On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification
The classification of Unexploded Ordnance (UXO) from magnetometer data is a critical but challenging task, frequently hindered by the data scarcity required for training robust machine learning models. To address this, we leverage a high-fidelity digital twin to generate a comprehensive dataset of m...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239766131802112 |
|---|---|
| author | Piotr Ściegienka Marcin Blachnik |
| author_facet | Piotr Ściegienka Marcin Blachnik |
| author_sort | Piotr Ściegienka |
| collection | DOAJ |
| description | The classification of Unexploded Ordnance (UXO) from magnetometer data is a critical but challenging task, frequently hindered by the data scarcity required for training robust machine learning models. To address this, we leverage a high-fidelity digital twin to generate a comprehensive dataset of magnetometer signals from both UXO and non-UXO objects, incorporating complex remanent magnetization effects. In this study, we design and evaluate a custom Convolutional Neural Network (CNN) for UXO classification and compare it against classical machine learning baseline, including Random Forest and kNN. Our CNN model achieves a balanced accuracy of 84.65%, significantly outperforming traditional models that exhibit performance collapse under slight distortions such as additive noise, drift, and time-wrapping. Additionally, we present a compact two-block CNN variant that retains competitive accuracy while reducing the number of learnable parameters by approximately 33%, making it suitable for real-time onboard classification in underwater vehicle missions. Through extensive ablation studies, we confirm that architectural components, such as residual skip connections and element-wise batch normalization, are crucial for achieving model stability and performance. The results also highlight the practical implications of underwater vehicles for survey design, emphasizing the need to mitigate signal drift and maintain constant survey speeds. This work not only provides a robust deep learning model for UXO classification, but also offers actionable suggestions for improving both model deployment and data acquisition protocols in the field. |
| format | Article |
| id | doaj-art-dc99b4662e074c629f9d4299812bd12d |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-dc99b4662e074c629f9d4299812bd12d2025-08-20T04:00:50ZengMDPI AGApplied Sciences2076-34172025-07-011515827410.3390/app15158274On the Development of a Neural Network Architecture for Magnetometer-Based UXO ClassificationPiotr Ściegienka0Marcin Blachnik1Joint Doctoral School, Silesian University of Technology, 44-100 Gliwice, PolandDepartment of Industrial Informatics, Silesian University of Technology, 44-100 Gliwice, PolandThe classification of Unexploded Ordnance (UXO) from magnetometer data is a critical but challenging task, frequently hindered by the data scarcity required for training robust machine learning models. To address this, we leverage a high-fidelity digital twin to generate a comprehensive dataset of magnetometer signals from both UXO and non-UXO objects, incorporating complex remanent magnetization effects. In this study, we design and evaluate a custom Convolutional Neural Network (CNN) for UXO classification and compare it against classical machine learning baseline, including Random Forest and kNN. Our CNN model achieves a balanced accuracy of 84.65%, significantly outperforming traditional models that exhibit performance collapse under slight distortions such as additive noise, drift, and time-wrapping. Additionally, we present a compact two-block CNN variant that retains competitive accuracy while reducing the number of learnable parameters by approximately 33%, making it suitable for real-time onboard classification in underwater vehicle missions. Through extensive ablation studies, we confirm that architectural components, such as residual skip connections and element-wise batch normalization, are crucial for achieving model stability and performance. The results also highlight the practical implications of underwater vehicles for survey design, emphasizing the need to mitigate signal drift and maintain constant survey speeds. This work not only provides a robust deep learning model for UXO classification, but also offers actionable suggestions for improving both model deployment and data acquisition protocols in the field.https://www.mdpi.com/2076-3417/15/15/8274magnetometry datadeep learningUXOUnexploded OrdnanceAUVunderwater vehicle |
| spellingShingle | Piotr Ściegienka Marcin Blachnik On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification Applied Sciences magnetometry data deep learning UXO Unexploded Ordnance AUV underwater vehicle |
| title | On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification |
| title_full | On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification |
| title_fullStr | On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification |
| title_full_unstemmed | On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification |
| title_short | On the Development of a Neural Network Architecture for Magnetometer-Based UXO Classification |
| title_sort | on the development of a neural network architecture for magnetometer based uxo classification |
| topic | magnetometry data deep learning UXO Unexploded Ordnance AUV underwater vehicle |
| url | https://www.mdpi.com/2076-3417/15/15/8274 |
| work_keys_str_mv | AT piotrsciegienka onthedevelopmentofaneuralnetworkarchitectureformagnetometerbaseduxoclassification AT marcinblachnik onthedevelopmentofaneuralnetworkarchitectureformagnetometerbaseduxoclassification |