References

gesj

GEOGRAPHY, ENVIRONMENT, SUSTAINABILITY

2071-93882542-1565

Russian Geographical Society

10.24057/2071-9388-2024-3109

gesj-3490

Research Article

RESEARCH PAPER

Статьи

Burned area detection using convolutional neural network based on spatial information of synthetic aperture radar data in Indonesia

Lestari

Anugrah I.

Cibinong, West Java, 16911

anugrah.indah.lestari@brin.go.id

Kushardono

Dony

Parepare, South Sulawesi, 91131

Bayanuddin

Athar A.

Parepare, South Sulawesi, 91131

National Research and Innovation AgencyIndonesiaDirectorate of Laboratory Management, Research Facilities, and Science and Technology Park, National Research and Innovation AgencyIndonesia

2024

05072024

1723648

2024

Lestari A., Kushardono D., Bayanuddin A.

Данная работа распространяется под лицензией Creative Commons Attribution 4.0.

This work is licensed under a Creative Commons Attribution 4.0 License.

https://ges.rgo.ru/jour/article/view/3490

Forest and land fires are disasters that often occur in Indonesia which affects neighbouring countries. The burned area can be observed using remote sensing. Synthetic aperture radar (SAR) sensor data is advantageous since it can penetrate clouds and smoke. However, image analysis of SAR data differs from optical data, which is based on properties such as intensity, texture, and polarimetric feature. This research aims to propose a method to detect burned areas from the extracted feature of Sentinel-1 data. The features were classified using the Convolutional Neural Network (CNN) classifier. To find the best input features, several classification schemes were tested, including intensity and polarimetric features by applying the Boxcar speckle filter and the Gray Level Co-occurrence Matrix (GLCM) texture feature without using the Boxcar speckle filter. Additionally, this research investigates the significance of a window size parameter for each scheme. The results show the highest overall accuracy achieved 84% using CNN classification utilizing the GLCM texture features and without conducting the Boxcar speckle filter on the window size of 17×17 pixels when tested on the part region of Pulang Pisau Regency and Kapuas Regency, Central Kalimantan in 2019. The total burned area was 76,098.6 ha. The use of GLCM texture features without conducting the Boxcar speckle filter as input classification performs better than using intensity and polarimetric features that undergo the Boxcar speckle filter. Combining intensity and polarimetric features with performing the Boxcar speckle filter improves better classification performance over utilizing them separately. Furthermore, the selection of window size also contributes to improve the model performance.

burned areaconvolutional neural networkgray level co-occurrence matrix texture featuresynthetic aperture radar

The authors sincerely thank the Research Center for Remote Sensing, Research Organization for Aeronautics and Space, National Research and Innovation Agency for providing very-high resolution images. Also, the authors would like to acknowledge the Ministry of Environment and Forestry Republic of Indonesia for providing Burned Area and Land Cover Maps.

References1

Abdikan S., Bayik C., Sekertekin A., Balcik F.B., Karimzadeh S., Matsuoka M., and Sanli F.B. (2022). Burned Area Detection Using MultiSensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest. Forests, 13(2), 347, DOI: 10.3390/f13020347.

Anand R., Shanthi T., Sabeenian R.S., and Veni S. (2023). GLCM Feature-Based Texture Image Classification Using Machine Learning Algorithms. In: B.V. Kumar., P. Sivakumar., B. Surendiran., and J. Ding, eds., Smart Computer Vision EAI/Springer Innovations in Communication and Computing, Cham: Springer Nature, 103-125, DOI: 10.1007/978-3-031-20541-5_5.

Ansari J., Ghosh S.M., Dev Behera M., and Gupta K. S. (2020). A Study on Speckle Removal Techniques for Sentinel-1A SAR Data Over Sundarbans, Mangrove Forest, India. 2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), 90-93, DOI: 10.1109/ InGARSS48198.2020.9358929.

Arjasakusuma S., Kusuma S.S., Vetrita Y., Prasasti I., and Arief R. (2022). Monthly Burned-Area Mapping Using Multi-Sensor Integration of Sentinel-1 and Sentinel-2 and Machine Learning: Case Study of 2019’s Fire Events in South Sumatra Province, Indonesia. Remote Sensing Applications: Society and Environment, 27, 100790, DOI: 10.1016/j.rsase.2022.100790.

Ban Y., Zhang P., Nascetti A., Bevington A.R., and Wulder M.A. (2020). Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning. Scientific Reports, 10(1), 1–15, DOI: 10.1038/s41598-019-56967-x.

Center for Kalimantan Ecoregion Development Control Ministry of Environment and Forestry Republic of Indonesia. (2016). Capacity of Natural Resources and The Environment of The Kalimantan Ecoregion Based on Ecosystem Services. (in Indonesian). Palangkaraya: Central Kalimantan Province Environmental Agency.

