Israel Oceanographic & Limnologic Research - Israel Marine Data Center (ISRAMAR)
Skip Navigation Links
Skip Navigation Links
Development of an Automated Real-Time Intelligent Information System for Early Warning and Preparedness of Offshore Oil and Gas Operations off the Coast of Israel — DARTIS

DARTIS was a German-Israeli Cooperation in Marine Sciences funded jointly by the Ministry of Science & Technology (MOST, Israel) and the Federal Ministry of Education & Research (BMBF, Germany) during 2018–2022. The cooperating teams

The project aims were to improve forecasting capabilities in maritime safety, particularly improving wave forecasts and oil spill response, with advanced technological and scientific methods in modelling, remote sensing, and artificial intelligence.

Pre-operational wave models developed in the project

Different approaches were developed during the project to improve or enhance the forecast of IOLR's SWAN model. These include data assimilation, deep learning, and neural network - model hybrids techniques. The following preoperational systems were created:

SWAN - 4DVar This SWAN based model assimilates wave observations from IOLR near-real-time stations and Copernicus wave observations. The model runs a 24-hour analysis that uses the 4DVar scheme to find the best correction to the wind field. The analysis serves as initial conditions to the forecast delivered here.
Neural nework-based wave model This forecasting system was generated with deep convolution neural network techniques. Encoder/decoder pairs were created and trained for the SKIRON wind forecast and the SWAN wave forecast. An artificial neural network was trained to emulate the 4DVar analysis in the encoded space. The system combined the components to create a complete neural network-based system.
SWAN - wind factor This SWAN-based system implements an artificial neural network to modify the wind input used by the SWAN model. The network was trained to emulate the results of the 4DVar system and is based on the SKIRON encoder.
HaderaANN This neural network-based system provides 24 hours forecast for the significant wave height at Hadera. The system uses SKIRON winds, SWAN forecast, and recent observations to create a forecast, which is updated hourly.
Automated oil spill detection developed in the project

With wide coverage and the capability of monitoring at night and during cloudy weather, Synthetic Aperture Radar (SAR) is suitable for setting up an oil spill early warning system. However, many other phenomena appear as dark formations in SAR, which are so-called ‘look-alikes’ issues, and make it challenging to distinguish themselves from oil spills.

In the general procedure of detecting oil spills from the previous studies, all the dark formations in the images are segmented, and their features are extracted for classifying whether they are oil spills or look-alikes. However, the segmentation separates the dark formations from their surrounding areas and, at the same time, discards the information of how they are different from their surroundings. Therefore, we invented a different approach for automated detection of oil spills in this project. Oil spills in SAR images are directly detected and defined with bounding boxes by an object detector, which was trained on a large manual inspected oil spills dataset. The exact areas covered by oil spills are then obtained from the segmentation method.

Most of the previous studies for oil spill detection focused on large oil spill events. However, for an operational service, targeting smaller oil spills is also important as they occur regularly in this area. With the system built in this project, the detections are not limited to large oil spills. Oil spills could be detected as long as there are oil spills with similar patterns or features in the training dataset. During the project, a training dataset of 9768 manually detected oil spills was created from SAR images of the southeastern Levantine in 2015–2018. This dataset was used to train the YOLOv4 object detector.

Usually, oil spill detection requires a lot of human work on manual inspection. An automated oil spill detection system can provide detected oil spills for the manual inspector to confirm, in this way, the total time on human work can be reduced.

Detections are automatically sent to ISRAMAR system to create a forward trajectory forecast in a dedicated interface. The service is currently in testing and is restricted. Some screenshots are available here.

scheme of the joint oil detection and forecasting system

schme of the joint oil detection and forecasting system

© Israel Oceanographic & Limnological Research. All Rights Reserved      Terms of Use     About Us
© כל הזכויות שמורות. אין לעשות שימוש בנתונים ללא אישור בכתב מחיא"ל