Cronin, Luc (2024) Fish Catch Optimisation using Variational Autoencoder. Bachelor's Thesis, Artificial Intelligence.
|
Text
FishCatchOptimisationusingVariationalAutoencoder.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (480kB) |
Abstract
The fishing industry plays a vital role in the global economy, particularly in Norway. There is currently no accurate methods for fisherman to know the locations of fish, this costs a lot of time, money and resources to find fish. These inefficiencies lead to major negative environmental impact as predicting fish locations on a daily basis remains a significant challenge. This study aims to investigate the effectiveness of a deep learning approach in solving this problem by implementing a Variational Autoencoder (VAE). The nature of the task is very complex due to the spatial and temporal aspects of the data. The model leverages spatio-temporal data, including Sea Surface Salinity (SSS), Sea Surface Temperature (SST), and historical catch data, to capture the complex patterns influencing fish movements. Our approach integrates convolutional and recurrent neural network layers to handle the spatial and temporal dimensions of the data. The results highlight the challenges in using deep learning models for this task, emphasising the need for improved data representation to achieve reliable predictions and support sustainable fishing practices.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Cardenas Cartagena, J. D. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 30 Jul 2024 09:49 |
| Last Modified: | 30 Jul 2024 09:49 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/33749 |
Actions (login required)
 |
View Item |