Deep CNN for Wetland Mapping from Satellite Imagery
DOI:
https://doi.org/10.52436/1.jutif.2025.6.5.5280Keywords:
Augmentation, CNN, Remote Sensing, WetlandAbstract
Wetland loss endangers the ecosystem through loss of biodiversity, carbon sequestration and flood regulation potential. A precise determination of wetlands status is necessary to safeguard for their conservation and ensure sustainable management. Implementation This study aims to assess the performance of deep CNNs in wetland detection using high-resolution Google Earth image data in South Kalimantan province, Indonesia. The work adopts the Chopped Picture Method (CPM) and the use of sliding windows for data augmentation to improve the diversity of the dataset and reduce the computational cost. Two CNN models, VGG-16Net, and LeNet-5, were trained using a dataset comprising 220 satellite images, which we converted into 89,100 patches of 56×56 pixels. Performance was compared using accuracy, precision, recall, and F1-score. Experimental results show good levels of accuracy for the two architectures, but LeNet-5 provided more stable results between test locations, having a F1-score closer to 100% and spending less computational time (≈10s per epoch) than VGG-16Net (≈40s per epoch). These results validate that CPM significantly increases the variety of training data, making it possible for a CNN to correctly identify the vague and irregular shapes of wetlands with high accuracy. In addition to advancing environmental conservation strategies, the study highlights the contribution of informatics to large-scale, automated environmental monitoring, particularly in supporting wetland conservation, sustainable land-use planning, and climate adaptation efforts.
Downloads
References
L. dkk Khairiyati, Buku Ajar Pengantar Lingkungan Lahan Basah. 2022.
K. A. Hapsari, T. Jennerjahn, S. H. Nugroho, E. Yulianto, and H. Behling, “Sea level rise and climate change acting as interactive stressors on development and dynamics of tropical peatlands in coastal Sumatra and South Borneo since the Last Glacial Maximum,” Glob. Chang. Biol., vol. 28, no. 10, pp. 3459–3479, May 2022, doi: https://doi.org/10.1111/gcb.16131.
L. K. Sharma and R. Naik, “Wetland Ecosystems BT - Conservation of Saline Wetland Ecosystems: An Initiative towards UN Decade of Ecological Restoration,” L. K. Sharma and R. Naik, Eds., Singapore: Springer Nature Singapore, 2024, pp. 3–32. doi: 10.1007/978-981-97-5069-6_1.
M. Mahdianpari, B. Salehi, F. Mohammadimanesh, and M. Motagh, “Random forest wetland classification using ALOS-2 L-band, RADARSAT-2 C-band, and TerraSAR-X imagery,” ISPRS J. Photogramm. Remote Sens., vol. 130, pp. 13–31, 2017, doi: https://doi.org/10.1016/j.isprsjprs.2017.05.010.
B. Brisco, F. Ahern, K. Murnaghan, L. White, F. Canisus, and P. Lancaster, “Seasonal change in wetland coherence as an aid to wetland monitoring,” Remote Sens., vol. 9, no. 2, pp. 1–19, 2017, doi: 10.3390/rs9020158.
S. Wdowinski, S.-W. Kim, F. Amelung, T. H. Dixon, F. Miralles-Wilhelm, and R. Sonenshein, “Space-based detection of wetlands’ surface water level changes from L-band SAR interferometry,” Remote Sens. Environ., vol. 112, no. 3, pp. 681–696, 2008, doi: https://doi.org/10.1016/j.rse.2007.06.008.
F. Hashim, H. Dibs, and H. S. Jaber, “Applying Support Vector Machine Algorithm on Multispectral Remotely sensed satellite image for Geospatial Analysis,” J. Phys. Conf. Ser., vol. 1963, no. 1, 2021, doi: 10.1088/1742-6596/1963/1/012110.
S. Gxokwe, T. Dube, and D. Mazvimavi, “Leveraging Google Earth Engine platform to characterize and map small seasonal wetlands in the semi-arid environments of South Africa,” Sci. Total Environ., vol. 803, p. 150139, 2022, doi: 10.1016/j.scitotenv.2021.150139.
R. B. Barito et al., “Landsat Image Classification Based on K-Nearest Neighbor,” in 2022 International Seminar on Application for Technology of Information and Communication (iSemantic), 2022, pp. 485–489. doi: 10.1109/iSemantic55962.2022.9920385.
C. S. Cunha, L. A. Guasselli, T. F. Belloli, and C. C. Korb, “Classification of Potential Wetlands using the Random Forest in Google Earth Engine in Geomorphological Units - Rio Grande do Sul, Brazil,” Rev. Bras. Cartogr., vol. 75, pp. 1–22, 2023, doi: 10.14393/rbcv75n0a-69753.
A. D. P. Pacheco, J. A. D. S. Junior, A. M. Ruiz-Armenteros, and R. F. F. Henriques, “Assessment of k-nearest neighbor and random forest classifiers for mapping forest fire areas in central portugal using landsat-8, sentinel-2, and terra imagery,” Remote Sens., vol. 13, no. 7, pp. 1–25, 2021, doi: 10.3390/rs13071345.