Central Kalimantan Province Environmental Agency. (2020). Environmental Performance Information Document in 2019 for Central Kalimantan Province. (in Indonesian). Palangkaraya: Central Kalimantan Province Environmental Agency.

Champion I., Germain C., Da Costa J.P., Alborini A., and Dubois-Fernandez P. (2014). Retrieval of Forest Stand Age from SAR Image Texture for Varying Distance and Orientation Values of The Gray Level Co-Occurrence Matrix. IEEE Geosci. Remote Sensing Lett., 11(1), 5–9, DOI: 10.1109/LGRS.2013.2244060.

Chen D., Stow D.A., and Gong P. (2004). Examining The Effect of Spatial Resolution and Texture Window Size on Classification Accuracy: An Urban Environment Case. International Journal of Remote Sensing, 25, 2177–2192, DOI: 10.1080/01431160310001618464.

De Luca G., Silva J.M.N., and Modica G. (2021). A Workflow Based on Sentinel-1 SAR Data and Open-Source Algorithms for Unsupervised Burned Area Detection in Mediterranean Ecosystems. GIScience & Remote Sensing, 58(4), 516-541, DOI: 10.1080/15481603.2021.1907896.

Dekker R.J. (2003). Texture Analysis and Classification of ERS SAR Images for Map Updating of Urban Areas in The Netherlands. IEEE Trans. Geosci. Remote Sensing, 41(9), 1950–1958, DOI: 10.1109/TGRS.2003.814628.

Dorigo W., Lucieer A., Podobnikar T., and Čarni A. (2012). Mapping Invasive Fallopia Japonica by Combined Spectral, Spatial, and Temporal Analysis of Digital Orthophotos. International Journal of Applied Earth Observation and Geoinformation, 19, 185–195, DOI: 10.1016/j.jag.2012.05.004.

Efransjah., Murniningtyas S., Muttaqin M.Z., eds., (2022). The state of Indonesia’s Forests 2022. Jakarta: Ministry of Environtment and Forestry.

Efransjah., Murniningtyas S., Erwinsyah., and Damayanti, E.K., eds., (2020). The state of Indonesia’s Forests 2020. Jakarta: Ministry of Environtment and Forestry.

Emery W.J. and Camps A. (2017). Introduction to Satellite Remote Sensing: Atmosphere, Ocean, Land and Cryosphere Applications. Amsterdam, Netherlands: Elsevier, DOI: 10.1016/C2015-0-04517-8.

Gaveau D.L.A., Descals A., Salim M.A., Sheil D., and Sloan S. (2021). Refined Burned-Area Mapping Protocol Using Sentinel-2 Data Increases Estimate of 2019 Indonesian Burning. Earth System Science Data, 13(11), 5353–5368, DOI: 10.5194/essd-13-5353-2021.

Gibson R. K., Mitchell A., and Chang H.C. (2023). Image texture analysis enhances classification of fire extent and severity using Sentinel 1 and 2 satellite imagery. Remote Sensing, 15(14), 3512, DOI: 10.3390/rs15143512.

Guidic, D. and Clark M. (2017). One-Dimensional Convolutional Neural Network Land-Cover Classification of Multi-Seasonal Hyperspectral Imagery in The San Francisco Bay Area, California. Remote Sensing, 9(6), 629, DOI: 10.3390/rs9060629.

Ho A.F.W., Zheng H., Earnest A., Cheong K.H., Pek P.P., Seok J.Y., Liu N., Kwan Y.H., Tan J.W.C., Wong T.H., Hausenloy D.J., Foo L.L., Tan B.Y.Q., and Ong M.E.H. (2019). Time-Stratified Case Crossover Study of The Association of Outdoor Ambient Air Pollution with The Risk of Acute Myocardial Infarction in The Context of Seasonal Exposure to The Southeast Asian Haze Problem. Journal of the American Heart Association, 8(6), e011272, DOI: 10.1161/JAHA.118.011272.

Hossain A.K.M.A. and Easson G. (2009). Microwave remote sensing of soil moisture in semi-arid environment. InTech, DOI: 10.5772/8301.

Hosseini M. and Lim S. (2023). Burned Area Detection Using Sentinel-1 SAR Data: A Case Study of Kangaroo Island, South Australia. Applied Geography, 151, 102854, DOI: 10.1016/j.apgeog.2022.102854.

Ismail A.S., Gao X., and Deng C. (2014). SAR Image Classification Based on Texture Feature Fusion. 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP), 153-156, DOI: 10.1109/ChinaSIP.2014.6889221.

