Mapping the global distribution of lead and its isotopes in seawater with explainable machine learning
File(s)
Published version
OA Location
Author(s)
Olivelli, Arianna
Arcucci, Rossella
Rehkamper, Mark
van de Flierdt, Tina
Type
Journal Article
Abstract
Lead (Pb) and its isotopes are powerful tools for studying the pathways of Pb pollution from land to
sea and, simultaneously, investigating biogeochemical processes in the ocean. However, the scarcity and sparsity
of in situ measurements of Pb concentrations and isotope compositions do not allow for a comprehensive understanding of Pb pollution pathways and biogeochemical cycling on a global scale. Here, we present three machine
learning models developed to map seawater Pb concentrations and isotope compositions, leveraging the global
GEOTRACES dataset as well as historical data. The models use climatologies of oceanographic and atmospheric
variables as features from which to predict Pb concentrations, 206Pb/
207Pb, and 208Pb/
207Pb. Using SHapley
Additive exPlanations (SHAP), we found that seawater temperature, atmospheric dust, atmospheric black carbon, and salinity are the most important features for predicting Pb concentrations. Dissolved oxygen concentration, salinity, temperature, and atmospheric dust are the most important features for predicting 206Pb/
207Pb,
atmospheric black carbon and dust, seawater temperature, and surface chlorophyll a for 208Pb/
207Pb. In line
with observations, our model outputs show that (i) the surface Indian Ocean has the highest levels of pollution,
(ii) pollution from previous decades is sinking in the North Atlantic and Pacific oceans, and (iii) waters characterised by highly anthropogenic Pb isotope fingerprints are spreading from the Southern Ocean throughout the
Southern Hemisphere at intermediate depths. By analysing the uncertainty associated with our maps, we identified the Southern Ocean as the key area to prioritise in future sampling campaigns. Our datasets, models, and
their outputs, in the forms of Pb concentrations, 206Pb/
207Pb climatologies, and 208Pb/
207Pb climatologies, are
made freely available to the community by Olivelli et al. (2024a; https://doi.org/10.5281/zenodo.14261154) and
Olivelli (2025; https://doi.org/10.5281/zenodo.15355008).
sea and, simultaneously, investigating biogeochemical processes in the ocean. However, the scarcity and sparsity
of in situ measurements of Pb concentrations and isotope compositions do not allow for a comprehensive understanding of Pb pollution pathways and biogeochemical cycling on a global scale. Here, we present three machine
learning models developed to map seawater Pb concentrations and isotope compositions, leveraging the global
GEOTRACES dataset as well as historical data. The models use climatologies of oceanographic and atmospheric
variables as features from which to predict Pb concentrations, 206Pb/
207Pb, and 208Pb/
207Pb. Using SHapley
Additive exPlanations (SHAP), we found that seawater temperature, atmospheric dust, atmospheric black carbon, and salinity are the most important features for predicting Pb concentrations. Dissolved oxygen concentration, salinity, temperature, and atmospheric dust are the most important features for predicting 206Pb/
207Pb,
atmospheric black carbon and dust, seawater temperature, and surface chlorophyll a for 208Pb/
207Pb. In line
with observations, our model outputs show that (i) the surface Indian Ocean has the highest levels of pollution,
(ii) pollution from previous decades is sinking in the North Atlantic and Pacific oceans, and (iii) waters characterised by highly anthropogenic Pb isotope fingerprints are spreading from the Southern Ocean throughout the
Southern Hemisphere at intermediate depths. By analysing the uncertainty associated with our maps, we identified the Southern Ocean as the key area to prioritise in future sampling campaigns. Our datasets, models, and
their outputs, in the forms of Pb concentrations, 206Pb/
207Pb climatologies, and 208Pb/
207Pb climatologies, are
made freely available to the community by Olivelli et al. (2024a; https://doi.org/10.5281/zenodo.14261154) and
Olivelli (2025; https://doi.org/10.5281/zenodo.15355008).
Date Issued
2025-07-30
Date Acceptance
2025-04-24
Citation
Earth System Science Data, 2025, 17 (7), pp.3679-3699
ISSN
1866-3508
Publisher
Copernicus Publications
Start Page
3679
End Page
3699
Journal / Book Title
Earth System Science Data
Volume
17
Issue
7
Subjects
ANTHROPOGENIC LEAD
CIRCULATION
CONTAMINATION
Geology
Geosciences, Multidisciplinary
INDUSTRIAL
Meteorology & Atmospheric Sciences
NORTH-ATLANTIC
OCEAN
PACIFIC
PB ISOTOPES
Physical Sciences
Science & Technology
SURFACE
VARIABILITY
Publication Status
Published
Date Publish Online
2025-07-30