scholarly journals Integration of Multiple Spectral Indices and a Neural Network for Burned Area Mapping Based on MODIS Data

2019 ◽  
Vol 11 (3) ◽  
pp. 326 ◽  
Author(s):  
Rui Ba ◽  
Weiguo Song ◽  
Xiaolian Li ◽  
Zixi Xie ◽  
Siuming Lo
Keyword(s):  
Neural Network ◽  
Land Cover ◽  
Empirical Formula ◽  
Training Sample ◽  
Mapping Method ◽  
Burned Area ◽  
Spectral Indices ◽  
American States ◽  
Burned Area Mapping ◽  
Formula Method

Since wildfires have occurred frequently in recent years, accurate burned area mapping is required for wildfire severity assessment and burned land reconstruction. Satellite remote sensing is an effective technology that can provide valuable information for wildfire assessment. However, the common approaches based on using a single satellite image to promptly detect the burned areas have low accuracy and limited applicability. This paper develops a new burned area mapping method that surpasses the detection accuracy of previous methods, while still using a single Moderate Resolution Imaging Spectroradiometer (MODIS) sensor image. The key innovation is integrating optimal spectral indices and a neural network algorithm. We used the traditional empirical formula method, multi-threshold method and visual interpretation method to extract the sample sets of five typical types (burned area, vegetation, cloud, bare soil, and cloud shadow) from the MODIS data of several wildfires in the American states of Nevada, Washington and California in 2016. Afterward, the separability index M was adopted to assess the capacity of seven spectral bands and 13 spectral indices to distinguish the burned area from four unburned land cover types. Based on the separability analysis between the burned area and unburned areas, the spectral indices with an M value higher than 1.0 were employed to generate the training sample sets that were assessed to have an overall accuracy of 98.68% and Kappa coefficient of 97.46%. Finally, we utilized a back-propagation neural network (BPNN) to learn the spectral differences of different types from the training sample sets and obtain the output burned area map. The proposed method was applied to three wildfire cases in the American states of Idaho, Nevada and Oregon in 2017. A comparison of detection results between the new MODIS-based burned area map and the reference burned area map compiled from Landsat-8 Operational Land Imager (OLI) data indicates that the proposed method can effectively exploit the spectral characteristics of various land cover types. Also, this new method can achieve higher accuracy with the reduction of commission error (CE, >10%) and omission error (OE, >6%) compared to the traditional empirical formula method. The new burned area mapping method could help managers and the public perform more effective wildfire assessments and emergency management.

scholarly journals Agreement Index for Burned Area Mapping: Integration of Multiple Spectral Indices Using Sentinel-2 Satellite Images

2020 ◽  
Vol 12 (11) ◽  
pp. 1862 ◽  
Author(s):  
Daniela Smiraglia ◽  
Federico Filipponi ◽  
Stefania Mandrone ◽  
Antonella Tornato ◽  
Andrea Taramelli
Keyword(s):  
Decision Making ◽  
Satellite Data ◽  
Burned Area ◽  
Decision Making Process ◽  
Large Set ◽  
Spectral Indices ◽  
Commission Errors ◽  
Burned Area Mapping ◽  
Optical Satellite Data ◽  
Sentinel 2

Identifying fire-affected areas is of key importance to support post-fire management strategies and account for the environmental impact of fires. The availability of high spatial and temporal resolution optical satellite data enables the development of procedures for detailed and prompt post-fire mapping. This study proposes a novel approach for integrating multiple spectral indices to generate more accurate burned area maps by exploiting Sentinel-2 images. This approach aims to develop a procedure to combine multiple spectral indices using an adaptive thresholding method and proposes an agreement index to map the burned areas by optimizing omission and commission errors. The approach has been tested for the burned area classification of four study areas in Italy. The proposed agreement index combines multiple spectral indices to select the actual burned pixels, to balance the omission and commission errors, and to optimize the overall accuracy. The results showed the spectral indices singularly performed differently in the four study areas and that high levels of commission errors were achieved, especially for wildfires which occurred during the fall season (up to 0.93) Furthermore, the agreement index showed a good level of accuracy (minimum 0.65, maximum 0.96) for all the study areas, improving the performance compared to assessing the indices individually. This suggests the possibility of testing the methodology on a large set of wildfire cases in different environmental conditions to support the decision-making process. Exploiting the high resolution of optical satellite data, this work contributes to improving the production of detailed burned area maps, which could be integrated into operational services based on the use of Earth Observation products for burned area mapping to support the decision-making process.

scholarly journals Improving Urban Land Cover/Use Mapping by Integrating A Hybrid Convolutional Neural Network and An Automatic Training Sample Expanding Strategy

