Contract Award: USGS Deep Learning & Remote Sensing Support. ==>> https://lnkd.in/eySSa9Vi
OrangeSlices Fed Citizen Services’ Post
More Relevant Posts
-
We developed and presented a two-stage, data-driven framework using machine learning to optimize the rate of penetration (ROP) in S-shaped wells in Southern Iraq. This framework uses existing well data and Dynamic Time Warping (DTW) techniques to identify optimal controllable parameters, adapting to new field data and expert recommendations. Four models—Support Vector Machines (SVM), Artificial Neural Networks (ANN), Random Forest, and XGBoost—were used to predict ROP. XGBoost, achieving the highest accuracy, was then used in a Particle Swarm Optimization (PSO) algorithm to optimize parameters like Weight on Bit (WOB), revolutions per minute (RPM), and Flow Rate. The results showed significant ROP improvements across four wells, ranging from 18.13% to 19.67%. This project was presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference and has been published on OnePetro.
To view or add a comment, sign in
-
📈 10M+ Views | 🚀 Turning Data into Actionable Insights | 🤖 AI, ML & Analytics Expert | 🎥 Content Creator & YouTuber | 💻 Power Apps Innovator | 🖼️ NFTs Advocate | 💡 Tech & Innovation Visionary | 🔔 Follow for More
🚀 New breakthrough in AI and computer vision! Researchers have developed the Deep Atmospheric TUrbulence Mitigation network (DATUM) to efficiently recover images distorted by atmospheric turbulence. By integrating classical multi-frame methods into a deep learning structure, DATUM outperforms existing algorithms and achieves a tenfold increase in processing speed. This innovation paves the way for real-world applications of turbulence mitigation. #AI #ComputerVision #DeepLearning #Innovation #DATUM
🚀 New breakthrough in AI and computer vision! Researchers have developed the Deep Atmospheric TUrbulence Mitigation network (DATUM) to efficiently recover images distorted by atmospheric turbulence. By integrating classical multi-frame methods into a deep learning structure, DATUM outperforms existing algorithms and achieves a tenfold increase in processing speed. This innovation paves the w...
arxiv.org
To view or add a comment, sign in
-
Seismic data processing has traditionally faced challenges in separating signal from noise but PGS has been deploying machine learning workflows at a large scale to enhance and accelerate imaging and interpretation. Learn more about how ML is transforming data processing in this new feature story with real-world applications. Julien Oukili, Jyoti Kumar, Jon Burren, Steven Cochran, Martin Bubner, Denis Nasyrov, Bagher Farmani #energysecurity #energytransition
PGS Machine Learning Applications Revolutionize Seismic Data Processing | PGS
pgs.com
To view or add a comment, sign in
-
Postdoctoral Fellow (Remote Sensing) || Deep Learning || Python || Earth Observation Expert || GeoAI || GIS || Geoinformatics
In the domain of #remotesensing #imageprocessing , road extraction from high-resolution #aerialimagery has already been a hot research topic. Although deep #CNNs have presented excellent results for semantic segmentation, the efficiency and capabilities of #visiontransformers are yet to be fully researched. As such, for accurate road extraction, a deep semantic segmentation #neuralnetworks that utilizes the abilities of residual learning, HetConvs, #UNet, and vision transformers, which is called ResUNetFormer, is proposed in this letter. The developed ResUNetFormer is evaluated on various cutting-edge deep learning-based road extraction techniques on the public Massachusetts road dataset. Statistical and visual results demonstrate the superiority of the ResUNetFormer over the state-of-the-art CNNs and vision transformers for segmentation. Paper: https://lnkd.in/gEnF37D2 Codes: https://lnkd.in/gPDjzB2E Authors: Ali Jamali, Swalpa Kumar Roy, Jonathan Li, and Pedram Ghamisi #cnn #deeplearning #machinelearning #vision #imageprocessing #remotesensing #roadextraction
To view or add a comment, sign in
-
I am pleased to announce that our new paper entitled "Enhancing vessel arrival time prediction: A fusion-based deep learning approach " has been published in the Journal: ‘Expert Systems With Applications', ‘Elsevier’, ‘IF: 8.5’. Here is the link to download: https://lnkd.in/ezciES6F I would like to extend my sincere gratitude to Professor Jos van Hillegersberg for his support throughout the development of this paper. Dr. Chintan Amrit, I sincerely appreciate your support as well. #UniversityofDerby #UniversityofTwente #UniversityofAmsterdam Abstract: The logistic community of shippers has struggled to predict the precise arrival time of seagoing vessels with reliable certainty. This research work proposes a method to predict vessel arrival time that could eventually be incorporated into an intelligent decision support system that we call Vessel Arrival Time Prediction …. #Arrivaltimeprediction #deeplearning #Intelligenttransportationsystems #IntelligentDecisionSupportSystem
To view or add a comment, sign in
-
📢 #HighlyViewedPapers 1. Research on Efficient Construction Paths for Intelligent Coal Mines in China from the Configuration Perspective 🔗 https://lnkd.in/gUAGk2CQ 2. Effective Class-Imbalance Learning Based on SMOTE and Convolutional Neural Networks 🔗 https://lnkd.in/gr_2zh5Y 3. Fuzzy-PID-Based Atmosphere Packaging Gas Distribution System for Fresh Food 🔗 https://lnkd.in/gBpPk9x3 4. A Pineapple Target Detection Method in a Field Environment Based on Improved YOLOv7 🔗 https://lnkd.in/gnQCWisv
To view or add a comment, sign in
-
BETA - Microsoft LSA ⭐ || AI/ML Lead @ Microsoft LSA, KIIT Chapter || Oracle Certified GenAI Professional || Ex - Intern @ Integrated Test Range, DRDO || Ex - Research Intern @ IIT Kharagpur || Researcher
🌟 Exciting News Alert! 🌟 I am thrilled to announce that our research paper titled "Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture", co-authored by myself, Sainath Dey, and Aniruddha Mukherjee, has been accepted for presentation at the 6th International Conference in Computational Intelligence and Pattern Recognition! 🚀 This paper delves into the cutting-edge realm of satellite imagery analysis, employing advanced Convolutional Neural Network (CNN) techniques, particularly the U-Net architecture, to segment landforms. Our work aims to revolutionize how we perceive and analyze satellite data, opening doors to enhanced understanding and applications in various domains. 📚 What's even more exciting is that our research will be published in the esteemed Lecture Notes in Network and Systems Series of Springer Nature Group, adding a significant milestone to our academic journey. Stay tuned for more updates as we embark on this exciting journey! 🌐✨ #Research #AI #SatelliteImagery #CNN #U-Net #PatternRecognition #ComputationalIntelligence #Springer #ConferenceAccepted
To view or add a comment, sign in
2,621 followers