Leveraging social media and deep learning to detect rare megafauna in video surveys

Do Whale Sharks Select for Specific Environments to Give Birth?

Neonate whale sharks < 1.5 m in length are rarely encountered, with approximately 35 sightings recorded globally between 1970 and 2020. Although potentially pregnant females seem to frequent certain sites, parturition areas are unknown, and most neonates have been sighted opportunistically in offshore environments, suggesting nursery habitat may occur in remote parts of the ocean. Here, documented accounts of neonate whale sharks with corresponding locations were mapped in relation to oceanography to identify whether there are commonalities in where they occur. Results show that locations of neonate sightings coincide with permanent oxygen minimum zones (OMZs)-with associated high surface chlorophyll-a (Chl-a) and low oxygen at depth-more often than would be expected by random chance. Two main hypotheses are proposed to explain this apparent association: (i) adult female whale sharks selectively pup in waters adjacent to low oxygen regions offering a proximate refuge from oceanic predators as well as enhanced foraging opportunities, or that (ii) pupping occurs randomly in the open ocean but that OMZs restrict neonates to shallower surface waters where they are more frequently encountered by humans than elsewhere. Testing both hypotheses requires more data on the relationship between whale shark movement ecology and dissolved oxygen concentrations. As a first step, a model predicts the highest likelihood of neonates occurring in waters above OMZs, focussed around intermediate Chl-a regions at the boundaries of highly productive upwelling systems. These areas could be the focus of future, more targeted studies. Here, biologging devices measuring in situ oxygen concentrations will be useful for exploring how different life stages interact with OMZs, which are expanding due to climate-driven deoxygenation. What this might mean for neonate whale shark conservation in future warmer oceans remains an open question.

Few-Shot Object Detection: A Comprehensive Survey

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection (FSOD) aims to learn from few object instances of new categories in the target domain. In this survey, we provide an overview of the state of the art in FSOD. We categorize approaches according to their training scheme and architectural layout. For each type of approach, we describe the general realization as well as concepts to improve the performance on novel categories. Whenever appropriate, we give short takeaways regarding these concepts in order to highlight the best ideas. Eventually, we introduce commonly used datasets and their evaluation protocols and analyze the reported benchmark results. As a result, we emphasize common challenges in evaluation and identify the most promising current trends in this emerging field of FSOD.

The analysis of ecological security and tourist satisfaction of ice-and-snow tourism under deep learning and the Internet of Things

This paper aims to propose a prediction method based on Deep Learning (DL) and Internet of Things (IoT) technology, focusing on the ecological security and tourist satisfaction of Ice-and-Snow Tourism (IST) to solve practical problems in this field. Accurate predictions of ecological security and tourist satisfaction in IST have been achieved by collecting and analyzing environment and tourist behavior data and combining with DL models, such as convolutional and recurrent neural networks. The experimental results show that the proposed method has significant advantages in performance indicators, such as accuracy, F1 score, Mean Squared Error (MSE), and correlation coefficient. Compared to other similar methods, the method proposed improves accuracy by 3.2%, F1 score by 0.03, MSE by 0.006, and correlation coefficient by 0.06. These results emphasize the important role of combining DL with IoT technology in predicting ecological security and tourist satisfaction in IST.

DiffusionFR: Species Recognition of Fish in Blurry Scenarios via Diffusion and Attention

Blurry scenarios, such as light reflections and water ripples, often affect the clarity and signal-to-noise ratio of fish images, posing significant challenges for traditional deep learning models in accurately recognizing fish species. Firstly, deep learning models rely on a large amount of labeled data. However, it is often difficult to label data in blurry scenarios. Secondly, existing deep learning models need to be more effective for the processing of bad, blurry, and otherwise inadequate images, which is an essential reason for their low recognition rate. A method based on the diffusion model and attention mechanism for fish image recognition in blurry scenarios, DiffusionFR, is proposed to solve these problems and improve the performance of species recognition of fish images in blurry scenarios. This paper presents the selection and application of this correcting technique. In the method, DiffusionFR, a two-stage diffusion network model, TSD, is designed to deblur bad, blurry, and otherwise inadequate fish scene pictures to restore clarity, and a learnable attention module, LAM, is intended to improve the accuracy of fish recognition. In addition, a new dataset of fish images in blurry scenarios, BlurryFish, was constructed and used to validate the effectiveness of DiffusionFR, combining bad, blurry, and otherwise inadequate images from the publicly available dataset Fish4Knowledge. The experimental results demonstrate that DiffusionFR achieves outstanding performance on various datasets. On the original dataset, DiffusionFR achieved the highest training accuracy of 97.55%, as well as a Top-1 accuracy test score of 92.02% and a Top-5 accuracy test score of 95.17%. Furthermore, on nine datasets with light reflection noise, the mean values of training accuracy reached a peak at 96.50%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 90.96% and 94.12%, respectively. Similarly, on three datasets with water ripple noise, the mean values of training accuracy reached a peak at 95.00%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 89.54% and 92.73%, respectively. These results demonstrate that the method showcases superior accuracy and enhanced robustness in handling original datasets and datasets with light reflection and water ripple noise.

Conserve the open media ecosystem! Legal and ethical considerations when using online repositories for AI training in ecological research

Ecological researchers who train Artificial Intelligence models using digital media have to be cognizant of legal and ethical implications when sourcing such content from online repositories. The way forward? Complying with Creative Commons licensing requirements, obtaining consent from media creators and adhering to FAIR data principles. Collective action from researchers, repositories, licence providers, and legislators is needed to conserve this complex open media ecosystem. This way, we can continue to develop innovative applications to address pressing ecological issues while maintaining the trust of content creators and respecting the legal and ethical framework of online media use.