2020 ◽  
Vol 12 (14) ◽  
pp. 2292
Author(s):  
Xin Luo ◽  
Xiaohua Tong ◽  
Zhongwen Hu ◽  
Guofeng Wu
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Training Sample ◽  
Urban Land ◽  
Support Vector ◽  
Land Cover Mapping ◽  
Urban Regions ◽  
Urban Land Cover

Moderate spatial resolution (MSR) satellite images, which hold a trade-off among radiometric, spectral, spatial and temporal characteristics, are extremely popular data for acquiring land cover information. However, the low accuracy of existing classification methods for MSR images is still a fundamental issue restricting their capability in urban land cover mapping. In this study, we proposed a hybrid convolutional neural network (H-ConvNet) for improving urban land cover mapping with MSR Sentinel-2 images. The H-ConvNet was structured with two streams: one lightweight 1D ConvNet for deep spectral feature extraction and one lightweight 2D ConvNet for deep context feature extraction. To obtain a well-trained 2D ConvNet, a training sample expansion strategy was introduced to assist context feature learning. The H-ConvNet was tested in six highly heterogeneous urban regions around the world, and it was compared with support vector machine (SVM), object-based image analysis (OBIA), Markov random field model (MRF) and a newly proposed patch-based ConvNet system. The results showed that the H-ConvNet performed best. We hope that the proposed H-ConvNet would benefit for the land cover mapping with MSR images in highly heterogeneous urban regions.

A daily burned area mapping method using AVHRR time-series data

2021 ◽  
Author(s):  
Shuhan Lou ◽  
Yuanhong Liao ◽  
Yufu Liu ◽  
Yuqi Bai
Keyword(s):  
Climate Change ◽  
Time Series ◽  
Land Cover ◽  
Change Detection ◽  
Time Series Data ◽  
Mapping Method ◽  
Series Data ◽  
Burned Area ◽  
Burnt Area ◽  
Area Data

<p>The study of complex interactions between fire and atmospheric dynamics of the earth system is drawing increasing attention in recent years, especially when fire seasons are extended due to global warming, where the historical daily burnt area data played a pivotal role in analyzing wildfire regimes change. Existing products could not fully meet the temporal requirements: daily burnt area data in global fire emissions database (GFED4) starts from mid-2000 using MODIS while ESA Fire Climate Change Initiative (FireCCILT10) Dataset from 1982 to 2017 is provided on a monthly grid.</p><p>Advanced Very High Resolution Radiometer (AVHRR) series of sensors are widely used to develop pre‐MODIS daily historical records. However, compared to MODIS, the AVHRR sensor has a lower radiometric and geometric quality and is missing Short Wave Infrared (SWIR) band. To address the data quality problem, this research study presents a time-series mapping method for daily burned area using AVHRR composite. Daily fire-sensitive indices are calculated to develop a time-series data composite which is masked by the burnable surface of GLASS_GLC land cover product. Then, Continuous Change Detection and Classification (CCDC) time-series model, which originally implemented on Landsat data monitoring land cover change, is revised to detect an abrupt change in the time-series data composite and remove noise, ensuring temporal consistency. The image of a time-series breakpoint is further classified using a spatial contextual method to distinguish biomass burning from other forest degradation change like a landslide and is used to generate burned area probability map.</p><p>The methodology is verified in California, US, where fuel aridity increased during 1984–2015 driven by anthropogenic climate change. The samples are collected based on the National Monitoring Trends in Burn Severity（MTBS）Burned Areas Boundaries Dataset from 1984 – 2018 and California Department of Forestry and Fire Protection's Fire and Resource Assessment Program (FRAP) fire perimeters from since 1950. Primary results show that the proposed method can effectively detect burned area on daily basis with CCDC algorithm reducing the complexity of change detection.</p>

scholarly journals 30 m Resolution Global Annual Burned Area Mapping Based on Landsat Images and Google Earth Engine

2019 ◽  
Vol 11 (5) ◽  
pp. 489 ◽  
Author(s):  
Tengfei Long ◽  
Zhaoming Zhang ◽  
Guojin He ◽  
Weili Jiao ◽  
Chao Tang ◽  
...  
Keyword(s):  
Time Series ◽  
Land Cover ◽  
Google Earth ◽  
Burned Area ◽  
Landsat 8 ◽  
Landsat Images ◽  
Burned Areas ◽  
Random Decision Forests ◽  
Burned Area Mapping ◽  
Google Earth Engine

Heretofore, global Burned Area (BA) products have only been available at coarse spatial resolution, since most of the current global BA products are produced with the help of active fire detection or dense time-series change analysis, which requires very high temporal resolution. In this study, however, we focus on an automated global burned area mapping approach based on Landsat images. By utilizing the huge catalog of satellite imagery, as well as the high-performance computing capacity of Google Earth Engine, we propose an automated pipeline for generating 30-m resolution global-scale annual burned area maps from time-series of Landsat images, and a novel 30-m resolution Global annual Burned Area Map of 2015 (GABAM 2015) was released. All the available Landsat-8 images during 2014–2015 and various spectral indices were utilized to calculate the burned probability of each pixel using random decision forests, which were globally trained with stratified (considering both fire frequency and type of land cover) samples, and a seed-growing approach was conducted to shape the final burned areas after several carefully-designed logical filters (NDVI filter, Normalized Burned Ratio (NBR) filter, and temporal filter). GABAM 2015 consists of spatial extent of fires that occurred during 2015 and not of fires that occurred in previous years. Cross-comparison with the recent Fire_cci Version 5.0 BA product found a similar spatial distribution and a strong correlation ( R 2 = 0.74) between the burned areas from the two products, although differences were found in specific land cover categories (particularly in agriculture land). Preliminary global validation showed the commission and omission errors of GABAM 2015 to be 13.17% and 30.13%, respectively.

scholarly journals Global Wildfire Outlook Forecast with Neural Networks

2020 ◽  
Vol 12 (14) ◽  
pp. 2246
Author(s):  
Yongjia Song ◽  
Yuhang Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
South America ◽  
Land Cover ◽  
Southern Africa ◽  
Burned Area ◽  
Good Prediction ◽  
Wildfire Occurrence ◽  
Fire Emissions ◽  
Burned Areas

Wildfire occurrence and spread are affected by atmospheric and land-cover conditions, and therefore meteorological and land-cover parameters can be used in area burned prediction. We apply three forecast methods, a generalized linear model, regression trees, and neural networks (Levenberg–Marquardt backpropagation) to produce monthly wildfire predictions 1 year in advance. The models are trained using the Global Fire Emissions Database version 4 with small fires (GFEDv4s). Continuous 1-year monthly fire predictions from 2011 to 2015 are evaluated with GFEDs data for 10 major fire regions around the globe. The predictions by the neural network method are superior. The 1-year moving predictions have good prediction skills over these regions, especially over the tropics and the southern hemisphere. The temporal refined index of agreement (IOA) between predictions and GFEDv4s regional burned areas are 0.82, 0.82, 0.8, 0.75, and 0.56 for northern and southern Africa, South America, equatorial Asia and Australia, respectively. The spatial refined IOA for 5-year averaged monthly burned area range from 0.69 in low-fire months to 0.86 in high-fire months over South America, 0.3–0.93 over northern Africa, 0.69–0.93 over southern Africa, 0.47–0.85 over equatorial Asia, and 0.53–0.8 over Australia. For fire regions in the northern temperate and boreal regions, the temporal and spatial IOA between predictions and GFEDv4s data in fire seasons are 0.7–0.79 and 0.24–0.83, respectively. The predictions in high-fire months are better than low-fire months. This study illustrates the feasibility of global fire activity outlook forecasts using a neural network model and the method can be applied to quickly assess the potential effects of climate change on wildfires.

scholarly journals DSMNN-Net: A Deep Siamese Morphological Neural Network Model for Burned Area Mapping Using Multispectral Sentinel-2 and Hyperspectral PRISMA Images

2021 ◽  
Vol 13 (24) ◽  
pp. 5138
Author(s):  
Seyd Teymoor Seydi ◽  
Mahdi Hasanlou ◽  
Jocelyn Chanussot
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Burned Area ◽  
High Resolution Data ◽  
Burned Areas ◽  
Heterogeneous Datasets ◽  
Burned Area Mapping ◽  
Net Framework ◽  
Sentinel 2

Wildfires are one of the most destructive natural disasters that can affect our environment, with significant effects also on wildlife. Recently, climate change and human activities have resulted in higher frequencies of wildfires throughout the world. Timely and accurate detection of the burned areas can help to make decisions for their management. Remote sensing satellite imagery can have a key role in mapping burned areas due to its wide coverage, high-resolution data collection, and low capture times. However, although many studies have reported on burned area mapping based on remote sensing imagery in recent decades, accurate burned area mapping remains a major challenge due to the complexity of the background and the diversity of the burned areas. This paper presents a novel framework for burned area mapping based on Deep Siamese Morphological Neural Network (DSMNN-Net) and heterogeneous datasets. The DSMNN-Net framework is based on change detection through proposing a pre/post-fire method that is compatible with heterogeneous remote sensing datasets. The proposed network combines multiscale convolution layers and morphological layers (erosion and dilation) to generate deep features. To evaluate the performance of the method proposed here, two case study areas in Australian forests were selected. The framework used can better detect burned areas compared to other state-of-the-art burned area mapping procedures, with a performance of >98% for overall accuracy index, and a kappa coefficient of >0.9, using multispectral Sentinel-2 and hyperspectral PRISMA image datasets. The analyses of the two datasets illustrate that the DSMNN-Net is sufficiently valid and robust for burned area mapping, and especially for complex areas.

Sign in / Sign up

Export Citation Format

Share Document