تعداد نشریات | 161 |
تعداد شمارهها | 6,532 |
تعداد مقالات | 70,501 |
تعداد مشاهده مقاله | 124,105,774 |
تعداد دریافت فایل اصل مقاله | 97,211,231 |
ارزیابی عملکرد پردازش تکزمانه و چندزمانۀ تصاویر ماهوارۀ لندست 8 مبتنی بر طبقهبندیکنندههای ماشین بردار پشتیبان و جنگل تصادفی در پایش آتشسوزی جنگلها | ||
مدیریت مخاطرات محیطی | ||
دوره 8، شماره 2، شهریور 1400، صفحه 119-135 اصل مقاله (1 M) | ||
نوع مقاله: پژوهشی کاربردی | ||
شناسه دیجیتال (DOI): 10.22059/jhsci.2021.321494.640 | ||
نویسندگان | ||
نادیا عباس زاده طهرانی* 1؛ آذر مروتی2؛ سارا خانبانی3؛ میلاد جانعلی پور1 | ||
1استادیار پژوهشگاه هوافضا، وزارت علوم، تحقیقات و فناوری، تهران، ایران | ||
2دانشجوی کارشناسی ارشد دانشگاه آزاد اسلامی واحد جنوب | ||
3دانشجوی دکتری فتوگرامتری دانشگاه تهران، تهران، ایران | ||
چکیده | ||
پدیدۀ آتشسوزی جنگلها، از مخاطرات محیط زیستی مهم محسوب میشود. دادههای ماهوارۀ لندست 8 با توان تفکیک مکانی متوسط و دسترسی آسان از منابع مهم در زمینۀ پایش آتشسوزیهای گسترده است. هدف این مقاله ارزیابی رویکرد تکزمانه و دوزمانه مبتنی بر تصویر حین آتشسوزی و تصاویر قبل و بعد از آتشسوزی از ماهوارۀ لندست 8 و طبقهبندیکنندههای ماشین بردار پشتیبان و جنگل تصادفی برای شناسایی آتشسوزی جنگلهاست. نتایج پردازش تصاویر ماهوارهای جنگلهای پارادایز منطقۀ ساکرامنتو در ایالت کالیفرنیا، نشان داد که روش طبقهبندی جنگل تصادفی بر روی دادۀ تکزمانه حین آتشسوزی با صحت کلی 83/99 درصد، در مقایسه با روش ماشین بردار پشتیبان با صحت کلی 53/99 درصد، توانایی بیشتری برای تفکیک آتش از غیر آتش دارد. البته در هر دو روش، صحت کلی زیاد است که مؤید مطلوبیت استفاده از هر دو روش برای تشخیص مخاطرۀ آتشسوزی است. همچنین عملکرد طبقهبندی تصویر تکزمانه بعد از آتشسوزی، بهتر از تصاویر دوزمانۀ قبل و بعد از آتشسوزی بوده است. | ||
کلیدواژهها | ||
طبقهبندی ماشین بردار پشتیبان؛ طبقهبندی جنگل تصادفی؛ ماهوارۀ لندست 8؛ مخاطرۀ آتشسوزی | ||
عنوان مقاله [English] | ||
Evaluating Performance of Support Vector Machine and Random Forest Classifiers in Monitoring Wildfire from pre- and post-event Landsat8 satellite Images | ||
نویسندگان [English] | ||
Nadia Abbaszadeh Tehrani1؛ Azar Morovati2؛ Sara Khanbani3؛ Milad Janalipour1 | ||
1Assistant professor at Aerospace Research Institute | ||
2Graduated in Remote Sensing Engineering | ||
3PhD student in Photogrammetry, University of Tehran | ||
چکیده [English] | ||
Occurrence of wildfires in forests is one of the important environmental hazards. Remote sensing is one of the useful sources for detecting and monitoring wildfires. The purpose of this paper is to evaluate "during fire" image and "before and after fire" images from Landsat8 satellite in identifying fire areas using Support Vector Machine (SVM) and Random Forest (RF) classifiers. Based on the analysis of the output from the images of the Sacramento area in the state of California, it was found that RF classification method with an overall accuracy of 99.83%, compared to the SVM method with an overall accuracy of 99.53%, has a better ability to distinguish fire from non-fire areas. It should be noted that in both methods, the overall accuracy was considerable and indicated their desirability to wildfire detection. Moreover, the classification results with a “single image” input during a fire were better than the “difference image” input. | ||
کلیدواژهها [English] | ||
wildfire detection, Support Vector Machine (SVM), Random Forest (RF), Landsat 8 | ||
مراجع | ||
]1[ جانعلیپور، میلاد؛ عباسزاده طهرانی، نادیا؛ محمدخانلو، حکمتالله؛ خصالی، الهه؛ و عنایتی، حمید. (1398). «شناسایی سریع مناطق آسیبدیده پس از وقوع زلزله با استفاده از تصاویر ماهوارهای Sentinel-2 (مطالعۀ موردی: زلزلۀ سرپل ذهاب)»، مدیریت مخاطرات محیطی، دوره 6، شمارۀ 2، ص 148-131.