C. Sothe et al., “Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data,” GIScience Remote Sens., vol. 57, no. 3, pp. 369–394, Apr. 2020, doi: 10.1080/15481603.2020.1712102.
K. Mainali, M. Evans, D. Saavedra, E. Mills, B. Madsen, and S. Minnemeyer, “Convolutional neural network for high-resolution wetland mapping with open data: Variable selection and the challenges of a generalizable model,” Sci. Total Environ., vol. 861, p. 160622, 2023, doi: https://doi.org/10.1016/j.scitotenv.2022.160622.
N. Ståhl and L. Weimann, “Identifying wetland areas in historical maps using deep convolutional neural networks,” Ecol. Inform., vol. 68, no. September 2021, p. 101557, 2022, doi: 10.1016/j.ecoinf.2022.101557.
X. M. Guan, D. Wang, L. Wan, and J. Zhang, “Extracting Wetland Type Information with a Deep Convolutional Neural Network,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/5303872.
J. Song, S. Gao, Y. Zhu, and C. Ma, “A survey of remote sensing image classification based on CNNs,” Big Earth Data, vol. 3, no. 3, pp. 232–254, 2019, doi: 10.1080/20964471.2019.1657720.
S. Minaee, Y. Boykov, F. Porikli, A. Plaza, N. Kehtarnavaz, and D. Terzopoulos, “Image Segmentation Using Deep Learning: A Survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 7, pp. 3523–3542, 2022, doi: 10.1109/TPAMI.2021.3059968.
J. Weinman, Z. Chen, B. Gafford, N. Gifford, A. Lamsal, and L. Niehus-Staab, “Deep Neural Networks for Text Detection and Recognition in Historical Maps,” in 2019 International Conference on Document Analysis and Recognition (ICDAR), 2019, pp. 902–909. doi: 10.1109/ICDAR.2019.00149.
A. Le Bris, S. Giordano, and C. Mallet, “CNN Semantic Segmentation to Retrieve Past Land Cover out of Historical Orthoimages and Dsm: First Experiments,” ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 5, no. 2, pp. 1013–1019, 2020, doi: 10.5194/isprs-annals-V-2-2020-1013-2020.
S. Branson, J. D. Wegner, D. Hall, N. Lang, K. Schindler, and P. Perona, “From Google Maps to a fine-grained catalog of street trees,” ISPRS J. Photogramm. Remote Sens., vol. 135, pp. 13–30, 2018, doi: https://doi.org/10.1016/j.isprsjprs.2017.11.008.
M. Mahdianpari, M. Rezaee, Y. Zhang, and B. Salehi, “Wetland classification using deep convolutional neural network,” Int. Geosci. Remote Sens. Symp., vol. 2018-July, no. November, pp. 9249–9252, 2018, doi: 10.1109/IGARSS.2018.8517919.
E. Ahmadzadeh, K. Jaferzadeh, S. Shin, and I. Moon, “Automated single cardiomyocyte characterization by nucleus extraction from dynamic holographic images using a fully convolutional neural network,” Biomed. Opt. Express, vol. 11, no. 3, p. 1501, 2020, doi: 10.1364/boe.385218.
T. Ise, M. Minagawa, and M. Onishi, “Classifying 3 Moss Species by Deep Learning, Using the ‘Chopped Picture’ Method,” Open J. Ecol., vol. 08, no. 03, pp. 166–173, 2018, doi: 10.4236/oje.2018.83011.
D. Potere, “Horizontal positional accuracy of google earth’s high-resolution imagery archive,” Sensors, vol. 8, no. 12, pp. 7973–7981, 2008, doi: 10.3390/s8127973.
W. Li, R. Dong, H. Fu, J. Wang, L. Yu, and P. Gong, “Integrating Google Earth imagery with Landsat data to improve 30-m resolution land cover mapping,” Remote Sens. Environ., vol. 237, no. November 2019, 2020, doi: 10.1016/j.rse.2019.111563.
S. Rizal, “Pemanfaatan Lahan Basah bagi Masyarakat di Wilayah Kalimantan Selatan,” Kompasiana. Accessed: Mar. 23, 2025. [Online]. Available: https://www.kompasiana.com/syamsulrizal4805/637459a508a8b55498451c02/pemanfaatan-lahan-basah-bagi-masyarakat-di-wilayah-kalimantan-selatan?page=2&page_images=1
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, doi: 10.1109/5.726791.
S. Watanabe, K. Sumi, and T. Ise, “Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese bamboo forests,” BMC Ecol., vol. 20, no. 1, pp. 1–14, 2020, doi: 10.1186/s12898-020-00331-5.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 As`'ary Ramadhan, Rudy Herteno, Andi Farmadi
This work is licensed under a Creative Commons Attribution 4.0 International License.
