Artificial Intelligence for Climate Change Biology: From Data Collection to Predictions

Integrative and Comparative Biology, Journal Year: 2024, Volume and Issue: 64(3), P. 953 - 974

Published: July 30, 2024

Synopsis In the era of big data, ecological research is experiencing a transformative shift, yet big-data advancements in thermal ecology and study animal responses to climate conditions remain limited. This review discusses how data analytics artificial intelligence (AI) can significantly enhance our understanding microclimates behaviors under changing climatic conditions. We explore AI’s potential refine microclimate models analyze from advanced sensors camera technologies, which capture detailed, high-resolution information. integration allow researchers dissect complex physiological processes with unprecedented precision. describe AI modeling through improved bias correction downscaling techniques, providing more accurate estimates that animals face various scenarios. Additionally, we capabilities tracking these conditions, particularly innovative classification utilize such as accelerometers acoustic loggers. For example, widespread usage traps benefit AI-driven image accurately identify thermoregulatory responses, shade panting. therefore instrumental monitoring interact their environments, offering vital insights into adaptive behaviors. Finally, discuss data-driven approaches inform conservation strategies. particular, detailed mapping microhabitats essential for species survival adverse guide design climate-resilient restoration programs prioritize habitat features crucial biodiversity resilience. conclusion, convergence AI, science heralds new precision conservation, addressing global environmental challenges 21st century.

Language: Английский

---

Smart camera traps and computer vision improve detections of small fauna

Ecosphere, Journal Year: 2025, Volume and Issue: 16(3)

Published: March 1, 2025

Abstract Limited data on species' distributions are common for small animals, impeding conservation and management. Small especially ectothermic taxa, often difficult to detect, therefore require increased time resources survey effectively. The rise of technology has enabled researchers monitor animals in a range ecosystems longer periods than traditional methods (e.g., live trapping), increasing the quality cost‐effectiveness wildlife monitoring practices. We used DeakinCams, custom‐built smart camera traps, address three aims: (1) To including ectotherms, evaluate performance customized computer vision object detector trained SAWIT dataset automating classification; (2) At same field sites using commercially available we evaluated how well MegaDetector—a freely detection model—detected images containing animals; (3) complementarity these two different approaches monitoring. collected 85,870 videos from DeakinCams 50,888 commercial cameras. For with data, yielded 98% Precision but 47% recall, species classification, varied by 0% Recall birds 26% 14% spiders. detections trap images, MegaDetector returned 99% Recall. found that only detected nocturnal ectotherms invertebrates. Making use more diverse datasets training models as advances machine learning will likely improve like YOLO novel environments. Our results support need continued cross‐disciplinary collaboration ensure large environmental train test existing emerging algorithms.

Language: Английский

---

Assessing the impacts of recreation on the spatial and temporal activity of mammals in an isolated alpine protected area

Ecology and Evolution, Journal Year: 2023, Volume and Issue: 13(11)

Published: Nov. 1, 2023

The management objectives of many protected areas must meet the dual mandates protecting biodiversity while providing recreational opportunities. It is difficult to balance these because it takes considerable effort monitor both status and impacts recreation. Using detections from 45 camera traps deployed between July 2019 September 2021, we assessed potential recreation on spatial temporal activity for 8 medium- large-bodied terrestrial mammals in an isolated alpine area: Cathedral Provincial Park, British Columbia, Canada. We hypothesised that some wildlife perceive a level threat people, such they avoid 'risky times' or places' associated with human activity. Other species may benefit associating be through access anthropogenic resource subsidies filtering competitors/predators are more human-averse (i.e., shield hypothesis). Specifically, predicted large carnivores would show greatest segregation people mesocarnivores ungulates associate spatially people. found co-occurrence recreation, consistent hypothesis, but did not see negative relationship larger humans, except coyotes (Canis latrans). Temporally, all other than cougars (Puma concolor) had diel patterns significantly different recreationists, suggesting displacement niche. Wolves lupus) mountain goats (Oreamnos americanus) showed shifts away trails relative off-trail areas, further evidence displacement. Our results highlight importance monitoring interactions activities communities, order ensure effectiveness era increasing impacts.

Language: Английский

---

A versatile, semi-automated image analysis workflow for time-lapse camera trap image classification

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102578 - 102578

Published: March 26, 2024

Camera traps are a powerful, practical, and non-invasive method used widely to monitor animal communities evaluate management actions. However, camera trap arrays can generate thousands millions of images that require significant time effort review. Computer vision has emerged as tool accelerate this image review process. We propose multi-step, semi-automated workflow which takes advantage site-specific generalizable models improve detections consists (1) automatically identifying removing low-quality in parallel with classification into animals, humans, vehicles, empty, (2) cropping objects from classifying them (rock, bait, species), (3) manually inspecting subset images. trained evaluated approach using 548,627 46 cameras two regions the Arctic: "Finnmark" (Finnmark County, Norway) "Yamal" (Yamalo-Nenets Autonomous District, Russia). The automated steps yield accuracies 92% 90% for Finnmark Yamal sets, respectively, reducing number required manual inspection 9.2% set 3.9% set. amount invested developing would be offset by saved automation after 960 thousand have been processed. Researchers modify multi-step process develop their own meet other needs monitoring surveying wildlife, balancing acceptable levels false negatives positives.

Language: Английский

---

Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings

Frontiers in Remote Sensing, Journal Year: 2024, Volume and Issue: 5

Published: April 25, 2024

Studying marine soundscapes by detecting known sound events and quantifying their spatio-temporal patterns can provide ecologically relevant information. However, the exploration of underwater data to find identify possible interest be highly time-intensive for human analysts. To speed up this process, we propose a novel methodology that first detects all potentially acoustic then clusters them in an unsupervised way prior manual revision. We demonstrate its applicability on short deployment. detect events, deep learning object detection algorithm from computer vision (YOLOv8) is re-trained any (short) event. This done converting audio spectrograms using sliding windows longer than expected interest. The model event present window provides time frequency limits. With approach, multiple happening simultaneously detected. further explore possibilities limit input needed create annotations train model, active approach select most informative files iterative manner subsequent annotation. obtained models are trained tested dataset Belgian Part North Sea, evaluated robustness freshwater major European rivers. proposed outperforms random selection files, both datasets. Once detected, they converted embedded feature space BioLingual which classify different (biological) sounds. representations clustered way, obtaining classes. These classes manually revised. method applied unseen as tool help bioacousticians recurrent sounds save when studying patterns. reduces researchers need go through long recordings allows conduct more targeted analysis. It also framework monitor regardless whether sources or not.

Language: Английский

---