]2[ جدی، علی؛ مقیمی، ابراهیم؛ احمدی، سیدعباس؛ و زارع، مهدی (1398). «راهبرد کاهش مخاطرات طبیعی در ایران برمبنای حقوق و روابط بینالملل»، مدیریت مخاطرات محیطی، دورۀ 6، شماره 1، ص 16-1.
]3[ شاهحیدریپور، علی؛ پهلوانی، پرهام؛ و بیگدلی، بهناز. (1397). «تهیۀ نقشۀ ریسک وقوع آتشسوزی مناطق جنگلی با استفاده از روش رگرسیون انطباقی چندمتغیرۀ اسپیلاین (مطالعۀ موردی: استان گلستان)»، مدیریت مخاطرات محیطی، دورۀ 5، شمارۀ 3، ص 277-256
[4] Abbasszadeh Tehrani, Nadia; & Janalipour, Milad. (2020). “Predicting ecosystem shift in a Salt Lake by using remote sensing indicators and spatial statistics methods (case study: Lake Urmia basin)”, Environmental Engineering Research, no. 26 (4):30-40.
[5] Abbaszadeh Tehrani, Nadia; Shafri, Helmi Zulhaidi Mohd; Salehi, Sara; Chanussot, Jocelyn; & Janalipour, Milad (2021). “Remotely-Sensed Ecosystem Health Assessment (RSEHA) model for assessing the changes of ecosystem health of Lake Urmia Basin”, International Journal of Image and Data Fusion:1-26.
[6] Alkhatib, Ahmad A.A. (2014). “A review on forest fire detection techniques”, International Journal of Distributed Sensor Networks, no. 10 (3).
[7] Allison, Robert S.; Johnston, Joshua M.; Craig, Gregory; & Jennings, Sion (2016). “Airborne optical and thermal remote sensing for wildfire detection and monitoring”, Sensors no. 16 (8).
[8] Anggraeni, Ajeng; & Chinsu, Lin. (2011). “Application of SAM and SVM Techniques to Burned Area Detection for Landsat TM Images in Forests of South Sumatra”, Paper read at International Conference on Environmental Science and Technology.
[9] Babaei, Hadiseh; Janalipour, Milad; & Abbaszadeh Tehrani, Nadia. (2019). “A simple, robust, and automatic approach to extract water body from Landsat images (case study: Lake Urmia, Iran)”, Journal of Water and Climate Change.
[10] Ban, Yifang; Zhang, Puzhao; Nascetti, Andrea; Bevington, Alexandre R.; & Wulder, Michael A. (2020). “Near real-time wildfire progression monitoring with Sentinel-1 SAR time series and deep learning”, Scientific Reports no. 10 (1):1-15.
[11] Bar, Somnath; Parida, Bikash Ranjan; & Pandey, Arvind Chandra (2020). “Landsat-8 and Sentinel-2 based Forest fire burn area mapping using machine learning algorithms on GEE cloud platform over Uttarakhand, Western Himalaya”, Remote Sensing Applications: Society and Environment.
[12] Bruzzone, Lorenzo, & Prieto, Diego F. (2000). “Automatic analysis of the difference image for unsupervised change detection”, IEEE Transactions on Geoscience and Remote sensing, no. 38(3):1171-1182.
[13] Calle, A, JL Casanova, & Romo, A. (2006). “Fire detection and monitoring using MSG Spinning Enhanced Visible and Infrared Imager (SEVIRI) data”, Journal of Geophysical Research: Biogeosciences, no. 111 (G4).
[14] Cervantes, Jair; Farid, Garcia-Lamont; , Lisbeth, Rodriguez-Mazahua; &Asdrubal, Lopez (2020). “A comprehensive survey on support vector machine classification: Applications, challenges and trends”, Neurocomputing, no. 408:189-215.
[15] Chambers, Jeffrey; Gorman, Caralyn; Feng, Yanlei; Torn, Margaret; & Stapp, Jared (2019). “Rapid remote sensing assessment of landscape-scale impacts from the California Camp Fire”,
[16] Chu, Thuan; & Guo, Xulin (2014). “Remote sensing techniques in monitoring post-fire effects and patterns of forest recovery in boreal forest regions: A review”, Remote Sensing, no. 6 (1):470-520.
[17] Chuvieco, Emilio; Aguado, Inmaculada; Salas, Javier; García, Mariano; Yebra, Marta; & Oliva, Patricia (2020). “Satellite remote sensing contributions to wildland fire science and management”, Current Forestry Reports, no. 6 (2):81-96.
[18] Çömert, Resul; MATCI, Dilek Küçük; & Avdan, Uğur (2019). “Object Based Burned Area Mapping with Random Forest Algorithm”, International Journal of Engineering and Geosciences, no. 4 (2):78-87.
