首页|Researchers from Woods Hole Oceanographic Institute Describe Findings in Machine Learning (Barium In Seawater: Dissolved Distribution, Relationship To Silicon, and Barite Saturation Statedetermined Using Machine Learning)
Researchers from Woods Hole Oceanographic Institute Describe Findings in Machine Learning (Barium In Seawater: Dissolved Distribution, Relationship To Silicon, and Barite Saturation Statedetermined Using Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Woods Hole, Ma ssachusetts, by NewsRx journalists, research stated, "Barium is widely used as a proxy for dissolved silicon and particulate organic carbon fluxes in seawater. However, these proxy applications are limited by insufficient knowledge of the d issolved distribution of Ba ([Ba])." Financial support for this research came from Woods Hole Oceanographic Instituti on. The news reporters obtained a quote from the research from Woods Hole Oceanograp hic Institute, "For example, there is significant spatial variability in the bar ium-silicon relationship, and ocean chemistry may influence sedimentary Ba prese rvation. To help address these issues, we developed 4095 models for predicting [Ba] using Gaussian process regression machine learning. These models were trained to predict [Ba] from standard oceanographic observations using GEOTRACES data from the Arctic, Atlant ic, Pacific, and Southern oceans. Trained models were then validated by comparin g predictions against withheld [Ba] data f rom the Indian Ocean. We find that a model trained using depth, temperature, and salinity, as well as dissolved dioxygen, phosphate, nitrate, and silicate, can accurately predict [Ba] in the Indian Ocea n with a mean absolute percentage deviation of 6.0 %. We use this m odel to simulate [Ba] on a global basis us ing these same seven predictors in the World Ocean Atlas. The resulting [Ba] distribution constrains the Ba budget of the ocean to 122 (+/-7) x 10(12) mol and reveals oceanographically consistent variability in the barium-silicon relationship. We then calculate the saturation state of seawater with respect to barite. This calculation reveals systematic spatial and vertical variations in marine barite saturation and shows that the ocean below 1000 m is at equilibrium with respect to barite. We describe a number of possible applica tions for our model outputs, ranging from use in mechanistic biogeochemical mode ls to paleoproxy calibration. Our approach demonstrates the utility of machine l earning in accurately simulating the distributions of tracers in the sea and pro vides a framework that could be extended to other trace elements."
Woods HoleMassachusettsUnited StatesNorth and Central AmericaAlkaline Earth MetalsBariumCyborgsEmerging Te chnologiesMachine LearningWoods Hole Oceanographic Institute
NETL
NSTL
