Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model
Weather radar data can capture large-scale bird migration information, helping solve a series of migratory ecological problems. However, extracting and identifying bird information from weather radar data remains one of the challenges of radar aeroecology. In recent years, deep learning was applied...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/24/4998 |
| _version_ | 1797501050140229632 |
|---|---|
| author | Shuaihang Wang Cheng Hu Kai Cui Rui Wang Huafeng Mao Dongli Wu |
| author_facet | Shuaihang Wang Cheng Hu Kai Cui Rui Wang Huafeng Mao Dongli Wu |
| author_sort | Shuaihang Wang |
| collection | DOAJ |
| description | Weather radar data can capture large-scale bird migration information, helping solve a series of migratory ecological problems. However, extracting and identifying bird information from weather radar data remains one of the challenges of radar aeroecology. In recent years, deep learning was applied to the field of radar data processing and proved to be an effective strategy. This paper describes a deep learning method for extracting biological target echoes from weather radar images. This model uses a two-stream CNN (Atrous-Gated CNN) architecture to generate fine-scale predictions by combining the key modules such as squeeze-and-excitation (SE), and atrous spatial pyramid pooling (ASPP). The SE block can enhance the attention on the feature map, while ASPP block can expand the receptive field, helping the network understand the global shape information. The experiments show that in the typical historical data of China next generation weather radar (CINRAD), the precision of the network in identifying biological targets reaches up to 99.6%. Our network can cope with complex weather conditions, realizing long-term and automated monitoring of weather radar data to extract biological target information and provide feasible technical support for bird migration research. |
| first_indexed | 2024-03-10T03:12:45Z |
| format | Article |
| id | doaj.art-853f1151d17542b9bb827cbac830c0c6 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:12:45Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-853f1151d17542b9bb827cbac830c0c62023-11-23T10:23:24ZengMDPI AGRemote Sensing2072-42922021-12-011324499810.3390/rs13244998Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning ModelShuaihang Wang0Cheng Hu1Kai Cui2Rui Wang3Huafeng Mao4Dongli Wu5School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaAdvanced Technology Research Institute, Beijing Institute of Technology, Jinan 250300, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Information and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaThe Meteorological Observation Center of China Meteorological Administration, Beijing 100081, ChinaWeather radar data can capture large-scale bird migration information, helping solve a series of migratory ecological problems. However, extracting and identifying bird information from weather radar data remains one of the challenges of radar aeroecology. In recent years, deep learning was applied to the field of radar data processing and proved to be an effective strategy. This paper describes a deep learning method for extracting biological target echoes from weather radar images. This model uses a two-stream CNN (Atrous-Gated CNN) architecture to generate fine-scale predictions by combining the key modules such as squeeze-and-excitation (SE), and atrous spatial pyramid pooling (ASPP). The SE block can enhance the attention on the feature map, while ASPP block can expand the receptive field, helping the network understand the global shape information. The experiments show that in the typical historical data of China next generation weather radar (CINRAD), the precision of the network in identifying biological targets reaches up to 99.6%. Our network can cope with complex weather conditions, realizing long-term and automated monitoring of weather radar data to extract biological target information and provide feasible technical support for bird migration research.https://www.mdpi.com/2072-4292/13/24/4998China next generation weather radar (CINRAD)atrous-gated CNNsqueeze-and-excitation (SE)atrous spatial pyramid pooling (ASPP)extract biological target information |
| spellingShingle | Shuaihang Wang Cheng Hu Kai Cui Rui Wang Huafeng Mao Dongli Wu Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model Remote Sensing China next generation weather radar (CINRAD) atrous-gated CNN squeeze-and-excitation (SE) atrous spatial pyramid pooling (ASPP) extract biological target information |
| title | Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model |
| title_full | Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model |
| title_fullStr | Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model |
| title_full_unstemmed | Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model |
| title_short | Animal Migration Patterns Extraction Based on Atrous-Gated CNN Deep Learning Model |
| title_sort | animal migration patterns extraction based on atrous gated cnn deep learning model |
| topic | China next generation weather radar (CINRAD) atrous-gated CNN squeeze-and-excitation (SE) atrous spatial pyramid pooling (ASPP) extract biological target information |
| url | https://www.mdpi.com/2072-4292/13/24/4998 |
| work_keys_str_mv | AT shuaihangwang animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel AT chenghu animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel AT kaicui animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel AT ruiwang animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel AT huafengmao animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel AT dongliwu animalmigrationpatternsextractionbasedonatrousgatedcnndeeplearningmodel |