Recent developments in data mining and machine learning approaches have brought lots of excitement in providing solutions for challenging tasks (e.g., computer vision). However, many approaches have limited interpretability, so their success and failure modes are difficult to understand and their scientific robustness is difficult to evaluate. Thus, there is an urgent need for better understanding of the scientific reasoning behind data mining and machine learning approaches. This requires taking a transdisciplinary view of data science and recognizing its foundations in mathematics, statistics, and computer science. Focusing on the geospatial domain, we apply this crucial transdisciplinary perspective to five common geospatial techniques (hotspot detection, colocation detection, prediction, outlier detection and teleconnection detection). We also describe challenges and opportunities for future advancement.
Bibliographical noteFunding Information:
Acknowledgments: This material is based upon work supported by the National Science Foundation under Grants No. 1541876, 1029711, IIS-1320580, 0940818 and IIS-1218168, the USDOD under Grants No. HM1582-08-1-0017 and HM0210-13-1-0005, ARPA-E under Grant No. DE-AR0000795, USDA under Grant No. 2017-51181-27222 and the OVPR Infrastructure Investment Initiative and Minnesota Supercomputing Institute (MSI) at the University of Minnesota. We also thank Kim Koffolt and Jayant Gupta for improving the readability of this article.
© 2017 by the authors.
- Computer science
- Geospatial data science
- Transdisciplinary foundations