logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Artificial Intelligence for Sustainable Ocean Management Using Satellite Data

delete2026-05-01
delete0
PRE
AI
J
Jorge A. Ruíz-Vanoye *
O
Ocotlán Díaz-Parra
F
Francisco R. Trejo-Macotela
R
Ramos-Fernandez, Julio C.
A
Aguilar-Ortiz, Jaime
L
Liceaga-Ortiz-De-La-Pena, Jose M.
V
Vera-Jimenez, Marco Antonio
L
Lopez, Julio Cesar Salas
S
Silva, Juvencio Sebastian Zarazua
DOI：10.61467/2007.1558.2026.v17i2.1291delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
The integration of artificial intelligence and satellite remote sensing provides an innovative approach to sustainable ocean management. This study demonstrates how oceanographic sensors and AI-driven predictive models enhance the monitoring and governance of Marine Protected Areas (MPAs) and sustainable fishing zones. Multivariate datasets are used to map areas of high primary productivity in the Gulf of Mexico, employing QGIS and ArcGIS for spatial analysis. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks trained on historical time series forecast ecological risks, including hypoxic zones and harmful algal blooms. Unsupervised clustering and dimensionality reduction identify anomalies relative to natural oceanographic patterns, supporting more adaptive and precautionary ocean governance. The integration of artificial intelligence and satellite remote sensing provides an innovative approach to sustainable ocean management. This study demonstrates how oceanographic sensors and AI-driven predictive models enhance the monitoring and governance of Marine Protected Areas (MPAs) and sustainable fishing zones. Multivariate datasets are used to map areas of high primary productivity in the Gulf of Mexico, employing QGIS and ArcGIS for spatial analysis. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks trained on historical time series forecast ecological risks, including hypoxic zones and harmful algal blooms. Unsupervised clustering and dimensionality reduction identify anomalies relative to natural oceanographic patterns, supporting more adaptive and precautionary ocean governance.
Keywords:
Artificial Intelligence
Sustainable Ocean Management
Marine Protected Areas
Gated Recurrent Units
Long Short-Term Memory
Satellite Remote Sensing
Oceanographic Modelling

Journal

I
International Journal of Combinatorial Optimization Problems and Informatics
IF:
0.3
Papers:
71
Citations:
61

Organization

No organization information available