysical property estimation in carbonate and unconventional reservoirs
šŸŒ Reservoir simulation, LWD analysis, and smart data integration using Python, Petrel, COMSOL
šŸ“– Notable studies include: elastic modulus upscaling, kerogen behavior under pyrolysis, RQI/FZI modeling
šŸ”¬ Interdisciplinary projects bridging data science with geoscience and reservoir engineering
šŸ¤ Collaboration with academic and industry leaders to develop practical, AI-driven solutions for energy challenges.

PublicationsĀ 

  • Elastic Properties of Anisotropic Rocks Using an Stepwise Loading Framework in a True Triaxial Testing Apparatus

    Geoenergy Science and Engineering
    2025-04 |Ā Journal article
    DOI:Ā 10.1016/j.geoen.2025.213883
    CONTRIBUTORS:Ā Farshad Sadeghpour;Ā Hem Bahadur Motra;Ā Chinmay Sethi;Ā Sandra Wind;Ā Bodhisatwa Hazra;Ā Ghasem Aghli;Ā Mehdi Ostadhassan

  • Storage Efficiency Prediction for Feasibility Assessment of Underground CO2 Storage: Novel Machine Learning Approaches

    Energy
    2025-04 |Ā Journal article
    DOI:Ā 10.1016/j.energy.2025.136040
    CONTRIBUTORS:Ā Farshad Sadeghpour

  • A new petrophysical-mathematical approach to estimate RQI and FZI parameters in carbonate reservoirs

    Journal of Petroleum Exploration and Production Technology
    2025-03 |Ā Journal article
    DOI:Ā 10.1007/s13202-025-01952-6
    CONTRIBUTORS:Ā Farshad Sadeghpour;Ā Kamran Jahangiri;Ā Javad Honarmand

  • Effect of stress on fracture development in the Asmari reservoir in the Zagros Thrust Belt

    Journal of Rock Mechanics and Geotechnical Engineering
    2024-11 |Ā Journal article
    DOI:Ā 10.1016/j.jrmge.2023.12.027
    CONTRIBUTORS:Ā Ghasem Aghli;Ā Babak Aminshahidy;Ā Hem Bahadur Motra;Ā Ardavan Darkhal;Ā Farshad Sadeghpour;Ā Mehdi Ostadhassan

  • Comparison of geomechanical upscaling methods for prediction of elastic modulus of heterogeneous media

    Geoenergy Science and Engineering
    2024-08 |Ā Journal article
    DOI:Ā 10.1016/j.geoen.2024.212915
    CONTRIBUTORS:Ā Farshad Sadeghpour;Ā Ardavan Darkhal;Ā Yifei Gao;Ā Hem B. Motra;Ā Ghasem Aghli;Ā Mehdi Ostadhassan

Yuanming Zhang | Intelligent data processing and analysis | Best Researcher Award

Posted on by sciencefather

Dr. Yuanming Zhang | Intelligent data processing and analysis | Best Researcher Award

Yuanming Zhang is an Associate Professor at the College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China. He earned his Ph.D. in Information Science from Utsunomiya University, Japan, in 2010. His research focuses on data processing, graph neural networks, knowledge graphs, prognostics, health management, and condition monitoring. With expertise in deep learning and artificial intelligence, he has contributed significantly to neural network advancements. His work integrates cutting-edge technologies for intelligent data analysis and predictive maintenance. šŸ“ŠšŸ§ šŸ”

Profile

Education šŸŽ“

Yuanming Zhang obtained his Ph.D. in Information Science from Utsunomiya University, Japan, in 2010. His academic journey emphasized computational intelligence, machine learning, and advanced data analytics. He developed expertise in deep learning models, including convolutional and graph neural networks. His education laid a strong foundation for interdisciplinary research, integrating artificial intelligence with real-world applications. šŸ“ššŸ§‘ā€šŸŽ“šŸ“ˆ

Experience šŸ‘Øā€šŸ«

Yuanming Zhang has been an Associate Professor at Zhejiang University of Technology since completing his Ph.D. in 2010. His professional journey spans over a decade in academia, focusing on AI, neural networks, and knowledge graphs. He has supervised research projects, collaborated on industry applications, and contributed to advancements in predictive analytics and condition monitoring. His expertise extends to teaching, mentoring, and interdisciplinary AI applications. šŸ«šŸ¤–šŸ“”