James J., Heddallikar A., Choudhari P., and Chopde S. (2021). Analysis of Features in SAR Imagery Using GLCM Segmentation Algorithm. In: G.K.Verma, B. Soni, S. Bourennane, and A.C.B. Ramos, eds., Transactions on Computer Systems and Networks Data Science: Theory, Algorithms, And Applications. Singapore: Springer Singapore, 253-266, DOI: 10.1007/978-981-16-1681-5.

Kiranyaz S., Avci O., Abdeljaber O., Ince T., Gabbouj M., and Inman D.J. (2021). 1D Convolutional Neural Networks and Applications: A Survey. Mechanical Systems and Signal Processing, 151, 107398, DOI: 10.1016/j.ymssp.2020.107398.

Landis J.R. and Koch G.G. (1977). The Measurement of Observer Agreement for Categorical Data. Biometrics, 33(1), 159-174.

Lasaponara R. and Tucci B. (2019). Identification of Burned Areas and Severity Using SAR Sentinel-1. IEEE Geosci. Remote Sensing Lett., 16(6), 917–921, DOI: 10.1109/LGRS.2018.2888641.

LeCun Y., Bengio Y., and Hinton G. (2015). Deep Learning. Nature, 521(7553), 436–444, DOI: 10.1038/nature14539.

Lestari A.I., Rizkinia M., and Sudiana D. (2021). Evaluation of Combining Optical and SAR Imagery for Burned Area Mapping Using Machine Learning. 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), 52-59, DOI: 10.1109/CCWC51732.2021.9376117.

Luft H., Schillaci C., Ceccherini G., Vieira D., and Lipani A. (2022). Deep Learning Based Burnt Area Mapping Using Sentinel 1 for The Santa Cruz Mountains Lightning Complex (CZU) and Creek Fires 2020. Fire, 5(5), 163, DOI: 10.3390/fire5050163.

Mandal D., Kumar V., Ratha D., Dey S., Bhattacharya A., Lopez-Sanchez J.M., McNairn H., and Rao Y.S. (2020). Dual Polarimetric Radar Vegetation Index for Crop Growth Monitoring Using Sentinel-1 SAR Data. Remote Sensing of Environment, 247,111954, DOI: 10.1016/j.rse.2020.111954.

Ministry of Environment and Forestry (MoEF) Republic of Indonesia. (2019). Recapitulation of Forest and Land Fire Area (Ha) per Province in Indonesia. (in Indonesian). [online] Available at: https://sipongi.menlhk.go.id/ [Accessed 21 Apr 2023].

Molin S. and Jee K. (2021). Hands-On Data Analysis with Pandas: A Python Data Science Handbook for Data Collection, Wrangling, Analysis, and Visualization. Birmingham: Packt Publishing.

Mullissa A.G., Marcos D., Tuia D., Herold M., and Reiche J. (2022). deSpeckNet: Generalizing Deep Learning-Based SAR Image Despeckling. IEEE Trans. Geosci. Remote Sensing, 60, 1–15, DOI: 10.1109/TGRS.2020.3042694.

Murashkin D., Spreen G., Huntemann M., and Dierking W. (2018). Method for Detection of Leads from Sentinel-1 SAR Images. Ann. Glaciol., 59,124–136, DOI: 10.1017/aog.2018.6.

Mutai, S.C. (2019). Analysis of Burnt Scar Using Optical and Radar Satellite Data. Master thesis. Enschede: University of Twente.

Nguyen L.S.P., Chang J.H.W., Griffith S.M., Hien T.T., Kong S.S.K., Le H.N., Huang, H.Y., Sheu, G.R., and Lin, N.H. (2022). Trans-Boundary Air Pollution in A Southeast Asian Megacity: Case Studies of The Synoptic Meteorological Mechanisms and Impacts on Air Quality. Atmospheric Pollution Research, 13, 101366, DOI: 10.1016/j.apr.2022.101366.

Periasamy, S. (2018). Significance of Dual Polarimetric Synthetic Aperture Radar in Biomass Retrieval: An Attempt on Sentinel-1. Remote Sensing of Environment, 217, 537–549, DOI: https://doi.org/10.1016/j.rse.2018.09.003.

Radman A., Shah-Hosseini R., and Homayouni S. (2023). An Unsupervised Saliency-Guided Deep Convolutional Neural Network for Accurate Burn Mapping from Sentinel-1 SAR Data. Remote Sensing, 15(5), 1184, DOI: 10.3390/rs15051184.

Sakti A.D., Anggraini T.S., Ihsan K.T.N., Misra P., Trang N.T.Q., Pradhan B., Wenten I.G., Hadi P.O., and Wikantika K. (2023). Multi-Air Pollution Risk Assessment in Southeast Asia Region Using Integrated Remote Sensing and Socio-Economic Data Products. Science of The Total Environment. 854, 158825, DOI: 10.1016/j.scitotenv.2022.158825.

Singh M. and Kaur G. (2011). SAR Image Classification Using PCA and Texture Analysis. In: Das, V.V., Thomas, G., Lumban Gaol, F., eds., Information Technology and Mobile Communication, Communications in Computer and Information Science. Heidelberg: Springer Berlin., 435-439, DOI: 10.1007/978-3-642-20573-6_78.

Small D. (2011). Flattening Gamma: Radiometric Terrain Correction for SAR Imagery. IEEE Trans. Geosci. Remote Sensing, 49(8), 3081– 3093, DOI: 10.1109/TGRS.2011.2120616.

Soh L.K. and Tsatsoulis C. (1999). Texture Analysis of SAR Sea Ice Imagery Using Gray Level Co-Occurrence Matrices. IEEE Trans. Geosci. Remote Sensing, 37(2),780–795.

Song Y., Zhang Z., Baghbaderani R.K., Wang F., Qu Y., Stuttsy, C., and Qi H. (2019). Land Cover Classification for Satellite Images Through 1D CNN, 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), 1-5, DOI: 10.1109/WHISPERS.2019.8921180.

Gupta D. K., Prashar S., Singh S., Srivastava, P.K., and Prasad, R. (2022). Introduction to Radar Remote Sensing. In: P.K. Srivastava, D.K. Gupta, T. Islam, D. Han, and R. Prasad, eds., Radar Remote Sensing: Applications and Challenges, Earth Observation Series. Amsterdam: Elsevier, 3-27, DOI: 10.1016/B978-0-12-823457-0.00018-5

Statistics Indonesia. (2010). Kapuas in Figures 2010. Kuala Kapuas, Kapuas: Statistic of Kapuas Regency.

Statistics Indonesia. (2023). Pulang Pisau Regency in Figures 2023. Kahayan Hilir, Pulang Pisau: Statistics of Pulang Pisau Regency.

Sudiana D., Lestari A.I., Riyanto I., Rizkinia M., Arief R., Prabuwono A.S., and Sumantyo J.T.S. (2023) A Hybrid Convolutional Neural Network and Random Forest for Burned Area Identification with Optical and Synthetic Aperture Radar (SAR) Data. Remote Sensing, 15(3), 728, DOI: 10.3390/rs15030728.

Tanase M.A., Belenguer-Plomer M.A., Roteta E., Bastarrika A., Wheeler J., Fernández-Carrillo Á., Tansey K., Wiedemann W., Navratil P., Lohberger S., Siegert F., and Chuvieco E. (2020). Burned Area Detection and Mapping: Intercomparison of Sentinel-1 and Sentinel-2 Based Algorithms Over Tropical Africa. Remote Sensing, 12(2), 334, DOI: 10.3390/rs12020334.

Tanase M.A., Santoro M., Riva J.D.L., Pérez-Cabello F., and Toan T.L. (2010). Sensitivity of X-, C-, And L-Band SAR Backscatter to Burn Severity in Mediterranean Pine Forests. IEEE Transactions on Geoscience and Remote Sensing, 48(10), 3663-3675, DOI: 10.1109/TGRS.2010.2049653.

Wen C., ZhangY., and Deng K. (2009). Urban Area Classification in High Resolution SAR Based on Texture Features. The International Conference on Geo-spatial Solutions for Emergency Management and the 50th Anniversary of the Chinese Academy of Surveying and Mapping, Beijing, China, 281-285.

Xie J., Li Z., Zhou C., Fang Y., and Zhang Q. (2018). Speckle Filtering of GF-3 Polarimetric SAR Data with Joint Restriction Principle. Sensors, 18(5), 1533, DOI: 10.3390/s18051533.

Yahia M., Ali T., Mortula M.M., Abdelfattah R., Mahdy S.E., and Arampola N.S. (2020). Enhancement of SAR Speckle Denoising Using The Improved Iterative Filter. IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing, 13, 859–871, DOI: 10.1109/JSTARS.2020.2973920.

Yeung J. (2019) Indonesian forests are burning, and Malaysia and Singapore are choking on the fumes. [online] Available at: https://www.huahintoday.com/sports/indonesian-forests-still-burning-and-malaysia-and-singapore-are-choking-on-the-fumes/#:~:text=More%20than%20930%2C000%20hectares%20%28about%202.3%20million%20acres%29,all%20week%2C%20with%20air%20quality%20reaching%20unhealthy%20levels [Accessed 20 June 2023].

ZhangC.,PanX.,LiH.,GardinerA.,SargentI.,HareJ.,andAtkinsonP.M.(2018).AHybridMLP-CNNClassifierforVeryFineResolutionRemotely Sensed Image Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 140,133–144, DOI: 10.1016/j.isprsjprs.2017.07.014

The authors declare that there are no conflicts of interest present.