Incorporating Sentinel-1 SAR imagery with the MODIS MCD64A1 burned area product to improve burn date estimates and reduce burn date uncertainty in wildland fire mapping

Lasko, Kristofer

doi:10.1080/10106049.2019.1608592

Cited by 26 publications

(11 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[13] applied Bayes' Theorem approach [14] to combine potential BA detections from Landsat-8 OLI, Sentinel-2 MSI and MODIS instruments to delineate the BA and monitor the progress of the 2017 Elephant Hill fire in California. One of the most recent studies by [15], combined Sentinel-1 SAR imagery with a monthly averaged MODIS BA product to reduce the burn date uncertainty of the MODIS BA product caused by observations obscured by clouds. Significant decrease in backscatter between two SAR images was used to detect BA affected pixels in SAR images which allowed to decrease the burning date uncertainty.…”

Section: Related Workmentioning

confidence: 99%

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

Rashkovetsky

Mauracher

Langer

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deriving the extent of areas affected by wildfires is critical to fire management, protection of the population, damage assessment, and better understanding of the consequences of fires. In the last two decades, several algorithms utilizing data from Earth observation satellites have been developed to detect fire-affected areas. However, most of these methods require the establishment of complex functional relationships between numerous remote sensing data parameters. In contrast, more recently, deep learning has found its way into the application, having the advantage of being able to detect patterns in complex data by learning from examples automatically. In this paper, a workflow for the detection of fire-affected areas from satellite imagery acquired in the visible, infrared and microwave domains is described. Using this workflow, the fire detection potentials of four sources of freely available satellite imagery were investigated: The C-SAR instrument on board Sentinel-1, the MSI instrument on board Sentinel-2, the SLSTR instrument on board Sentinel-3 and the MODIS instrument on board Terra and Aqua. For each of them, a single-input convolutional neural network based on the well-known U-Net architecture was trained on a newly created dataset. The performance of the resulting four single-instrument models was evaluated in presence of clouds and in clear conditions.In addition, the potential of combining predictions from pairs of single-instrument models was investigated. The results show that fusion of Sentinel-2 and Sentinel-3 data provides the best detection rate in clear conditions, whereas the fusion of Sentinel-1 and Sentinel-2 data shows a significant benefit in cloudy weather.

show abstract

Section: Related Workmentioning

confidence: 99%

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

Rashkovetsky

Mauracher

Langer

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The IOP Publishing doi:10.1088/1755-1315/1061/1/012013 2 delineation of burned areas using only radar images may be difficult or limited for some landscapes, since the radar signal reflected from the burned surface may be similar in intensity to the signal from other components of the landscape (for example, areas of open ground) or be associated with other processes (logging, flooding, etc.) [13]. Therefore, the optimal solution is often the joint use of radar images and optical range images to delineate burned areas and analyze their recovery rates [10,11,[13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

“…[13]. Therefore, the optimal solution is often the joint use of radar images and optical range images to delineate burned areas and analyze their recovery rates [10,11,[13][14][15][16]. Another interesting methodological approach is the joint use of radar images in different polarizations (usually C and L) to monitor vegetation restoration in burning areas [17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Using SAR-data and optical data to delineate burned territories in Kalmykia, Chernye Zemli reserve

Karpachevskiy

Mikhailukova

Sharapova

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The study of fires and their consequences using remote sensing methods in the optical range is widespread. There are many studies devoted to forest fires, a little less to fires in arid areas. At the same time, even in arid regions, weather conditions do not always allow us to get a correct representation of the fire spread in a sufficiently high spatial resolution (the first tens of meters). Our study is related to the territory of Chernye Zemli reserve located in Kalmykia, Russian Federation. In this study, we are conducting an experiment on the joint use of multitemporal synthesis of vertical polarization radar data and the burn index (dNBR2) according to Landsat-8 satellite data. The use of the image segmentation approach gave good results in identifying the boundaries of the burned territories from radar data, and the use of a training sample from optical data index image made it possible to classify the selected superpixels according to the classes of “burned” or “not burned”.

show abstract

“…In the works [Rasul, et al, 2021;Ertugrul, et al, 2019;Lasko, 2019], the authors determine the dynamics of increasing the large burned areas of forest over certain periods of time using remote sensing data from the resource MCD64A1 500m. The main factors causing the increase of fires in the studied regions are analyzed.…”

Section: Introductionmentioning

confidence: 99%

Geodesy, Cartography and Aerial Photography

Babushka¹,

Babiy²,

Chetverikov³

et al. 2021

ISTCGCAP

View full text Add to dashboard Cite

Earth remote sensing and using the satellite images play an important role when monitoring the effects of forest fires and assessing damage. Applying different methods of multispectral space images processing, we can determine the risk of fire distribution, define hot spots and determine thermal parameters, mapping the damaged areas and assess the consequences of fire. The purpose of the work is the severity assessment connected with the post-fire period on the example of the forests in the Chornobyl Exclusion Zone. The tasks of the study are to define the area of burned zones using space images of different time which were obtained from the Sentinel-2 satellite applying the method of a normalized burn ratio (NBR) and method of supervised classification. Space images taken from the Sentinel-2 satellite before and after the fire were the input data for the study. Copernicus Open Access Hub service is a source of images and its spatial resolution is 10 m for visible and near infrared bands of images, and 20 m for medium infrared bands of images. We used method of Normalized Burn Ratio (NBR) and automatically calculated the area damaged with fire. Using this index we were able to identify areas of zones after active combustion. This index uses near and middle infrared bands for the calculations. In addition, a supervised classification was performed on the study area, and signature files were created for each class. According to the results of the classification, the areas of the territories damaged by the fire were also calculated. The scientific novelty relies upon the application of a method of using the normalized combustion coefficient (NBR) and supervised classification for space images obtained before and after the fire in the Chernobyl Exclusion Zone. The practical significance lies in the fact that the studied methods of GIS technologies can be used to identify territories and calculate the areas of vegetation damaged by fires. These results can be used by local organizations, local governments and the Ministry of Emergency Situations to monitor the condition and to plan reforestation. The normalized burned ratio (NBR) gives possibility efficiently and operatively to define and calculate the area which were damaged by fires, that gives possibility operatively assess the consequences of such fires and estimate the damage. The normalized burned ratio allows to calculate the area of burned forest almost 2 times more accurately than the supervised classification. The calculation process itself also takes less time and does not require additional procedures (set of signatures). Supervised classification in this case gives worse accuracy, the process itself is longer, but allows to determine the area of several different classes.

show abstract

Incorporating Sentinel-1 SAR imagery with the MODIS MCD64A1 burned area product to improve burn date estimates and reduce burn date uncertainty in wildland fire mapping

Cited by 26 publications

References 110 publications

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

Using SAR-data and optical data to delineate burned territories in Kalmykia, Chernye Zemli reserve

Geodesy, Cartography and Aerial Photography

Contact Info

Product

Resources

About