Ecosystems globally have reached critical tipping points because of climate change, urbanization, unsustainable resource consumption, and pollution. In response, international agreements have set targets for conserving 30% of global ecosystems and restoring 30% of degraded lands and waters by 2030 (30×30). In 2021, the United States set a target to jointly conserve and restore 30% of US lands and waters by 2030, with a specific goal to restore coastal ecosystems, namely wetlands, seagrasses, coral and oyster reefs, and mangrove and kelp forests, to increase resilience to climate change.
View Article and Find Full Text PDFGiant kelp and bull kelp forests are increasingly at risk from marine heatwave events, herbivore outbreaks, and the loss or alterations in the behavior of key herbivore predators. The dynamic floating canopy of these kelps is well-suited to study via satellite imagery, which provides high temporal and spatial resolution data of floating kelp canopy across the western United States and Mexico. However, the size and complexity of the satellite image dataset has made ecological analysis difficult for scientists and managers.
View Article and Find Full Text PDFThe recent collapse of predatory sunflower sea stars () owing to sea star wasting disease (SSWD) is hypothesized to have contributed to proliferation of sea urchin barrens and losses of kelp forests on the North American west coast. We used experiments and a model to test whether restored populations may help recover kelp forests through their consumption of nutritionally poor purple sea urchins () typical of barrens. consumed 0.
View Article and Find Full Text PDFAdvances in artificial intelligence for computer vision hold great promise for increasing the scales at which ecological systems can be studied. The distribution and behavior of individuals is central to ecology, and computer vision using deep neural networks can learn to detect individual objects in imagery. However, developing supervised models for ecological monitoring is challenging because it requires large amounts of human-labeled training data, requires advanced technical expertise and computational infrastructure, and is prone to overfitting.
View Article and Find Full Text PDF