學術產出-Theses
Article View/Open
Publication Export
-
題名 應用多元遙測影像偵測叢林火災之評估
Evaluation of Bushfire Detection Methods with Remote Sensing Imagery作者 尤琪
Yu, Chi貢獻者 林士淵
Lin, Shih-Yuan
尤琪
Yu, Chi關鍵詞 火災偵測
遙感探測
影像分類
隨機森林
投票集成
Bushfire detection
Remote sensing
Image classification
Random forest
Voting method日期 2024 上傳時間 1-Mar-2024 13:58:51 (UTC+8) 摘要 近幾十年來，森林火災事件變得更加頻繁、持續時間更長且更加嚴峻。本研究收集了2019/20年澳洲黑色夏季森林大火（Black Summer Bushfire）期間的遙測資料，包括Sentinel-1 雷達影像、ASTER DEM以及MODIS產品產製的NDVI影像和LST資料，並將之組成為五個不同的波段組合，包括SAR+DEM、NDVI ratio、LST等三種基本組合；以及 SAR+DEM+NDVI ratio和 SAR+DEM+LST 兩個集成組合。我們利用這五個波段組合，透過隨機森林（random forest）和投票集成（voting）方法進行兩步驟影像分類，對已燒、新燃燒和未燒的三種火災狀況進行分類。分類分析結果發現， SAR+DEM+LST組合是最有效的組合，其分類結果圖具有高空間解析度，並且所有總體精度均超過 90%。另一方面，若以分類效率進行評估，LST是最有效率的組合，因為其無需經過投票分類過程即可提供可接受的結果。
In recent decades, the bushfire events become more frequent, lasting longer, and accompanied with unbearable severity. The present study collects the remote sensing data of Black Summer Bushfire in Australia acquired in the period of 2019/20, including Sentinel-1 SAR imagery, ASTER DEM data, and NDVI images and LST data generated from MODIS products. The data are further combined into five different band combinations including three basic combinations of SAR+DEM, NDVI ratio, and LST; and two merged combinations of SAR+DEM+NDVI ratio and SAR+DEM+LST. The five band combinations are used to classify fire conditions of burned, new burning, and non-burned by two-step classification through random forest and voting methods. According to the analysis result, the SAR+DEM+LST combination is the most effective combination when we evaluate by the result maps and confusion matrices. It generates the maps with high spatial resolution, and also, all of the classification accuracies are over 90%. On the other hand, the LST is the most efficient combination which can provide satisfactory result without the voting process.參考文獻 詹靜怡，2012，「以衛星遙測多光譜影像探討台中環山地區森林火燒嚴重度分類及植生恢復」，國立屏東科技大學森林系碩士學位論文：屏東。 劉良明、鄢俊潔，2004，「MODIS 數據在火災監測中的應用」，『武漢大學學報』，29(1)：55-57。 謝巧柔、蘇潘、林政侑，2016，「應用環境指標萃取火燒潛勢區位之研究」，『水土保持學報』，48 (3): 1789–1802。 謝依達、鍾玉龍、廖晟淞、余曜光、鄧國禎、吳守從，2011，「以變遷偵測技術探討高解析力數值航攝影像於森林火災自動製圖之應用」，『航測及遙測學刊』，16(1): 11-22。 Abram, N. J., Henley, B. J., Sen Gupta, A., Lippmann, T. J. R., Clarke, H., Dowdy, A. J., Sharples, J. J., Nolan, R. H., Zhang, T., Wooster, M. J., Wurtzel, J. B., Meissner, K. J., Pitman, A. J., Ukkola, A. M., Murphy, B. P., Tapper, N. J., & Boer, M. M. (2021). Connections of climate change and variability to large and extreme forest fires in southeast Australia. Communications Earth & Environment, 2(1). Ajadi, O., Meyer, F., & Webley, P. (2016). Change Detection in Synthetic Aperture Radar Images Using a Multiscale-Driven Approach. Remote Sensing, 8(6). Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. Borchers Arriagada, N., Palmer, A. J., Bowman, D. M., Morgan, G. G., Jalaludin, B. B., & Johnston, F. H. (2020). Unprecedented smoke-related health burden associated with the 2019-20 bushfires in eastern Australia. Med J Aust, 213(6), 282-283. Bourgeau‐Chavez, L. L., Kasischke, E. S., Riordan, K., Brunzell, S., Nolan, M., Hyer, E., Slawski, J., Medvecz, M., Walters, T., & Ames, S. (2007). Remote monitoring of spatial and temporal surface soil moisture in fire disturbed boreal forest ecosystems with ERS SAR imagery. International Journal of Remote Sensing, 28(10), 2133-2162. Breiman, L. (2001). Random Forests. Machine Learning 