Global sea surface dimethyl sulfide dataset simulated by artificial neural network

This dataset contains (1) the matched and binned data used for constructing an artificial neural network (ANN) model to simulate the sea surface concentration of dimethyl sulfide (DMS); (2) the simulated global daily sea surface concentrations of DMS ranging from 2005 to 2014 by ANN model and the calculated total transfer velocities (Kt) and sea-to-air fluxes; (3) the simulated global monthly sea surface concentrations of DMS ranging from 2005 to 2100 by ANN model and CMIP6 ensemble and the calculated Kt and sea-to-air fluxes; (4) the yearly mean DMS concentration of each grid in different sensitivity experiments exploring the roles different variables play in driving DMS future changes. The input variables of this ANN model include chlorophyll a, sea surface temperature (SST), mixed layer depth (MLD), nitrate, phosphate, silicate, dissolved oxygen (DO), downward short-wave radiation (DSWF), and sea surface salinity (SSS). The future projections (2015-2100) are subjected into two Shared Socioeconomic Pathway scenarios SSP2-4.5 and SSP5-8.5. The spatial resolution of the simulated dataset is 1°×1°. The units of DMS concentration, Kt, and flux are nmol L–1, m s–1, and μmol S m–2 d –1, respectively.

Compared with the previous version (v1.0), this version is based on an updated ANN model after adjusting the data match-up between satellite and in-situ chlorophyll a for ANN training. In addition, the historical simulation based on CMIP6 only covers the time period from 2005 to 2014, which was from 1850 to 2014 for v1.0.

本数据集包含四类数据：（1）用于构建人工神经网络（Artificial Neural Network，ANN）模型以模拟二甲基硫（Dimethyl Sulfide，DMS）海表浓度的匹配分箱数据；（2）2005至2014年由ANN模型模拟得到的全球逐日DMS海表浓度，以及计算得到的总传输速率（Kt）和海-气通量；（3）2005至2100年由ANN模型与CMIP6集合模拟得到的全球逐月DMS海表浓度，以及计算得到的Kt和海-气通量；（4）不同敏感性试验中各网格的年平均DMS浓度，用于探究不同变量在驱动DMS未来变化中所起的作用。

该ANN模型的输入变量包括叶绿素a、海表温度（Sea Surface Temperature，SST）、混合层深度（Mixed Layer Depth，MLD）、硝酸盐、磷酸盐、硅酸盐、溶解氧（Dissolved Oxygen，DO）、下行短波辐射（Downward Short-wave Radiation，DSWF）以及海表盐度（Sea Surface Salinity，SSS）。

2015至2100年的未来预估试验采用两类共享社会经济路径（Shared Socioeconomic Pathways，SSP）：SSP2-4.5与SSP5-8.5。本模拟数据集的空间分辨率为1°×1°。DMS浓度、Kt及通量的单位分别为nmol L–1、m s–1与μmol S m–2 d–1。

相较于此前发布的v1.0版本，本数据集基于更新后的ANN模型构建，该模型调整了ANN训练中卫星与原位叶绿素a的匹配配对处理流程。此外，本版基于CMIP6的历史模拟时段仅覆盖2005至2014年，而v1.0版本的对应时段为1850至2014年。