dGB Earth Sciences has announced what it claims is the world’s first fully-integrated machine learning platform for E&P data.
dGB Earth Sciences has announced what it claims is the world’s first fully-integrated machine learning platform for E&P data. The machine learning plugin for OpendTect links its seismic interpretation system with the R&D world of Python, TensorFlow, Keras and Scikit Learn.
‘Geoscientists can deploy trained machine learning models to solve their seismic and well problems. No programming skills are required,’ said dGB. ‘Experimental geoscientists can develop new workflows and train models to add value to their data. This is done with the existing tools and models available in the platform. Newly trained models can be shared with others ensuring rapid deployment in operational settings. Researchers can speed up their machine learning research by programming in a Python environment that takes care of data IO and visualization.’
Deep learning models created in this environment are directly available in the machine learning plugin for further use. dGB Earth Sciences supports the FORCE Machine Learning Competition 2020. dGB offers the competition datasets pre-loaded in OpendTect format. The machine learning plugin and all other commercial plugins controlled by dGB will work on these special OpendTect projects without licence keys.
