Introduction to Special Issue: Geoscience Data Analytics and Machine Learning摘要
MOTIVATION FOR THIS SPECIAL ISSUE OF THE AAPG BULLETIN
A digital revolution is underway in all sectors of our economy (Gurumurthy and Schatsky, 2019), posing unique challenges and opportunities for science and engineering research and practice. Still, in many ways, geoscientists and subsurface engineers are further down the digital path due to our long history of implementing data-driven methods in our workflows. Motivated by the complexity of the vast subsurface, the challenges of subsurface data, including data volume, variety, and veracity, and the necessity to support costly development decisions, statistical tools for subsurface resource estimation and mapping were developed by Krige (1951) and later augmented with theory and given the name “geostatistics” by Matheron (1962). Many practical geoscience applications have been developed in mineral mining (Journel and Huijbregts, 1978; Rossi and Deutsch, 2014), petroleum (Caers, 2005; Pyrcz and Deutsch, 2014), and hydrogeology (Kitanidis, 1997) supported by open-source software (Deutsch and Journel, 1997; Remy et al., 2009; Pyrcz et al., 2021).
|
@ 2023 版权所有 中国地质图书馆 (中国地质调查局地学文献中心)
京ICP备 05064591号 京公网安备11010802017129号
建议浏览器: 火狐、谷歌、微软 Edge、不支持 IE