An Integrated Convolutional Neural Networks and Light Gradient Boosting Approach for Flood Classification Using Sentinel-1 SAR Satellite Imagery

Siddiq Ahmad Anshori, Asep Id Hadiana, Fatan Kasyidi

Abstract

od classification plays a crucial role in disaster mitigation, particularly in areas frequently affected by floods. This study proposes a novel model combining Convolutional Neural Networks (CNN) using ResNet-50 and Light Gradient Boosting Machine (LightGBM) for classifying flood and non-flood areas using Sentinel-1 SAR imagery. The dataset used consists of 21,016 images, evenly distributed between flood and non-flood classes, and processed through resizing, normalization, denoising, and augmentation. Feature extraction was conducted using the ResNet-50 architecture, which captured spatial and textural patterns efficiently, followed by LightGBM for classification. The proposed model achieved a high accuracy of 96%, with Precision, Recall, and F1-scores exceeding 95% for both classes. The evaluation metrics, including Precision-Recall Curve with an AUC of 0.9852 and a Confusion Matrix, confirmed the model's robustness and balance in classifying both categories. Additionally, comparisons with previous research, such as SAR-FloodNet, demonstrated the superiority of the proposed approach, achieving a 2% improvement in accuracy. Despite these results, limitations such as the exclusive use of Sentinel-1 data and the lack of validation across diverse environmental conditions remain. Future research should explore integrating multispectral Sentinel-2 data and testing on broader datasets to enhance scalability and reliability. The findings underscore the model's potential for real-world applications in flood monitoring and disaster management systems.

Full Text:

PDF (68-76)

References

P. Ghorpade et al., “Flood Forecasting Using Machine Learning: A Review,” 2021 8th International Conference on Smart Computing and Communications: Artificial Intelligence, AI Driven Applications for a Smart World, ICSCC 2021, pp. 32–36, 2021, doi: 10.1109/ICSCC51209.2021.9528099.

S. Li, M. Goldberg, S. Helfrich, S. Kalluri, W. Sjoberg, and D. Sun, “Time-Series Global Flood Mapping Datasets from Suomi-NPP&NOAA-20/VIIRS for Flood Analysis and Modelling,” International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2023-July, pp. 1004–1007, 2023, doi: 10.1109/IGARSS52108.2023.10283346.

E. Portales-Julia, N. I. Bountos, M. Sdraka, G. Mateo-Garcia, I. Papoutsis, and L. Gomez-Chova, “Multimodal and Multitemporal Data Fusion for Flood Extent Segmentation Exploiting Kurosiwo and WorldFloods Sentinel Datasets,” International Geoscience and Remote Sensing Symposium (IGARSS), pp. 950–953, 2024, doi: 10.1109/IGARSS53475.2024.10690461.

M. Glasscoe et al., “Integrating Hydrologic Models and Earth Observation Data for Global Flood Forecasting and Alerting in Near Real-Time,” International Geoscience and Remote Sensing Symposium (IGARSS), pp. 554–557, 2021, doi: 10.1109/IGARSS47720.2021.9554638.

B. Demissie, S. Vanhuysse, T. Grippa, C. Flasse, and E. Wolff, “Using Sentinel-1 and Google Earth Engine cloud computing for detecting historical flood hazards in tropical urban regions: a case of Dar es Salaam,” Geomatics, Natural Hazards and Risk, vol. 14, no. 1, p., 2023, doi: 10.1080/19475705.2023.2202296.

B. M. Sukojo, L. Azizah, and H. Sanjaya, “Flood Disaster Monitoring Application In The National Rice Granary Area Based On Sentinel-1 Imagery (Case Study: Laren Disctrict, Lamongan Regency),” 2023 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2023, pp. 1–7, 2023, doi: 10.1109/ICARES60489.2023.10329903.

M. Nhangumbe, A. Nascetti, and Y. Ban, “Multi-Temporal Sentinel-1 SAR and Sentinel-2 MSI Data for Flood Mapping and Damage Assessment in Mozambique,” ISPRS Int J Geoinf, vol. 12, no. 2, 2023, doi: 10.3390/ijgi12020053.

L. J. L. Canillo and A. A. Hernandez, “Flood Risk Visualization and Prediction Information System: Case of City Manila, Philippines,” Proceeding - 2021 IEEE 17th International Colloquium on Signal Processing and Its Applications, CSPA 2021, no. March, pp. 59–63, 2021, doi: 10.1109/CSPA52141.2021.9377276.

B. Swapna, R. Venkatessan, F. Taskeen, K. Indrapriya, D. Manjula, and D. S. Muthukumar, “Scalable Deep Learning for Categorization of Satellite Images,” 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023 - Proceedings, pp. 773–778, 2023, doi: 10.1109/I-SMAC58438.2023.10290437.

