Browsing by Author "Marquez, L."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- A general survey of the feasibility of culturing the mysid Gastrosaccus roscoffensis (Peracarida, Mysida): growth, survival, predatory skills, and lipid compositionPublication . Escanez, A.; Riere, R.; Marquez, L.; Skalli, A.; Felipe, B. C.; Garcia-Herrero, I.; Reis, D.; Rodriguez, C.; Almansa, E.The effects of culture conditions on growth, survival, predation, and nutritional composition of the mysid Gastrosaccus roscoffensis were studied. Light had a negative effect on the predation rates of G roscoffensis and predator size was important to prey on Artemia nauplii and rotifers (Brachionus plicatilis). Growth rates were higher in the first three weeks and measured individuals increased almost 7 mm in length in six weeks. Mortality rate was not constant, but it peaked during the first 10 days and after the 40th day of culture. Lipid class composition of cultured G. roscoffensis juveniles showed differences compared to wild G roscoffensis and other mysid species, with a high proportion of neutral lipids (72.04% total lipids) mainly triacylglycerol (41.74%). Fatty acid composition was characterized by high levels of 18:3n-3 (23.16% total lipids) and monoenes in cultured G. roscoffensis. The experiments demonstrated the feasibility of the culturing conditions assayed for G roscoffensis, although further experiments should be carried out to test this mysid as a prey for new species of commercial interest, including fish and cephalopods.
- Artificial intelligence convolutional neural networks map giant kelp forests from satellite imageryPublication . Marquez, L.; Fragkopoulou, Eliza; Cavanaugh, K. C.; Houskeeper, H. F.; Assis, J.Climate change is producing shifts in the distribution and abundance of marine species. Such is the case of kelp forests, important marine ecosystem-structuring species whose distributional range limits have been shifting worldwide. Synthesizing long-term time series of kelp forest observations is therefore vital for understanding the drivers shaping ecosystem dynamics and for predicting responses to ongoing and future climate changes. Traditional methods of mapping kelp from satellite imagery are time-consuming and expensive, as they require high amount of human effort for image processing and algorithm optimization. Here we propose the use of mask region-based convolutional neural networks (Mask R-CNN) to automatically assimilate data from open-source satellite imagery (Landsat Thematic Mapper) and detect kelp forest canopy cover. The analyses focused on the giant kelp Macrocystis pyrifera along the shorelines of southern California and Baja California in the northeastern Pacific. Model hyper-parameterization was tuned through cross-validation procedures testing the effect of data augmentation, and different learning rates and anchor sizes. The optimal model detected kelp forests with high performance and low levels of overprediction (Jaccard's index: 0.87 +/- 0.07; Dice index: 0.93 +/- 0.04; over prediction: 0.06) and allowed reconstructing a time series of 32 years in Baja California (Mexico), a region known for its high variability in kelp owing to El Nino events. The proposed framework based on Mask R-CNN now joins the list of cost-efficient tools for long-term marine ecological monitoring, facilitating well-informed biodiversity conservation, management and decision making.