Machine Learning and Reservoir Sedimentological Models

Machine Learning and Reservoirs

We presented our work that uses machine learning to improve oil and gas reservoir sedimentological models. Here are the details:

Workshop on Deep Water Sedimentation

I took part of the 2018 Workshop on Deep Water Sedimentation. Below you can find the list of works I presented:

  • Javier Iparraguirre, Mariano Arcuri, Carlos Zavala, Mariano Di Meglio y Agustin Zorzano. Quantification of Net-To-Gross and Oil Impregnation in Bioturbated Heterolithic Clastic Reservoirs.
  • Javier Iparraguirre, Carlos Zavala, and Mariano Arcuri. From a Core to an Oil Field: Machine Learning Applied to Sedimentological Models.
  • Javier Iparraguirre, Mariano Arcuri, Carlos Zavala, Mariano Di Meglio y Agustin Zorzano. Lithohero: Creating comprehensive sedimentary logs from cores and outcrops.
WDWS 2018

More results from our online video summarization algorithm

In this page you will find more results from our algorithm that performs online video summarization. The method is called LFOVS (Local Features Online Video Summarization). If you use the data, please cite the publication listed below (BibTex code):

title={Online Video Summarization Based on Local Features},
author={Iparraguirre, Javier and Delrieux, Claudio A},
journal={International Journal of Multimedia Data Engineering and Management (IJMDEM)},
publisher={IGI Global}

video summarization results
video summarization results

Heterogeneous Computers Publication at ARGENCON 2014

We presented the paper titled “Speeded-up robust features (SURF) as a benchmark for heterogeneous computers” at ARGECON 2014. In this work we run CUDA and OpenCL SURF implementations int order to test performance on heterogeneous computers.

You can find the paper on IEEE Xplore.


Video Summarization Paper Presented at IEEE ISM 2013

We present our paper titled “Speeded-up Video Summarization Based on Local Features” at IEEE International Symposium on Multimedia (ISM2013). You can find the complete work at IEEE Xplore.


Digital video has become a very popular media in several contexts, with an ever expanding horizon of applications and uses. Thus, the amount of available video data is growing almost limitless. For this reason, video summarization continues to attract the attention of a wide spectrum of research efforts. In this work we present a novel video summarization technique based on tracking local features among consecutive frames. Our approach operates on the uncompressed domain, and requires only a small set of consecutive frames to perform, thus being able to process the video stream directly and produce results on the fly. We tested our implementation on standard available datasets, and compared the results with the most recent published work in the field. The results achieved show that our proposal produces summarizations that have similar quality than the best published proposals, with the additional advantage of being able to process the stream directly in the uncompressed domain.


You can see published results here.