Publikationsdatum:
2017-06-13
Beschreibung:
Empirical methods for the estimation of Southern Ocean CO 2 : Support Vector and Random Forest Regression Luke Gregor, Schalk Kok, and Pedro M. S. Monteiro Biogeosciences Discuss., https//doi.org/10.5194/bg-2017-215,2017 Manuscript under review for BG (discussion: open, 0 comments) We use machine learning to extrapolate ship measurements of CO 2 using satellite data. We present two ML methods new to this field. These methods perform well in context of previous work and reproduce the decadal trends of previous estimates. To test the methods, we simulate the exact observed setup in biogeochemical ocean model output. We show that there are not yet enough measurements of CO 2 in the SO for the community to resolve CO 2 to the point where non-linear ML methods agree.
Print ISSN:
1810-6277
Digitale ISSN:
1810-6285
Thema:
Biologie
,
Geologie und Paläontologie