@conference {, title = {A Cloud Computing Architecture to Map Trawling Activities Using Positioning Data}, year = {2019}, abstract = {

Descriptive and spatially-explicit information on fisheries plays a key role for an efficient integrated management of the maritime activities and the sustainable use of marine resources. However, this information is today still hard to obtain and, consequently, is a major issue for implementing Marine Spatial Planning (MSP). Since 2002, the Automatic Identification System (AIS) has been undergoing a major development allowing now for a real time geo-tracking and identification of equipped vessels of more than 15m in length overall (LOA) and, if properly processed, for the production of adequate information for MSP. Such monitoring systems or other low-cost and low-burden solutions are still missing for small vessels (LOA \< 12m), whose catches and fishing effort remain spatially unassessed and, hence, unregulated. In this context, we propose an architecture to process vessel tracking data, understand the behaviour of trawling fleets and map related fishing activities. It could be used to process not only AIS data but also positioning data from other low cost systems as IoT sensors that share their position over LoRa and 2G/3G/4G links. Analysis gives back important and verified data (overall accuracy of 92\% for trawlers) and opens up development perspectives for monitoring small scale fisheries, helping hence to fill fishery data gaps and obtain a clearer picture of the fishing grounds as a whole.

}, doi = {10.1115/DETC2019-97779}, url = {https://doi.org/10.1115/DETC2019-97779}, author = {Alessandro Galdelli and Adriano Mancini and Anna Nora Tassetti and Carmen Ferra Vega and Enrico Armelloni and Giuseppe Scarcella and Gianna Fabi and Primo Zingaretti} }