Monitoring fish stocks and fleets’ activities is key for Marine Spatial Planning. In recent years Vessel Monitoring System and Automatic Identification System have been developed for vessels longer than 12 and 15m in length, respectively, while small scale vessels (< 12m in length) remain untracked and largely unregulated, even though they account for 83% of all fishing activity in the Mediterranean Sea. In this paper we present an architecture that makes use of a low-cost LoRa/cellular network to acquire and process positioning data from small scale vessels, and a feature encoding approach that can be easily extended to process and map small scale fisheries. The feature encoding method uses a Markov chain to model transitions between successive behavioural states (e.g., fishing, steaming) of each vessel and classify its activity. The approach is evaluated using k-fold and Leave One Boat Out cross-validations and, in both cases, it results in significant improvements in the classification of fishing activities. The use of a such low-cost and open source technology coupled to artificial intelligence could open up potential for more integrated and transparent platforms to inform coastal resource and fisheries management, and cross-border marine spatial planning. It enables a new monitoring strategy that could effectively include small-scale fleets and support the design of new policies oriented to the optimal use of marine resources.

A Feature Encoding Approach and a Cloud Computing Architecture to Map Fishing Activities / Galdelli, A.; Tassetti, A. N.; Mancini, A.; Frontoni, E.. - ELETTRONICO. - 7:(2021). (Intervento presentato al convegno 17th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA) tenutosi a Virtual, Online nel August 17–19, 2021) [10.1115/DETC2021-69799].

A Feature Encoding Approach and a Cloud Computing Architecture to Map Fishing Activities

A. Galdelli
Primo
Writing – Original Draft Preparation
;
A. N. Tassetti
Writing – Review & Editing
;
A. Mancini
Supervision
;
E. Frontoni
Supervision
2021-01-01

Abstract

Monitoring fish stocks and fleets’ activities is key for Marine Spatial Planning. In recent years Vessel Monitoring System and Automatic Identification System have been developed for vessels longer than 12 and 15m in length, respectively, while small scale vessels (< 12m in length) remain untracked and largely unregulated, even though they account for 83% of all fishing activity in the Mediterranean Sea. In this paper we present an architecture that makes use of a low-cost LoRa/cellular network to acquire and process positioning data from small scale vessels, and a feature encoding approach that can be easily extended to process and map small scale fisheries. The feature encoding method uses a Markov chain to model transitions between successive behavioural states (e.g., fishing, steaming) of each vessel and classify its activity. The approach is evaluated using k-fold and Leave One Boat Out cross-validations and, in both cases, it results in significant improvements in the classification of fishing activities. The use of a such low-cost and open source technology coupled to artificial intelligence could open up potential for more integrated and transparent platforms to inform coastal resource and fisheries management, and cross-border marine spatial planning. It enables a new monitoring strategy that could effectively include small-scale fleets and support the design of new policies oriented to the optimal use of marine resources.
2021
978-0-7918-8543-7
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/307043
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? ND
social impact