|
Applications of remote sensing and geographic information systems in identifying areas susceptible to marine fishing: A systematic review
|
Komeil Rokni *   , Sharifeh Hazini , Mohammad Gholizadeh |
|
|
|
Abstract: (8 Views) |
Efficiently locating economic fishing areas is a fundamental challenge in marine fisheries, directly affecting fuel consumption and stock sustainability. Traditional methods of finding fish rely on ship-based identification and fishermen’s experience, which are time-consuming, fuel-intensive, and spatially limited. Satellite remote sensing and geographic information systems have revolutionized the identification of fishing grounds by providing real-time, synchronized observations of oceanographic conditions that promote fish aggregation. This systematic review analyzes past studies on the application of remote sensing and geographic information systems to the identification of fishing grounds in marine fisheries. Sea surface temperature (SST) and chlorophyll a (Chl-a) concentration are identified as two strong environmental predictors, with frontal regions and mesoscale gyres consistently forming focal points for the aggregation of aquatic species. Machine learning approaches, particularly random forest and ensemble models, show higher prediction accuracy than traditional statistical methods, achieving area under the curve values between 85 and 94% in validated studies. Participatory geographic information systems are also recognized as a complementary approach that integrates indigenous knowledge into fisheries management frameworks. The main limitations include: data gaps caused by cloud cover in optical sensors, temporal inconsistency between satellite overpass times and fishing activity, and the inability of models to account for fishing effort or monitoring constraints. This review concludes that although the integration of remote sensing and GIS is a major advance towards data-driven fisheries management, future research should focus on cloud-penetrating algorithms, operational transfer of machine learning models to data-poor areas, and integration with climate forecast scenarios.
|
|
| Keywords: Geographic Information Systems (GIS), Remote Sensing, Preferential Fishing Zones (PFZ), Sea Surface Temperature (SST), Chlorophyll-a, Participatory Geographic Information System (PGIS) |
|
|
|
Type of Study: Research |
Subject:
Special
Received: 2026/06/16 | Accepted: 2026/09/3 | Published: 2026/09/3
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
