Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland
ABSTRACT In this study, we compared the established MaxEnt and a more novel deep learning approach for modeling the distribution of humpback whales (Megaptera novaeangliae) in north Iceland. We examined the mechanisms, structures, and optimization techniques of both approaches, highlighting their di...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-03-01
|
| Series: | Ecology and Evolution |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ece3.71099 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850280505046466560 |
|---|---|
| author | Nils Barthel Charla J. Basran Marianne H. Rasmussen Benjamin Burkhard |
| author_facet | Nils Barthel Charla J. Basran Marianne H. Rasmussen Benjamin Burkhard |
| author_sort | Nils Barthel |
| collection | DOAJ |
| description | ABSTRACT In this study, we compared the established MaxEnt and a more novel deep learning approach for modeling the distribution of humpback whales (Megaptera novaeangliae) in north Iceland. We examined the mechanisms, structures, and optimization techniques of both approaches, highlighting their differences and similarities. Monthly distribution models for Skjálfandi Bay were created, from 2018 until 2021, using presence‐only sighting data and satellite remote sensing data. Search efforts and boat tracklines were utilized to create pseudo‐absence points for both models. Additionally, the trained models were used to create distribution projections for the year 2022, solely based on the available environmental data. We compared the results using the established area under the curve value. The findings indicate that both approaches have their limitations and advantages. MaxEnt does not allow continuous updating within a time series, yet it mitigates the risk of overfitting by employing the maximum entropy principle. The deep learning model is more likely to overfit, but the larger weight network increases the model's capability to capture complex relationships and patterns. Ultimately, the results show that the deep learning model had a higher predictive performance in modeling both current and future humpback whale distributions. Both modeling approaches have inherent limitations, such as the low resolution of the input data, spatial biases, and the inability to fully capture the entire complexity of natural processes. Despite this, deep learning showed promising results in modeling the distribution of humpback whales and prompts further research in different study areas and applications for other mobile animal species. |
| format | Article |
| id | doaj-art-c88ccb6f252f43178f29bd4cc14fc101 |
| institution | OA Journals |
| issn | 2045-7758 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecology and Evolution |
| spelling | doaj-art-c88ccb6f252f43178f29bd4cc14fc1012025-08-20T01:48:44ZengWileyEcology and Evolution2045-77582025-03-01153n/an/a10.1002/ece3.71099Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North IcelandNils Barthel0Charla J. Basran1Marianne H. Rasmussen2Benjamin Burkhard3Institute of Physical Geography and Landscape Ecology Leibniz University Hannover Hannover GermanyHúsavík Research Center University of Iceland Húsavík IcelandHúsavík Research Center University of Iceland Húsavík IcelandInstitute of Physical Geography and Landscape Ecology Leibniz University Hannover Hannover GermanyABSTRACT In this study, we compared the established MaxEnt and a more novel deep learning approach for modeling the distribution of humpback whales (Megaptera novaeangliae) in north Iceland. We examined the mechanisms, structures, and optimization techniques of both approaches, highlighting their differences and similarities. Monthly distribution models for Skjálfandi Bay were created, from 2018 until 2021, using presence‐only sighting data and satellite remote sensing data. Search efforts and boat tracklines were utilized to create pseudo‐absence points for both models. Additionally, the trained models were used to create distribution projections for the year 2022, solely based on the available environmental data. We compared the results using the established area under the curve value. The findings indicate that both approaches have their limitations and advantages. MaxEnt does not allow continuous updating within a time series, yet it mitigates the risk of overfitting by employing the maximum entropy principle. The deep learning model is more likely to overfit, but the larger weight network increases the model's capability to capture complex relationships and patterns. Ultimately, the results show that the deep learning model had a higher predictive performance in modeling both current and future humpback whale distributions. Both modeling approaches have inherent limitations, such as the low resolution of the input data, spatial biases, and the inability to fully capture the entire complexity of natural processes. Despite this, deep learning showed promising results in modeling the distribution of humpback whales and prompts further research in different study areas and applications for other mobile animal species.https://doi.org/10.1002/ece3.71099comparative analysisdistribution modelsenvironmental driversMegaptera novaeangliaeSkjálfandi Bay |
| spellingShingle | Nils Barthel Charla J. Basran Marianne H. Rasmussen Benjamin Burkhard Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland Ecology and Evolution comparative analysis distribution models environmental drivers Megaptera novaeangliae Skjálfandi Bay |
| title | Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland |
| title_full | Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland |
| title_fullStr | Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland |
| title_full_unstemmed | Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland |
| title_short | Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland |
| title_sort | comparative analysis of maxent and deep learning approaches for modeling humpback whale distribution in north iceland |
| topic | comparative analysis distribution models environmental drivers Megaptera novaeangliae Skjálfandi Bay |
| url | https://doi.org/10.1002/ece3.71099 |
| work_keys_str_mv | AT nilsbarthel comparativeanalysisofmaxentanddeeplearningapproachesformodelinghumpbackwhaledistributioninnorthiceland AT charlajbasran comparativeanalysisofmaxentanddeeplearningapproachesformodelinghumpbackwhaledistributioninnorthiceland AT mariannehrasmussen comparativeanalysisofmaxentanddeeplearningapproachesformodelinghumpbackwhaledistributioninnorthiceland AT benjaminburkhard comparativeanalysisofmaxentanddeeplearningapproachesformodelinghumpbackwhaledistributioninnorthiceland |