Related Experiment Video
Updated: May 7, 2026
09:32
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
Published on: November 20, 2017
9.4K
Applying Deep Learning to Quantify Drivers of Long-Term Ecological Change in a Swedish Marine Protected Area
Christian L Nilsson1,2, Søren Faurby2,3, Emil Burman1,2
1Department of Marine Sciences University of Gothenburg Gothenburg Sweden.
Ecology and Evolution
|September 4, 2025
Summary
An AI model analyzed marine life in Kosterhavet National Park, revealing shifts in benthic invertebrate communities. Warmer temperatures are driving changes, with smaller, heat-tolerant species increasing in abundance.
Area of Science:
- Marine Ecology
- Artificial Intelligence in Ecology
- Conservation Science
Background:
- Kosterhavet National Park, Sweden, is a marine protected area with historical video footage dating back to 1997.
- Benthic invertebrate communities are crucial indicators of marine ecosystem health.
- Understanding long-term ecological changes requires robust data collection and analysis methods.
Purpose of the Study:
- To develop and apply an object-detection model for classifying benthic invertebrates in archived underwater video footage.
- To generate a comprehensive dataset of occurrence records for 17 benthic invertebrate taxa from 1997 to 2023.
- To analyze depth distributions and abundance trends of benthic taxa and functional groups to identify ecological shifts.
Main Methods:
- Training an object-detection model with a mean average precision of 0.738 to classify 17 benthic invertebrate taxa.
- Applying the trained model to archived video footage (1997-2023) to create a dataset of 72,369 occurrence records.
- Quantifying depth distributions and temporal abundance trends, and correlating these with environmental factors like temperature.
Main Results:
- Depth distributions were established for 15 of 17 taxa at depths ≥ 45m, with proposed expansions for six taxa.
- Significant abundance increases were observed for eight taxa and decreases for five taxa.
- Community structure shifted towards smaller, heat-tolerant suspension feeders, with large, heat-sensitive taxa migrating to deeper waters.
Conclusions:
- Temperature preference and organism size are key drivers of observed abundance trends in benthic invertebrates.
- The Kosterhavet National Park's protective measures are effective, as evidenced by increasing abundances of sensitive taxa.
- Recommendations include expanding fishery regulations to deeper waters and establishing new deep-water marine protected areas to conserve cold-water species.
Keywords:
deep learninghard‐substrate communitieslong‐term ecological trendsmarine protected areas (MPAs)object detection modelsvideo‐based biodiversity monitoringMore Related Videos
05:57Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
Published on: April 8, 2019
6.9K
09:19Measuring the Structure, Composition, and Change of Underwater Environments with Large-area Imaging
Published on: April 18, 2025
799
Related Concept Videos
02:04Conservation of Small Populations
Small population sizes put a species at extreme risk of extinction due to a lack of variation, and a consequent decrease in adaptability. This weakens the chances of survival under pressures such as climate change, competition from other species, or new diseases. Large populations are more likely to survive pressures such as these, as such populations are more likely to harbor individuals that have genetic variants that are adaptive under new stresses. Small populations are much less likely to...
02:07Conservation of Declining Populations
Conservation of declining population focuses on ways of detecting, diagnosing, and halting a population decline. The approach uses methods to prevent populations from going extinct.
01:30Marine Microbial Ecology
Marine microbial ecosystems are shaped by distinct physicochemical limits, including high salinity, low nutrient availability, and fluctuating oxygen levels. These conditions favor smaller microbial cell sizes, which maximize their surface-to-volume ratio for efficient nutrient uptake.Microbial activity and community composition are closely linked to biogeochemical cycles, particularly in dynamic environments like estuaries, where halotolerant microbes thrive in response to variable salinity...
01:18Deep Sea Microbial Ecology
The deep ocean and its underlying sediments represent vast, largely unexplored microbial habitats that extend far beyond the sunlit photic zone. The photic (euphotic) zone typically spans the upper ~100–200 meters of pelagic waters in the open ocean, but its depth varies geographically and seasonally, where sufficient light supports photosynthetic life. Below this lies the deep sea, spanning roughly 1000–6000 meters (bathypelagic to abyssal zones), with deeper hadal trenches extending beyond...
01:24Freshwater Microbial Ecology
Freshwater systems such as streams, rivers, and lakes exhibit distinct physical and biological characteristics that influence their microbial communities. These environments are broadly categorized into lotic systems—those with flowing waters like streams and most rivers—and lentic systems, which include still or slow-moving waters such as lakes, ponds, and marshes.In lentic systems, phytoplankton drive primary production, generating autochthonous organic carbon. In contrast, lotic systems...