L. Ma, Y. Liu, X. Zhang, Y. Ye, G. Yin, and B. A. Johnson, “Deep learning in remote sensing applications: A meta-analysis and review,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 152, no. March, pp. 166–177, 2019, doi: 10.1016/j.isprsjprs.2019.04.015.

D. Chakravarty, A. M. Thomas, and V. Vivek, “A Survey on Decentralization and Virtualization of Medical Trials: An approach through Ensemble learning models and Convolutional Neural Networks,” 2023 International Conference on Computer Science and Emerging Technologies, CSET 2023, pp. 1–7, 2023, doi: 10.1109/CSET58993.2023.10346978.

M. Doostparast, M. Pouyani, and M. H. Y. Moghaddam, “Bootstrap Aggregating as an ensembled machine learning algorithm for power consumption prediction under asymmetric loss with linear model-base learners,” 2023 27th International Electrical Power Distribution Conference, EPDC 2023, vol. 0, no. 6, pp. 6–11, 2023, doi: 10.1109/EPDC59105.2023.10218875.

M. M. Santoni, T. Basaruddin, K. Junus, and O. Lawanto, “Automatic Detection of Students’ Engagement During Online Learning: A Bagging Ensemble Deep Learning Approach,” IEEE Access, vol. 12, no. July, pp. 96063–96073, 2024, doi: 10.1109/ACCESS.2024.3425820.

R. K. Priyadarshini, A. Bazila Banu, and T. Nagamani, “Gradient Boosted Decision Tree based Classification for Recognizing Human Behavior,” Proceedings of the 2019 International Conference on Advances in Computing and Communication Engineering, ICACCE 2019, pp. 19–22, 2019, doi: 10.1109/ICACCE46606.2019.9080014.

C. Arunkumar Madhuvappam, D. Vinod Kumar, S. Kanna, S. Vaishnodevi, G. Murali, and M. Karthick, “Enhanced Lung Cancer Detection using Ensemble Learning Algorithms: A Comparative Study of LightGBM & CatBoost,” pp. 324–328, 2024, doi: 10.1109/icipcn63822.2024.00060.

M. R. Machado, S. Karray, and I. T. De Sousa, “LightGBM: An effective decision tree gradient boosting method to predict customer loyalty in the finance industry,” 14th International Conference on Computer Science and Education, ICCSE 2019, no. Nips, pp. 1111–1116, 2019, doi: 10.1109/ICCSE.2019.8845529.

A. Aparna, A. Emily Jenifer, and N. Sudha, “SAR-FloodNet: A Patch-based Convolutional Neural Network for Flood Detection on SAR Images,” Proceedings - International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2022, no. Icaaic, pp. 195–200, 2022, doi: 10.1109/ICAAIC53929.2022.9792770.

A. Toma, I. Șandric, and B. A. Mihai, “Flooded area detection and mapping from Sentinel-1 imagery. Complementary approaches and comparative performance evaluation,” Eur J Remote Sens, vol. 57, no. 1, 2024, doi: 10.1080/22797254.2024.2414004.

Z. Zhao, B. Zhang, F. Wu, and J. Yang, “Deep Learning-Based Flood Detection Using Multi-Temporal Sentinel-1 SAR Data: A Case Study in Beijing Area, 2023,” 2023 SAR in Big Data Era, BIGSARDATA 2023 - Proceedings, pp. 1–4, 2023, doi: 10.1109/BIGSARDATA59007.2023.10295008.

C. Singha, V. K. Rana, Q. B. Pham, D. C. Nguyen, and E. Łupikasza, “Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment,” Environmental Science and Pollution Research, vol. 31, no. 35, pp. 48497–48522, 2024, doi: 10.1007/s11356-024-34286-7.

H. G. Dong Ye, Qing Xu, “An Efficient and Lightweight Convolutional Neural for Remote Sensing Image Scene Classificatio,” S, 2020.

C. Qi, Z. Yang, and Y. Wen, “Improved ResNet-50 Model for AI Image Recognition Based on Multi-Scale Attention Mechanism,” 2024 6th International Conference on Communications, Information System and Computer Engineering (CISCE), pp. 825–829, 2024, doi: 10.1109/cisce62493.2024.10653161.

M. Priyanka, S. Sreekumar, and S. Arsh, “Detection of Covid-19 from the Chest X-Ray Images: A Comparison Study between CNN and Resnet-50,” MysuruCon 2022 - 2022 IEEE 2nd Mysore Sub Section International Conference, pp. 1–7, 2022, doi: 10.1109/MysuruCon55714.2022.9972488.

Y. Wang, Y. Ling, T. O. Chan, and J. Awange, “High-resolution earthquake-induced landslide hazard assessment in Southwest China through frequency ratio analysis and LightGBM,” International Journal of Applied Earth Observation and Geoinformation, vol. 131, no. June, p. 103947, 2024, doi: 10.1016/j.jag.2024.103947.

DOI: https://doi.org/10.37058/innovatics.v7i1.13600

Refbacks

  • There are currently no refbacks.