Introduction to Geoscience Data Analytics Using Machine Learning
Before the arrival of big data, statistical methods used in science and engineering were dominantly model-based with an emphasis on estimation unbiasedness. Although many traditional statistical methods work well with small datasets and a proper experimental design, they are less effective in handling some of the problems that have arisen out of big data. Artificial intelligence (AI) has led the way to data mining for discovering patterns and regularities from big data and for making predictions for scientific and technical applications. Although the movement was initially led by computer scientists, statisticians, scientists and engineers are now all involved, thus strengthening the trend.
In exploration and production, data have also grown exponentially. Extracting information from data and making predictions using data have become increasingly important. Most data in exploration and production are soft data. Each data source may tell us something, but no source tells us everything; that is, few data give us a definitive answer. Hard data are still sparse. How to integrate big soft data with small hard data is a challenge for reservoir characterization and modeling. This chapter presents an introduction to machine learning and applications of neural networks to geoscience data analytics.
- Bansal, Y., Ertekin, T., Karpyn, Z., Ayala, L., Nejad, A., Suleen, F., Balogun, O., Liebmann, D., & Sun, Q. (2013). Forecasting well performance in a discontinuous tight oil reservoir using artificial neural networks. Paper presented at the Unconventional Resources Conference, SPE, The Woodlands, Texas, SPE 164542.Google Scholar
- Negnevitsky, M. (2005). Artificial intelligence: a guide to intelligent systems. Harlow, England: Pearson Education.Google Scholar
- Schapire, R. E. (1990). The strength of weak learnability. Machine Learning, 5, 197–227.Google Scholar