scholarly journals FLOOD MONITORING USING NDWI AND MNDWI SPECTRAL INDICES: A CASE STUDY OF AGHQALA FLOOD-2019, GOLESTAN PROVINCE, IRAN

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 605-607
Author(s):  
F. Khalifeh Soltanian ◽  
M. Abbasi ◽  
H. R. Riyahi Bakhtyari
Keyword(s):  
Natural Hazards ◽  
Satellite Imagery ◽  
Water Bodies ