Automatic detection of migrating soaring bird flocks using weather radars by deep learning
Abstract The use of weather radars to detect and distinguish between different biological patterns greatly improves our understanding of aeroecology and its consequences for our lives. Importantly, it allows us to quantify passerine bird migration at different scales. Yet, no algorithm to detect soa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-08-01
|
| Series: | Methods in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/2041-210X.14161 |
| _version_ | 1827882661293588480 |
|---|---|
| author | Inbal Schekler Tamir Nave Ilan Shimshoni Nir Sapir |
| author_facet | Inbal Schekler Tamir Nave Ilan Shimshoni Nir Sapir |
| author_sort | Inbal Schekler |
| collection | DOAJ |
| description | Abstract The use of weather radars to detect and distinguish between different biological patterns greatly improves our understanding of aeroecology and its consequences for our lives. Importantly, it allows us to quantify passerine bird migration at different scales. Yet, no algorithm to detect soaring bird flocks in weather radar is available, precluding our ability to study this type of migration over large spatial scales. We developed the first automatic algorithm for detecting the migration of flocks of soaring birds, an important bio‐flow phenomenon involving many millions of birds that travel across large spatial extents, with implications for risk of bird‐aircraft collisions. The algorithm was developed with a deep learning network for semantic segmentation using U‐Net architecture. We tested several models with different weather radar products and with image sequences for flock movement identification. The best model includes the radial velocity product and a sequence of two previous images. It identifies 93% of soaring bird flocks that were tagged by a human on the radar image, with a false discovery of less than 20%. Large birds such as those detected by the algorithm pose a serious risk for flight safety of civilian and military transportation and therefore the application of this algorithm can substantially reduce bird‐strikes, leading to reduced financial losses and threats to human lives. In addition, it can help overcome one of the main challenges in the study of bird migration by automatically and continuously detecting flocks of large birds over wide spatial scales without the need to equip the birds with tracking devices, unravelling the abundance, timing, spatial flyways, seasonal trends and influences of environmental conditions on the migration of bird flocks. |
| first_indexed | 2024-03-12T19:00:56Z |
| format | Article |
| id | doaj.art-04ed3bfa79f9408cab5963a74fcfa4ab |
| institution | Directory Open Access Journal |
| issn | 2041-210X |
| language | English |
| last_indexed | 2024-03-12T19:00:56Z |
| publishDate | 2023-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Methods in Ecology and Evolution |
| spelling | doaj.art-04ed3bfa79f9408cab5963a74fcfa4ab2023-08-02T06:34:44ZengWileyMethods in Ecology and Evolution2041-210X2023-08-011482084209410.1111/2041-210X.14161Automatic detection of migrating soaring bird flocks using weather radars by deep learningInbal Schekler0Tamir Nave1Ilan Shimshoni2Nir Sapir3Department of Evolutionary and Environmental Biology and Institute of Evolution University of Haifa Haifa IsraelALGOFEK Kiryat Ono IsraelDepartment of Information Systems University of Haifa Haifa IsraelDepartment of Evolutionary and Environmental Biology and Institute of Evolution University of Haifa Haifa IsraelAbstract The use of weather radars to detect and distinguish between different biological patterns greatly improves our understanding of aeroecology and its consequences for our lives. Importantly, it allows us to quantify passerine bird migration at different scales. Yet, no algorithm to detect soaring bird flocks in weather radar is available, precluding our ability to study this type of migration over large spatial scales. We developed the first automatic algorithm for detecting the migration of flocks of soaring birds, an important bio‐flow phenomenon involving many millions of birds that travel across large spatial extents, with implications for risk of bird‐aircraft collisions. The algorithm was developed with a deep learning network for semantic segmentation using U‐Net architecture. We tested several models with different weather radar products and with image sequences for flock movement identification. The best model includes the radial velocity product and a sequence of two previous images. It identifies 93% of soaring bird flocks that were tagged by a human on the radar image, with a false discovery of less than 20%. Large birds such as those detected by the algorithm pose a serious risk for flight safety of civilian and military transportation and therefore the application of this algorithm can substantially reduce bird‐strikes, leading to reduced financial losses and threats to human lives. In addition, it can help overcome one of the main challenges in the study of bird migration by automatically and continuously detecting flocks of large birds over wide spatial scales without the need to equip the birds with tracking devices, unravelling the abundance, timing, spatial flyways, seasonal trends and influences of environmental conditions on the migration of bird flocks.https://doi.org/10.1111/2041-210X.14161bird migrationconvolutional neural networksdeep learningflight safetysoaring birdsU‐Net |
| spellingShingle | Inbal Schekler Tamir Nave Ilan Shimshoni Nir Sapir Automatic detection of migrating soaring bird flocks using weather radars by deep learning Methods in Ecology and Evolution bird migration convolutional neural networks deep learning flight safety soaring birds U‐Net |
| title | Automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| title_full | Automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| title_fullStr | Automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| title_full_unstemmed | Automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| title_short | Automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| title_sort | automatic detection of migrating soaring bird flocks using weather radars by deep learning |
| topic | bird migration convolutional neural networks deep learning flight safety soaring birds U‐Net |
| url | https://doi.org/10.1111/2041-210X.14161 |
| work_keys_str_mv | AT inbalschekler automaticdetectionofmigratingsoaringbirdflocksusingweatherradarsbydeeplearning AT tamirnave automaticdetectionofmigratingsoaringbirdflocksusingweatherradarsbydeeplearning AT ilanshimshoni automaticdetectionofmigratingsoaringbirdflocksusingweatherradarsbydeeplearning AT nirsapir automaticdetectionofmigratingsoaringbirdflocksusingweatherradarsbydeeplearning |