45, 5–32. Cao, X., Chen, J., Matsushita, B., Imura, H., & Wang, L. (2009). An automatic method for burn scar mapping using support vector machines. International Journal of Remote Sensing, 30(3), 577-594. Colesanti, C., & Wasowski, J. (2006). Investigating landslides with space-borne Synthetic Aperture Radar (SAR) interferometry. Engineering Geology, 88(3-4), 173-199. Giglio, L., Schroeder, W., & Justice, C. O. (2016). The collection 6 MODIS active fire detection algorithm and fire products. Remote Sens Environ, 178, 31-41. Gigović L, Pourghasemi HR, Drobnjak S, Bai S. (2019). Testing a New Ensemble Model Based on SVM and Random Forest in Forest Fire Susceptibility Assessment and Its Mapping in Serbia’s Tara National Park. Forests, 10(5):408. Haghani, M., Kuligowski, E., Rajabifard, A., & Kolden, C. A. (2022). The state of wildfire and bushfire science: Temporal trends, research divisions and knowledge gaps. Safety Science, 153. Key, C. & Benson, N. (2005). Landscape Assessment (LA) Sampling and Analysis Methods. Malik, A., Jalin, N., Rani, S., Singhal, P., Jain, S., & Gao, J. (2021). Wildfire Risk Prediction and Detection using Machine Learning in San Diego, California 2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation Lee, I. K., Trinder, J. C., & Sowmya, A. (2020). Application of U-Net Convolutional Neural Network to Bushfire Monitoring in Australia with Sentinel-1/-2 Data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2020, 573-578. Lozano, O. M., Salis, M., Ager, A. A., Arca, B., Alcasena, F. J., Monteiro, A. T., Finney, M. A., Del Giudice, L., Scoccimarro, E., & Spano, D. (2017). Assessing Climate Change Impacts on Wildfire Exposure in Mediterranean Areas. Risk Anal, 37(10), 1898-1916. Martinis S., Caspard M., Plank S., Clandillon S. & Haouet S. (2017). Mapping burn scars, fire severity and soil erosion susceptibility in Southern France using multisensoral satellite data. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 1099-1102. Rignot, E. J. M. & van Zyl, J. J. (1993). Change Detection Techniques for ERS-1 SAR Data. IEEE Transactions on Geoscience and Remote Sensing, 31(4): 896-906. Rykhus, R., & Lu, Z. (2011). Monitoring a boreal wildfire using multi-temporal Radarsat-1 intensity and coherence images. Geomatics, Natural Hazards and Risk, 2(1), 15-32. Schroeder, W., Oliva, P., Giglio, L., Quayle, B., Lorenz, E., & Morelli, F. (2016). Active fire detection using Landsat-8/OLI data. Remote Sensing of Environment, 185, 210-220. Stevens-Rumann, C. and Morgan, P. (2016), Repeated wildfires alter forest recovery of mixed-conifer ecosystems. Ecol Appl, 26: 1842-1853. Stroppiana, D., Azar, R., Calò, F., Pepe, A., Imperatore, P., Boschetti, M., Silva, J., Brivio, P., & Lanari, R. (2015). Integration of Optical and SAR Data for Burned Area Mapping in Mediterranean Regions. Remote Sensing, 7(2), 1320-1345. Takeuchi S.&Yamada S. (2002). Monitoring of forest fire damage by using JERS-1 InSAR. IEEE International Geoscience and Remote Sensing Symposium, 6, 3290-3292. Yun, H. W., Kim, J. R., Choi, Y. S., & Lin, S. Y. (2019). Analyses of Time Series InSAR Signatures for Land Cover Classification: Case Studies over Dense Forestry Areas with L-Band SAR Images. Sensors (Basel), 19(12). Zennir, R., & Khallef, B. (2023). Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest ‒ Algeria. Journal of Forest Science, 69(1), 33-40. Zhang, P., Ban, Y., & Nascetti, A. (2021). Learning U-Net without forgetting for near real-time wildfire monitoring by the fusion of SAR and optical time series. Remote Sensing of Environment, 261. Zhang, P., Nascetti, A., Ban, Y., & Gong, M. (2019). An implicit radar convolutional burn index for burnt area mapping with Sentinel-1 C-band SAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 158, 50-62. 描述 碩士
