Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series
In the current biodiversity crisis, the increasing demand for effective conservation tools aligns with significant advancements in artificial intelligence (AI). There is the need for the development of more robust and accurate forecasting methods, ultimately enhancing our understanding of ecological...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X25000482 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557585666932736 |
|---|---|
| author | Sébastien Lhoumeau João Pinelo Paulo A.V. Borges |
| author_facet | Sébastien Lhoumeau João Pinelo Paulo A.V. Borges |
| author_sort | Sébastien Lhoumeau |
| collection | DOAJ |
| description | In the current biodiversity crisis, the increasing demand for effective conservation tools aligns with significant advancements in artificial intelligence (AI). There is the need for the development of more robust and accurate forecasting methods, ultimately enhancing our understanding of ecological dynamics and supporting the formulation of effective conservation strategies. This research conducted a comparative analysis of Local Polynomial Regression (LOESS), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Recurrent Neural Network (RNN) models for time-series prediction. Using a unique Long-Term Monitoring Program for island forest arthropods (2012–2023), wherein we selected the 39 most prevalent species collected using SLAM (Sea Land Air Malaise) traps within a native forest fragment on Terceira Island in the Azores archipelago. The results indicate that RNN outperformed LOESS in terms of both goodness of fit and overall accuracy. Although RNN did not surpass classical SARIMA in data prediction, it demonstrated superior goodness-of-fit on the training dataset. Furthermore, we investigated extinction and invasion scenarios within the Terceira arthropod assemblage, providing insight into broader implications and avenues for future research. This study discusses the utility and limitations of RNN models in biodiversity conservation through various scenarios. It contributes to the ongoing discourse at the convergence of conservation, ecology, and artificial intelligence (AI), highlighting advancements and innovative solutions crucial for the effective implementation of conservation strategies. |
| format | Article |
| id | doaj-art-8385bb32f677448697abee50cea79166 |
| institution | Kabale University |
| issn | 1470-160X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj-art-8385bb32f677448697abee50cea791662025-02-03T04:16:31ZengElsevierEcological Indicators1470-160X2025-02-01171113119Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time seriesSébastien Lhoumeau0João Pinelo1Paulo A.V. Borges2cE3c-Centre for Ecology, Evolution and Environmental Changes, Azorean Biodiversity Group, CHANGE—Global Change and Sustainability Institute, School of Agricultural and Environmental Sciences, University of the Azores, Rua Capitão João d’Ávila, Pico da Urze, 9700-042 Angra do Heroísmo, Azores, Portugal; Corresponding author at: cE3c-Centre for Ecology, Evolution and Environmental Changes, Azorean Biodiversity Group, CHANGE—Global Change and Sustainability Institute, School of Agricultural and Environmental Sciences, University of the Azores, Rua Capitão João d’Ávila, Pico da Urze, 9700-042 Angra do Heroísmo, Azores, Portugal.Atlantic International Research Centre, 9700-702 Angra do Heroísmo, Azores, PortugalcE3c-Centre for Ecology, Evolution and Environmental Changes, Azorean Biodiversity Group, CHANGE—Global Change and Sustainability Institute, School of Agricultural and Environmental Sciences, University of the Azores, Rua Capitão João d’Ávila, Pico da Urze, 9700-042 Angra do Heroísmo, Azores, Portugal; IUCN SSC Atlantic Islands Invertebrate Specialist Group, 9700-042 Angra do Heroísmo, Azores, Portugal; IUCN SSC Species Monitoring Specialist Group, 9700-042 Angra do Heroísmo, Azores, PortugalIn the current biodiversity crisis, the increasing demand for effective conservation tools aligns with significant advancements in artificial intelligence (AI). There is the need for the development of more robust and accurate forecasting methods, ultimately enhancing our understanding of ecological dynamics and supporting the formulation of effective conservation strategies. This research conducted a comparative analysis of Local Polynomial Regression (LOESS), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Recurrent Neural Network (RNN) models for time-series prediction. Using a unique Long-Term Monitoring Program for island forest arthropods (2012–2023), wherein we selected the 39 most prevalent species collected using SLAM (Sea Land Air Malaise) traps within a native forest fragment on Terceira Island in the Azores archipelago. The results indicate that RNN outperformed LOESS in terms of both goodness of fit and overall accuracy. Although RNN did not surpass classical SARIMA in data prediction, it demonstrated superior goodness-of-fit on the training dataset. Furthermore, we investigated extinction and invasion scenarios within the Terceira arthropod assemblage, providing insight into broader implications and avenues for future research. This study discusses the utility and limitations of RNN models in biodiversity conservation through various scenarios. It contributes to the ongoing discourse at the convergence of conservation, ecology, and artificial intelligence (AI), highlighting advancements and innovative solutions crucial for the effective implementation of conservation strategies.http://www.sciencedirect.com/science/article/pii/S1470160X25000482Conservation scenarioEcological modellingAzores arthropodsMachine learningLong-term ecological dataModel comparison |
| spellingShingle | Sébastien Lhoumeau João Pinelo Paulo A.V. Borges Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series Ecological Indicators Conservation scenario Ecological modelling Azores arthropods Machine learning Long-term ecological data Model comparison |
| title | Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| title_full | Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| title_fullStr | Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| title_full_unstemmed | Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| title_short | Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| title_sort | artificial intelligence for biodiversity exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series |
| topic | Conservation scenario Ecological modelling Azores arthropods Machine learning Long-term ecological data Model comparison |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X25000482 |
| work_keys_str_mv | AT sebastienlhoumeau artificialintelligenceforbiodiversityexploringthepotentialofrecurrentneuralnetworksinforecastingarthropoddynamicsbasedontimeseries AT joaopinelo artificialintelligenceforbiodiversityexploringthepotentialofrecurrentneuralnetworksinforecastingarthropoddynamicsbasedontimeseries AT pauloavborges artificialintelligenceforbiodiversityexploringthepotentialofrecurrentneuralnetworksinforecastingarthropoddynamicsbasedontimeseries |