[19] de Carvalho, Nathália Silva; Ferreira, Igor José M; Korting, T.S.; Eduardo, L.; Aragao, C.D.; & Anderson, L.O. (2018). “Random forest and support vector machine applied for mapping burned areas in Amazon. Paper read at Proceedings of XIX Brazilian Symposium on Remote Sensing”.
[20] Eisavi, Vahid; & Homayouni, Saeid (2016). “Performance evaluation of random forest and support vector regressions in natural hazard change detection”, Journal of Applied Remote Sensing, no. 10 (4):046030.
[21] Ghavami, Zinat; Arefi, Hossein; Bigdeli, Behnaz; & Janalipour, Milad (2017). “Comprehensive investigation on non-parametric classification methods in order to separate urban objects using the integration of very high spatial resolution LiDAR and aerial data”.
[22] Gigović, Ljubomir; Pourghasemi, Hamid Reza; Drobnjak, Siniša & Bai, Shibiao. (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, no. 10 (5):408.
[23] Hussain, Masroor; Chen, Dongmei; Cheng, Angela; Wei, Hui; & Stanley, David (2013). “Change detection from remotely sensed images: From pixel-based to object-based approaches”, ISPRS Journal of Photogrammetry and Remote Sensing, no. 80:91-106.
[24] Jaafari, Abolfazl; & Pourghasemi, Hamid Reza (2019). “Factors influencing regional-scale wildfire probability in Iran: an application of random forest and support vector machine”, In Spatial modeling in GIS and R for Earth and environmental sciences, 607-619. Elsevier.
[25] Jianya, Gong, Haigang, Sui; Guorui, Ma; & Qiming. Zhou (2008). “A review of multi-temporal remote sensing data change detection algorithms”, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, no. 37 (B7):757-762.
[26] Joachims, Thorsten (1999). “Svmlight: Support vector machine”, SVM-Light Support Vector Machine http://svmlight. joachims. org/, University of Dortmund, no. 19 (4).
[27] Khanbani, Sara, Mohammadzadeh, Ali; & Janalipourm Milad (2020). “A novel unsupervised change detection method from remotely sensed imagery based on an improved thresholding algorithm”, Applied Geomatics:1-17.
[28] Khanbani, Sara; Mohammadzadeh, Ali; & Janalipour, Milad (2020). “Unsupervised change detection of remotely sensed images from rural areas based on using the hybrid of improved Thresholding techniques and particle swarm optimization”, Earth Science Informatics:1-14.
[29] Lafarge, Florent; Descombes, Xavier; & Zerubia, Josiane (2005). “Textural kernel for SVM classification in remote sensing: Application to forest fire detection and urban area extraction”, Paper read at IEEE International Conference on Image Processing 2005.
[30] Liu, Sicong; Zheng, Yongjie; Dalponte, Michele; & Tong, Xiaohua (2020). “A novel fire index-based burned area change detection approach using Landsat-8 OLI data”, European journal of remote sensing, no. 53 (1):104-112.
[31] Lu, Dengsheng; Mausel, Paul; Brondizio, Eduardo; & Moran, Emilio (2004). “Change detection techniques”, International journal of remote sensing, no. 25 (12):2365-2401.
[32] Petropoulos, George P.; Charalambos, Kontoes; & Iphigenia, Keramitsoglou; (2011). “Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using support vector machines”, International Journal of Applied Earth Observation and Geoinformation, no. 13 (1):70-80.
[33] Prakash, Anupma (2000). “Thermal remote sensing: concepts, issues and applications”, International Archives of Photogrammetry and Remote Sensing, no. 33 (B1; PART 1):239-243.
[34] Richards, John Alan; & Richards, J.A. (1999). Remote sensing digital image analysis. Vol. 3: Springer.
[35] Sabat-Tomala, Anita; Raczko, Edwin; & Zagajewski, Bogdan (2020). “Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data”, Remote Sensing, no. 12 (3):516.
[36] Schroeder, Wilfrid; Oliva, Patricia; Giglio, Louis; Quayle, Brad; Lorenz, Eckehard; & Morelli, Fabiano (2016). “Active fire detection using Landsat-8/OLI data”, “Remote sensing of environment”, no. 185:210-220.
[37] Slonecker, Terrence; Fisher, Gary B.; Aiello, Danielle P.; & Haack, Barry. (2010). “Visible and infrared remote imaging of hazardous waste: a review”, Remote Sensing, no. 2 (11):2474-2508.
[38] Syifa, Mutiara; Panahi, Mahdi; & Lee, Chang-Wook. (2020). “Mapping of post-wildfire burned area using a hybrid algorithm and satellite data: the case of the camp fire wildfire in California, USA”, Remote Sensing, no. 12 (4).
[39] Wooster, Martin J.; Roberts, Gareth; Alistair MS Smith; Johnston, Joshua; Freeborn, Patrick; Amici, Stefania; & Hudak; Andrew T. (2013). “Thermal remote sensing of active vegetation fires and biomass burning events”, In Thermal Infrared Remote Sensing, 347-390, Springer. | ||
آمار تعداد مشاهده مقاله: 515 تعداد دریافت فایل اصل مقاله: 453 |