國立政治大學
地政學系
111257005資料來源 http://thesis.lib.nccu.edu.tw/record/#G0111257005 資料類型 thesis dc.contributor.advisor 林士淵 zh_TW dc.contributor.advisor Lin, Shih-Yuan en_US dc.contributor.author (Authors) 尤琪 zh_TW dc.contributor.author (Authors) Yu, Chi en_US dc.creator (作者) 尤琪 zh_TW dc.creator (作者) Yu, Chi en_US dc.date (日期) 2024 en_US dc.date.accessioned 1-Mar-2024 13:58:51 (UTC+8) - dc.date.available 1-Mar-2024 13:58:51 (UTC+8) - dc.date.issued (上傳時間) 1-Mar-2024 13:58:51 (UTC+8) - dc.identifier (Other Identifiers) G0111257005 en_US dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150223 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 地政學系 zh_TW dc.description (描述) 111257005 zh_TW dc.description.abstract (摘要) 近幾十年來，森林火災事件變得更加頻繁、持續時間更長且更加嚴峻。本研究收集了2019/20年澳洲黑色夏季森林大火（Black Summer Bushfire）期間的遙測資料，包括Sentinel-1 雷達影像、ASTER DEM以及MODIS產品產製的NDVI影像和LST資料，並將之組成為五個不同的波段組合，包括SAR+DEM、NDVI ratio、LST等三種基本組合；以及 SAR+DEM+NDVI ratio和 SAR+DEM+LST 兩個集成組合。我們利用這五個波段組合，透過隨機森林（random forest）和投票集成（voting）方法進行兩步驟影像分類，對已燒、新燃燒和未燒的三種火災狀況進行分類。分類分析結果發現， SAR+DEM+LST組合是最有效的組合，其分類結果圖具有高空間解析度，並且所有總體精度均超過 90%。另一方面，若以分類效率進行評估，LST是最有效率的組合，因為其無需經過投票分類過程即可提供可接受的結果。 zh_TW dc.description.abstract (摘要) In recent decades, the bushfire events become more frequent, lasting longer, and accompanied with unbearable severity. The present study collects the remote sensing data of Black Summer Bushfire in Australia acquired in the period of 2019/20, including Sentinel-1 SAR imagery, ASTER DEM data, and NDVI images and LST data generated from MODIS products. The data are further combined into five different band combinations including three basic combinations of SAR+DEM, NDVI ratio, and LST; and two merged combinations of SAR+DEM+NDVI ratio and SAR+DEM+LST. The five band combinations are used to classify fire conditions of burned, new burning, and non-burned by two-step classification through random forest and voting methods. According to the analysis result, the SAR+DEM+LST combination is the most effective combination when we evaluate by the result maps and confusion matrices. It generates the maps with high spatial resolution, and also, all of the classification accuracies are over 90%. On the other hand, the LST is the most efficient combination which can provide satisfactory result without the voting process. en_US dc.description.tableofcontents 謝誌 i 摘要 ii Abstract iii Content iv Figures vi Tables ix Chapter 1 Introduction 1 1.1 Background and motivation 1 1.2 Purposes of the research 4 1.3 Dissertation structure 4 2 Remote sensing approaches 6 2.1 Multispectral imagery 7 2.1.1 Vegetation index 7 2.1.2 Detecting through infrared band data 10 2.2 Synthetic aperture radar 11 2.2.1 Amplitude 11 2.2.2 Phase coherence 13 2.3 Summary 15 3 Methodology 16 3.1 Study area 16 3.2 Materials and tools 17 3.2.1 Materials 17 3.2.1.1 SAR imagery 17 3.2.1.2 MODIS products 18 3.2.1.3 Digital Elevation Model (DEM) 20 3.2.2 Tools 21 3.2.2.1 Sentinel Application Platform 21 3.2.2.2 Google Earth Engine 21 3.2.2.3 ArcGIS Pro 21 3.3 