Research Interests šŸ”¬

Yuanming Zhang specializes in deep learning, attention mechanisms, graph neural networks, and AI-driven predictive analytics. His research explores neural architectures for data processing, knowledge representation, and condition monitoring. His expertise spans convolutional networks, LSTMs, GRUs, and deep belief networks. His work contributes to advancements in AI-driven diagnostics, intelligent systems, and real-time health monitoring applications. šŸ§ šŸ“ŠšŸ–„ļø

Awards & Recognitions šŸ…

Yuanming Zhang has received recognition for his contributions to AI, machine learning, and data analytics. His work in deep learning and knowledge graphs has earned him accolades from research institutions and conferences. His papers in neural networks and predictive maintenance have been highly cited, solidifying his impact in the field. His research excellence has been acknowledged through grants and academic distinctions. šŸŽ–ļøšŸ“œšŸ”¬

PublicationsĀ 

 

Dingming Wu | Computer Science | Best Researcher Award

Posted on by sciencefather

Dr. Dingming Wu | Computer Science | Best Researcher Award

 

Profile

  • scopus

Education

He holds a Ph.D. in Computer Science and Technology from Harbin Institute of Technology, where he studied under the supervision of Professor Xiaolong Wang from March 2018 to December 2022. Prior to that, he earned a Masterā€™s degree in Probability Theory and Mathematical Statistics from Shandong University of Science and Technology in collaboration with the University of Chinese Academy of Sciences, completing his studies under the guidance of Professor Tiande Guo between September 2014 and July 2017. His academic journey began with a Bachelorā€™s degree in Information and Computational Science from Shandong University of Science and Technology, which he completed between September 2006 and July 2010.

Work experience

He is currently a Postdoctoral Fellow at the University of Electronic Science and Technology of China, Chengdu, a position he has held since December 2022 and will continue until December 2024. His research focuses on EEG signal processing and algorithm feature extraction, specifically addressing the challenges posed by the complexity and individual variations of EEG signals. Given the limitations of traditional classification methods, his work aims to enhance recognition accuracy through advanced deep learning models, improving the decoding of intricate EEG signals and optimizing control accuracy. Additionally, he integrates artificial intelligence technologies to predict user intentions and provide proactive responses, ultimately enhancing the interactive experience. His system is designed for long-term stability and adaptability, leveraging self-learning mechanisms based on user feedback.

Previously, he worked as a Data Analyst at Qingdao Sanlujiu International Trade Co., Ltd., Shanghai, from September 2010 to July 2014. In this role, he was responsible for conducting statistical analysis of trade flow data.

Publication

  • [1] Dingming Wu, Xiaolong Wangāˆ—, and Shaocong Wu. Jointly modeling transfer learning of
    industrial chain information and deep learning for stock prediction[J]. Expert Systems with
    Applications, 2022, 191(7):116257.
    [2] Dingming Wu, Xiaolong Wangāˆ—, and Shaocong Wu.A hybrid framework based on extreme
    learning machine, discrete wavelet transform, and autoencoder with feature penalty for stock
    prediction[J]. Expert Systems with Applications, 2022, 207(24):118006.
    [3] Dingming Wu, Xiaolong Wangāˆ—, and Shaocong Wu. Construction of stock portfolio based on
    k-means clustering of continuous trend features[J]. Knowledge-Based Systems, 2022,
    252(18):109358.
    [4] Dingming Wu, Xiaolong Wangāˆ—, Jingyong Su, Buzhou Tang, and Shaocong Wu. A labeling
    method for financial time series prediction based on trends[J]. Entropy, 2020, 22(10):1162.
    [5] Dingming Wu, Xiaolong Wangāˆ—, and Shaocong Wu. A hybrid method based on extreme
    learning machine and wavelet transform denoising for stock prediction[J]. Entropy, 2021,
    23(4):440.
    Papers to be published:
    [6] Wavelet transform in conjunction with temporal convolutional networks for time series
    prediction. Journal: PATTERN RECOGNITION; Status: under review; Position: Sole
    Author.
    [7] A Multidimensional Adaptive Transformer Network for Fatigue Detection. Journal: Cognitive
    Neurodynamics; Status: accept; Position: First Author.
    [8] A Multi-branch Feature Fusion Deep Learning Model for EEG-Based Cross-Subject Motor
    Imagery Classification. Journal: ENGINEERING APPLICATIONS OF ARTIFICIAL
    INTELLIGENCE; Status: under review; Position: First Author.
    [9] A Coupling of Common-Private Topological Patterns Learning Approach for Mitigating Interindividual Variability in EEG-based Emotion Recognition. Journal: Biomedical Signal
    Processing and Control; Status: Revise; Position: First Corresponding Author.
    [10] A Function-Structure Adaptive Decoupled Learning Framework for Multi-Cognitive Tasks
    EEG Decoding. Journal: IEEE Transactions on Neural Networks and Learning Systems;
    Status: under review; Position: Co-First Author.
    [11] Decoding Topology-Implicit EEG Representations Under Manifold-Euclidean Hybrid Space.
    Computer conference: International Joint Conference on Artificial Intelligence 2025 (IJCAI);
    Status: under review; Position: Second Corresponding Author.
    [12] Style Transfer Mapping for EEG-Based Neuropsychiatric Diseases Recognition. Journal:
    EXPERT SYSTEMS WITH APPLICATIONS; Status: under review; Position: Second
    Corresponding Author.
    [13] An Adaptive Ascending Learning Strategy Based on Graph Optional Interaction for EEG
    Decoding. Computer conference: International Joint Conference on Artificial Intelligence
    2025 (IJCAI); Status: under review; Position: Second Corresponding Author.
    [14] A Transfer Optimization Methodology of Graph Representation Incorporating CommonPrivate Feature Decomposition for EEG Emotion Recognition. Computer conference:
    International Joint Conference on Artificial Intelligence 2025 (IJCAI); Status: under review;
    Position: Second Corresponding Author.
    [15] An Interpretable Neural Network Incorporating Rule-Based Constraints for EEG Emotion
    Recognition. Computer conference: International Joint Conference on Artificial Intelligence
    2025 (IJCAI); Status: under review; Position: First Author.

