Browsing by Author "Mcilwaine, Ben"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Investigating optimal unmanned aircraft systems flight plans for the detection of marine ingress
    (Elsevier, 2022-03-08) Mcilwaine, Ben; Rivas Casado, Monica; Waine, Toby
    From the shutting down of coastal tourism industries, the mass destruction of aquaculture, to the clogging of power station water intakes, marine ingress events have the potential to cause widespread disruption along our coastlines. To gain the ability to respond to such events, efforts are being made to advance the understanding of bloom events which predominantly present as large aggregations of jellyfish, or detached aquatic macroalgaes in the water column. This paper investigates the optimal flight search patterns with a focus on marine ingress bloom detection from unmanned aircraft systems (UAS). The detection performance of four flight search patterns are examined against five different bloom shapes. Monte-Carlo simulations are deployed to assess probable performance of flight search pattern against variable bloom shapes. A total of 50,000 simulated flights were conducted, offering a maximum of 500 million marine ingress objects for possible detection. A two phased flight approach is proposed, with first phase flights conducted as area search strategies, and second phase flights as datum searches for scenarios where some information of possible bloom location is available. Parallel sweep was found to be the best performing generalist flight search pattern, closely followed by the phase two search pattern expanding square. Crossing barrier was found to be competitive but appeared to lend itself towards specific detection scenarios with sector search being a consistently poor performing flight search pattern. This paper also investigates the comparative performance of visual line of sight (VLOS), extended visual line of sight (EVLOS), and beyond visual line of sight (BVLOS) operations. Increase of total survey area was found to increase bloom detection frequency, with BVLOS operations the highest performer successfully increasing bloom detection by a factor of 3.7. This paper exhibits the first assessment of flight search patterns within the context of drone-based detection of marine ingress bloom events. This should facilitate the development of an early warning detection system that can provide reliable warning to coastal industries prior to a marine ingress event occurring.
  • Thumbnail Image
    ItemOpen Access
    JellyNet: The convolutional neural network jellyfish bloom detector
    (Elsevier, 2021-01-21) Mcilwaine, Ben; Rivas Casado, Monica
    Coastal industries face disruption on a global scale due to the threat of large blooms of jellyfish. They can decimate coastal fisheries and clog the water intake systems of desalination and nuclear power plants. This can lead to losses of revenue and power output. This paper presents JellyNet: a convolutional neural network (CNN) jellyfish bloom detection model trained on high resolution remote sensing imagery collected by unmanned aerial vehicles (UAVs). JellyNet provides the detection capability for an early (6–8 h) bloom warning system. 1539 images were collected from flights at 2 locations: Croabh Haven, UK and Pruth Bay, Canada. The training/test dataset was manually labelled, and split into two classes: ‘Bloom present’ and ‘No bloom present’. 500 × 500 pixel images were used to increase fine-grained pattern detection of the jellyfish blooms. Model testing was completed using a 75/25% training/test split with hyperparameters selected prior to model training using a held-out validation dataset. Transfer learning using VGG-16 architecture, and a jellyfish bloom specific binary classifier surpassed an accuracy of 90%. Test model performance peaked at 97.5% accuracy. This paper exhibits the first example of a high resolution, multi-sensor jellyfish bloom detection capability, with integrated robustness from two oceans to tackle real world detection challenges.
  • Thumbnail Image
    ItemOpen Access
    Using 1st derivative reflectance signatures within a remote sensing framework to identify macroalgae in marine environments
    (MDPI, 2019-03-23) Mcilwaine, Ben; Rivas Casado, Monica; Leinster, Paul
    Macroalgae blooms (MABs) are a global natural hazard that are likely to increase in occurrence with climate change and increased agricultural runoff. MABs can cause major issues for indigenous species, fish farms, nuclear power stations, and tourism activities. This project focuses on the impacts of MABs on the operations of a British nuclear power station. However, the outputs and findings are also of relevance to other coastal operators with similar problems. Through the provision of an early-warning detection system for MABs, it should be possible to minimize the damaging effects and possibly avoid them altogether. Current methods based on satellite imagery cannot be used to detect low-density mobile vegetation at various water depths. This work is the first step towards providing a system that can warn a coastal operator 6–8 h prior to a marine ingress event. A fundamental component of such a warning system is the spectral reflectance properties of the problematic macroalgae species. This is necessary to optimize the detection capability for the problematic macroalgae in the marine environment. We measured the reflectance signatures of eight species of macroalgae that we sampled in the vicinity of the power station. Only wavelengths below 900 nm (700 nm for similarity percentage (SIMPER)) were analyzed, building on current methodologies. We then derived 1st derivative spectra of these eight sampled species. A multifaceted univariate and multivariate approach was used to visualize the spectral reflectance, and an analysis of similarities (ANOSIM) provided a species-level discrimination rate of 85% for all possible pairwise comparisons. A SIMPER analysis was used to detect wavebands that consistently contributed to the simultaneous discrimination of all eight sampled macroalgae species to both a group level (535–570 nm), and to a species level (570–590 nm). Sampling locations were confirmed using a fixed-wing unmanned aerial vehicle (UAV), with the collected imagery being used to produce a single orthographic image via standard photogrammetric processes. The waveband found to contribute consistently to group-level discrimination has previously been found to be associated with photosynthetic pigmentation, whereas the species-level discriminatory waveband did not share this association. This suggests that the photosynthetic pigments were not spectrally diverse enough to successfully distinguish all eight species. We suggest that future work should investigate a Charge-Coupled Device (CCD)-based sensor using the wavebands highlighted above. This should facilitate the development of a regional-scale early-warning MAB detection system using UAVs, and help inform optimum sensor filter selection. -