Preprints
https://doi.org/10.5194/egusphere-2023-1876
https://doi.org/10.5194/egusphere-2023-1876
05 Oct 2023
 | 05 Oct 2023

PPCon 1.0: Biogeochemical Argo Profile Prediction with 1D Convolutional Networks

Gloria Pietropolli, Luca Manzoni, and Gianpiero Cossarini

Abstract. Effective observation of the ocean is vital for studying and assessing the state and evolution of the marine ecosystem, and for evaluating the impact of human activities. However, obtaining comprehensive oceanic measurements across temporal and spatial scales and for different biogeochemical variables remains challenging. Autonomous oceanographic instruments, such as Biogeochemical (BCG) Argo profiling floats, have helped expand our ability to obtain subsurface and deep-ocean measurements, but measuring biogeochemical variables such as nutrient concentration still remains more demanding and expensive than measuring physical variables. Therefore, developing methods to estimate marine biogeochemical variables from high-frequency measurements is very much needed. Current Neural Network (NN) models developed for this task are based on a Multilayer Perceptron (MLP) architecture, trained over punctual pairs of input-output features. However, MLPs lack awareness of the typical shape of biogeochemical variable profiles they aim to infer, resulting in irregularities such as jumps and gaps when used for the prediction of vertical profiles. In this study, we evaluate the effectiveness of a one-dimensional Convolutional Neural Network (1D CNN) model to predict nutrient profiles, leveraging the typical shape of vertical profiles of a variable as a prior constraint during training. We will present a novel model named PPCon (Predict Profiles Convolutional), which is trained over a dataset containing BCG Argo float measurements, for the prediction of nitrate, chlorophyll and backscattering (bbp700), starting from the date, geolocation, temperature, salinity, and oxygen. The effectiveness of the model is then accurately validated by presenting both quantitative metrics and visual representations of the predicted profiles. Our proposed approach proves capable of overcoming the limitations of MLPs, resulting in smooth and accurate profile predictions.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Gloria Pietropolli, Luca Manzoni, and Gianpiero Cossarini

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-1876', Anonymous Referee #1, 24 Nov 2023
    • AC1: 'Reply on RC1', Gloria Pietropolli, 05 Jan 2024
  • RC2: 'Comment on egusphere-2023-1876', Anonymous Referee #2, 27 Nov 2023
    • AC2: 'Reply on RC2', Gloria Pietropolli, 05 Jan 2024
Gloria Pietropolli, Luca Manzoni, and Gianpiero Cossarini
Gloria Pietropolli, Luca Manzoni, and Gianpiero Cossarini

Viewed

Total article views: 380 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
225 129 26 380 16 19
  • HTML: 225
  • PDF: 129
  • XML: 26
  • Total: 380
  • BibTeX: 16
  • EndNote: 19
Views and downloads (calculated since 05 Oct 2023)
Cumulative views and downloads (calculated since 05 Oct 2023)

Viewed (geographical distribution)

Total article views: 373 (including HTML, PDF, and XML) Thereof 373 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 21 May 2024
Download
Short summary
Harness AI for better ocean insights. BGC-Argo floats collect deep ocean data, yet forecasting vital nutrient levels is a challenge. Our novel AI approach, PPCon, learns from Argo float measurements and provides improved nutrient predictions. This enhances our understanding of ocean dynamics and nutrient distribution.