Research Design 22 3.3.1 Data preprocessing 25 3.3.1.1 Remote sensing data preprocessing 25 3.3.1.2 Automatic training and validation data generation 31 3.3.2 Image classification 33 4 Results and discussion 38 4.1 Data collection and preprocessing 38 4.2 Classification results of basic band sets 48 4.2.1 SAR + DEM 48 4.2.1.1 Two-class classification of SAR + DEM sets 48 4.2.1.2 Three-class classification of SAR + DEM sets 51 4.2.1.3 Summary 54 4.2.2 NDVI ratio 55 4.2.2.1 Two-class classification of NDVI ratio sets 55 4.2.2.2 Three-class classification of NDVI ratio sets 58 4.2.2.3 Summary 60 4.2.3 LST 61 4.2.3.1 Two-class classification of LST set 62 4.2.3.2 Three-class classification of LST sets 64 4.2.3.3 Summary 67 4.3 Classification results of merged band sets 68 4.3.1 SAR + DEM + NDVI ratio 68 4.3.2 SAR + DEM + LST 81 4.4 Discussion 94 5 Conclusions 97 Reference 100 zh_TW dc.format.extent 33005826 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0111257005 en_US dc.subject (關鍵詞) 火災偵測 zh_TW dc.subject (關鍵詞) 遙感探測 zh_TW dc.subject (關鍵詞) 影像分類 zh_TW dc.subject (關鍵詞) 隨機森林 zh_TW dc.subject (關鍵詞) 投票集成 zh_TW dc.subject (關鍵詞) Bushfire detection en_US dc.subject (關鍵詞) Remote sensing en_US dc.subject (關鍵詞) Image classification en_US dc.subject (關鍵詞) Random forest en_US dc.subject (關鍵詞) Voting method en_US dc.title (題名) 應用多元遙測影像偵測叢林火災之評估 zh_TW dc.title (題名) Evaluation of Bushfire Detection Methods with Remote Sensing Imagery en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 詹靜怡，2012，「以衛星遙測多光譜影像探討台中環山地區森林火燒嚴重度分類及植生恢復」，國立屏東科技大學森林系碩士學位論文：屏東。 劉良明、鄢俊潔，2004，「MODIS 數據在火災監測中的應用」，『武漢大學學報』，29(1)：55-57。 謝巧柔、蘇潘、林政侑，2016，「應用環境指標萃取火燒潛勢區位之研究」，『水土保持學報』，48 (3): 1789–1802。 謝依達、鍾玉龍、廖晟淞、余曜光、鄧國禎、吳守從，2011，「以變遷偵測技術探討高解析力數值航攝影像於森林火災自動製圖之應用」，『航測及遙測學刊』，16(1): 11-22。 Abram, N. J., Henley, B. J., Sen Gupta, A., Lippmann, T. J. R., Clarke, H., Dowdy, A. J., Sharples, J. J., Nolan, R. H., Zhang, T., Wooster, M. J., Wurtzel, J. B., Meissner, K. J., Pitman, A. J., Ukkola, A. M., Murphy, B. P., Tapper, N. J., & Boer, M. M. (2021). Connections of climate change and variability to large and extreme forest fires in southeast Australia. Communications Earth & Environment, 2(1). Ajadi, O., Meyer, F., & Webley, P. (2016). Change Detection in Synthetic Aperture Radar Images Using a Multiscale-Driven Approach. Remote Sensing, 8(6). Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. Borchers Arriagada, N., Palmer, A. J., Bowman, D. M., Morgan, G. G., Jalaludin, B. B., & Johnston, F. H. (2020). Unprecedented smoke-related health burden associated with the 2019-20 bushfires in eastern Australia. Med J Aust, 213(6), 282-283. Bourgeau‐Chavez, L. L., Kasischke, E. S., Riordan, K., Brunzell, S., Nolan, M., Hyer, E., Slawski, J., Medvecz, M., Walters, T., & Ames, S. (2007). Remote monitoring of spatial and temporal surface soil moisture in fire disturbed boreal forest ecosystems with ERS SAR imagery. International Journal of Remote Sensing, 28(10), 2133-2162. Breiman, L. (2001). Random Forests. Machine Learning 45, 5–32. Cao, X., Chen, J., Matsushita, B., Imura, H., & Wang, L. (2009). An automatic method for burn scar mapping using support vector machines. International Journal of Remote Sensing, 30(3), 577-594. Colesanti, C., & Wasowski, J. (2006). Investigating landslides with space-borne Synthetic Aperture Radar (SAR) interferometry. Engineering Geology, 88(3-4), 