Spatio-temporal distribution of Gymnocypris przewalskii during migration with UAV-based photogrammetry and deep neural network

Abstract

The naked carp (Gymnocypris przewalskii) plays a central role in the ecosystem of the Qinghai Lake, the largest saline-alkaline lake in China. The adult naked carp migrates in large groups with high population density annually from the Qinghai Lake to the upstream freshwater rivers to spawn. Nevertheless, the responsiveness of the fish to local abiotic cues in the form of distribution patterns during migration across the riverine-lacustrine network of the Qinghai Lake region remains unknown. This knowledge gap has reduced efficiency in fish conservation and management efforts in the region. To address this issue, we carried out two field surveys from June to August, 2018, with the aid of unmanned aerial vehicles to a 200-m long back channel characterizing diverse morphological and hydraulic features on the migration route. Combined structure from motion photogrammetry and deep neural network techniques were used to establish a new workflow for detecting and extracting the profiles of fish individuals in large schools. The spatio-temporal distribution pattern of the fish demonstrated that the naked carp was attracted by hydraulic environments with high flow velocity or deep-water during migration. The diurnal variation of temperature and light could alter the preference for hydraulic environments of the fish. Our results highlight the crucial role of the interactions between river morphology and hydraulics, water temperature and light on the migration behaviours of the naked carp.

Keywords:

• Gymnocypris przewalskii
• fish migration
• spatio-temporal distribution
• structure from motion (SfM)
• deep neural network (DNN)
• the Qinghai Lake

Acknowledgements

We would like to thank Mr. Weiguo Zhou from the Rescue Centre of Naked Carp in Qinghai Lake for field assistance and sharing his experiences of fish conservation in the Quanji River. Qinglin Huang from Tsinghua University is kindly acknowledged for her assistance in field investigation and data processing. We also thank Lujie Han, Diran Yan, Jiarui Hai, Jinrui Wang and Chenyang Wang from Tsinghua University for their assistance in data processing. The authors thank the associate editor, Hervé Capra, and two anonymous reviewers for their comments and suggestions that significantly improved the quality of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The authors gratefully acknowledge the support of the National Natural Scientific Foundation of China (No. 51779120, 91547204) and the China Postdoctoral Science Foundation (2018M641369). Giri R Kattel would like to acknowledge the Global Talent Visiting Scholar Program and National Key Research grants (2016YFC0402900, 2016YFE0201900) at Tsinghua University.