Mahmoud Alimoradi | Machine Learning | Best Researcher Award

Posted on by sciencefather

Mr. Mahmoud Alimoradi | Machine Learning | Best Researcher Award

Lahijan Azad ,Iran

He understands the growing need for Machine Learning and has a keen interest in the field, which he considers a blessing. Recognizing the importance of managing large and complex computations to control various aspects of the human environment has led him into this vast world. He is particularly fascinated by machine learning, especially reinforcement learning, supervised learning, semi-supervised learning, outliers, and basic data challenges. Furthermore, optimization, an area of artificial intelligence that requires fundamental studies and a change in approach, is another of his key research interests.

Profile

Education

He holds a Masterā€™s degree in Artificial Intelligence Engineering from the University of Shafagh, completed in 2020. His thesis was titled “Trees Social Relations Optimization Algorithm: A New Swarm-Based Metaheuristic Technique to Solve Continuous and Discrete Optimization Problems.” He also earned a Bachelorā€™s degree in Software Engineering from Azad Lahijan University, which he attended from 2007 to 2011.

Research Interests

Theory: Reinforcement Learning (high-dimensional problems, regularized algorithms, model
learning,
representation learning and deep RL, learning from demonstration, inverse optimal control, deep
Reinforcement Learning); Machine Learning (statistical learning theory, nonparametric
algorithms, time series. processes, manifold learning, online learning); Large-scale Optimization;
Evolutionary Computation, Metaheuristic Algorithm, Deep Learning, Healthcare Machine
learning, Big Data, Data Problems (Imbalanced), Signal Analysis
Applications: Automated control, space affairs, robotic control, medicine and health, asymmetric
data, data science, scheduling, proposing systems, self-enhancing systems

Work Experience

He is a freelance programmer with expertise in various operating systems, including Microsoft Windows and Linux (Arch, Ubuntu, Fedora). He is proficient in software tools such as Microsoft Office, Anaconda, Jupyter, PyCharm, Visual Studio, Tableau, RapidMiner, MATLAB, and Visual Studio. His programming skills include Matlab, Python, C++, Scala, Java, and Julia, with a focus on data mining, data science, computer vision, and machine learning. He is experienced with Python libraries like Pandas, Numpy, Matplotlib, Seaborn, PyCV, TensorFlow, Time Series Analysis, Spark, Hadoop, and Cassandra. Additionally, he is skilled in using Github, Docker, and MySQL. His expertise spans machine learning, deep learning, imbalanced data, missing data, semi-supervised learning, healthcare machine learning, algorithm design, and metaheuristic algorithms. He is fluent in English and Persian.

Publications