173-199. Giglio, L., Schroeder, W., & Justice, C. O. (2016). The collection 6 MODIS active fire detection algorithm and fire products. Remote Sens Environ, 178, 31-41. Gigović L, Pourghasemi HR, Drobnjak S, Bai S. (2019). Testing a New Ensemble Model Based on SVM and Random Forest in Forest Fire Susceptibility Assessment and Its Mapping in Serbia’s Tara National Park. Forests, 10(5):408. Haghani, M., Kuligowski, E., Rajabifard, A., & Kolden, C. A. (2022). The state of wildfire and bushfire science: Temporal trends, research divisions and knowledge gaps. Safety Science, 153. Key, C. & Benson, N. (2005). Landscape Assessment (LA) Sampling and Analysis Methods. Malik, A., Jalin, N., Rani, S., Singhal, P., Jain, S., & Gao, J. (2021). Wildfire Risk Prediction and Detection using Machine Learning in San Diego, California 2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation Lee, I. K., Trinder, J. C., & Sowmya, A. (2020). Application of U-Net Convolutional Neural Network to Bushfire Monitoring in Australia with Sentinel-1/-2 Data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2020, 573-578. Lozano, O. M., Salis, M., Ager, A. A., Arca, B., Alcasena, F. J., Monteiro, A. T., Finney, M. A., Del Giudice, L., Scoccimarro, E., & Spano, D. (2017). Assessing Climate Change Impacts on Wildfire Exposure in Mediterranean Areas. Risk Anal, 37(10), 1898-1916. Martinis S., Caspard M., Plank S., Clandillon S. & Haouet S. (2017). Mapping burn scars, fire severity and soil erosion susceptibility in Southern France using multisensoral satellite data. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 1099-1102. Rignot, E. J. M. & van Zyl, J. J. (1993). Change Detection Techniques for ERS-1 SAR Data. IEEE Transactions on Geoscience and Remote Sensing, 31(4): 896-906. Rykhus, R., & Lu, Z. (2011). Monitoring a boreal wildfire using multi-temporal Radarsat-1 intensity and coherence images. Geomatics, Natural Hazards and Risk, 2(1), 15-32. Schroeder, W., Oliva, P., Giglio, L., Quayle, B., Lorenz, E., & Morelli, F. (2016). Active fire detection using Landsat-8/OLI data. Remote Sensing of Environment, 185, 210-220. Stevens-Rumann, C. and Morgan, P. (2016), Repeated wildfires alter forest recovery of mixed-conifer ecosystems. Ecol Appl, 26: 1842-1853. Stroppiana, D., Azar, R., Calò, F., Pepe, A., Imperatore, P., Boschetti, M., Silva, J., Brivio, P., & Lanari, R. (2015). Integration of Optical and SAR Data for Burned Area Mapping in Mediterranean Regions. Remote Sensing, 7(2), 1320-1345. Takeuchi S.&Yamada S. (2002). Monitoring of forest fire damage by using JERS-1 InSAR. IEEE International Geoscience and Remote Sensing Symposium, 6, 3290-3292. Yun, H. W., Kim, J. R., Choi, Y. S., & Lin, S. Y. (2019). Analyses of Time Series InSAR Signatures for Land Cover Classification: Case Studies over Dense Forestry Areas with L-Band SAR Images. Sensors (Basel), 19(12). Zennir, R., & Khallef, B. (2023). Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest ‒ Algeria. Journal of Forest Science, 69(1), 33-40. Zhang, P., Ban, Y., & Nascetti, A. (2021). Learning U-Net without forgetting for near real-time wildfire monitoring by the fusion of SAR and optical time series. Remote Sensing of Environment, 261. Zhang, P., Nascetti, A., Ban, Y., & Gong, M. (2019). An implicit radar convolutional burn index for burnt area mapping with Sentinel-1 C-band SAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 158, 50-62. zh_TW
