WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra
The frequent occurrence of marine oil spills underscores the need for efficient methods to identify spilled substances and analyze their thickness. Traditional models based on Laser-Induced Fluorescence (LIF) technology often focus on a single functionality, limiting their ability to simultaneously...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/6/3177 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850090055897448448 |
|---|---|
| author | Shubo Zhang Menghan Li Jing Li |
| author_facet | Shubo Zhang Menghan Li Jing Li |
| author_sort | Shubo Zhang |
| collection | DOAJ |
| description | The frequent occurrence of marine oil spills underscores the need for efficient methods to identify spilled substances and analyze their thickness. Traditional models based on Laser-Induced Fluorescence (LIF) technology often focus on a single functionality, limiting their ability to simultaneously perform qualitative and quantitative analyses. This study introduces a novel LIF-based spectral analysis method that integrates a self-designed detection system and a multi-task framework, the Wavelet CNN-sLSTM-KAN-Enhanced Transformer (WaveConv-sLSTM-KET). By combining a Wavelet Transform CNN block, a scalar LSTM block, and a Kolmogorov–Arnold Network-Enhanced Transformer block, the framework enables simultaneous oil-type identification and thickness prediction without preprocessing or fully connected layers. It achieves high classification accuracy and precise regression for oil film thicknesses (50 µm–0.5 mm). Its reliability, real-time operation, and lightweight structure address limitations of conventional methods, offering a promising solution for non-destructive, efficient oil spill detection. |
| format | Article |
| id | doaj-art-c66ddf84af6c4140809cee5f5d173b14 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-c66ddf84af6c4140809cee5f5d173b142025-08-20T02:42:38ZengMDPI AGApplied Sciences2076-34172025-03-01156317710.3390/app15063177WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence SpectraShubo Zhang0Menghan Li1Jing Li2Department of Optical Science and Engineering, Fudan University, Shanghai 200433, ChinaDepartment of Optical Science and Engineering, Fudan University, Shanghai 200433, ChinaDepartment of Optical Science and Engineering, Fudan University, Shanghai 200433, ChinaThe frequent occurrence of marine oil spills underscores the need for efficient methods to identify spilled substances and analyze their thickness. Traditional models based on Laser-Induced Fluorescence (LIF) technology often focus on a single functionality, limiting their ability to simultaneously perform qualitative and quantitative analyses. This study introduces a novel LIF-based spectral analysis method that integrates a self-designed detection system and a multi-task framework, the Wavelet CNN-sLSTM-KAN-Enhanced Transformer (WaveConv-sLSTM-KET). By combining a Wavelet Transform CNN block, a scalar LSTM block, and a Kolmogorov–Arnold Network-Enhanced Transformer block, the framework enables simultaneous oil-type identification and thickness prediction without preprocessing or fully connected layers. It achieves high classification accuracy and precise regression for oil film thicknesses (50 µm–0.5 mm). Its reliability, real-time operation, and lightweight structure address limitations of conventional methods, offering a promising solution for non-destructive, efficient oil spill detection.https://www.mdpi.com/2076-3417/15/6/3177oil spill detectionlaser-induced fluorescencequalitative and quantitative analyseswavelet CNN-sLSTM-KAN-enhanced transformerlightweight structure |
| spellingShingle | Shubo Zhang Menghan Li Jing Li WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra Applied Sciences oil spill detection laser-induced fluorescence qualitative and quantitative analyses wavelet CNN-sLSTM-KAN-enhanced transformer lightweight structure |
| title | WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra |
| title_full | WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra |
| title_fullStr | WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra |
| title_full_unstemmed | WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra |
| title_short | WaveConv-sLSTM-KET: A Novel Framework for the Multi-Task Analysis of Oil Spill Fluorescence Spectra |
| title_sort | waveconv slstm ket a novel framework for the multi task analysis of oil spill fluorescence spectra |
| topic | oil spill detection laser-induced fluorescence qualitative and quantitative analyses wavelet CNN-sLSTM-KAN-enhanced transformer lightweight structure |
| url | https://www.mdpi.com/2076-3417/15/6/3177 |
| work_keys_str_mv | AT shubozhang waveconvslstmketanovelframeworkforthemultitaskanalysisofoilspillfluorescencespectra AT menghanli waveconvslstmketanovelframeworkforthemultitaskanalysisofoilspillfluorescencespectra AT jingli waveconvslstmketanovelframeworkforthemultitaskanalysisofoilspillfluorescencespectra |