A global monthly climatology of total alkalinity (AT): a neural network approach (NCEI Accession 0222470)

This NCEI accession contains global monthly climatology of oceanic total alkalinity (AT). Total alkalinity (AT) monthly climatology was created from a neural network approach (Broullón et al., 2019). The neural network was trained with GLODAPv2.2019 data (Olsen et al., 2019) using as predictor variables position (latitude, longitude and depth), temperature, salinity, phosphate, nitrate, silicate and dissolved oxygen. The relations extracted between these predictor variables and AT were used to obtain the climatology passing through the network global monthly climatologies of the predictor variables: temperature and salinity fields of the World Ocean Atlas version 2013 (WOA13), filtered WOA13 oxygen (fifth-order one-dimensional median filter through the depth dimension; see Broullón et al., 2019 for details) and nutrients computed using CANYON-B (Bittig et al., 2018) over the three previous fields. The obtained climatology has a 1ºx1º spatial resolution and 102 depth levels between 0 and 5500 m, with a monthly resolution from 0 to 1500 m and an annual resolution from 1550 to 5500m.

本美国国家环境信息中心（National Centers for Environmental Information, NCEI）收录的数据集包含全球海洋总碱度（total alkalinity, AT）逐月气候态数据。本次逐月总碱度气候态数据基于神经网络方法（Broullón等，2019）构建。该神经网络以GLODAPv2.2019数据集（Olsen等，2019）为训练数据源，选取位置参数（纬度、经度与水深）、温度、盐度、磷酸盐、硝酸盐、硅酸盐及溶解氧作为预测变量。基于上述预测变量与总碱度间提取得到的关联关系，结合以下预测变量的全球逐月气候态数据输入该神经网络，即可得到目标总碱度气候态：2013版世界海洋图集（World Ocean Atlas 2013, WOA13）的温度与盐度场、经深度维度五阶一维中值滤波处理后的WOA13溶解氧数据（详细方法参见Broullón等，2019），以及基于前述三场数据通过CANYON-B模型（Bittig等，2018）计算得到的营养盐数据。所得气候态数据的空间分辨率为1°×1°，共设置102个水深层级，覆盖0至5500米水深范围；其中0至1500米水深层采用逐月分辨率，1550至5500米水深层采用年分辨率。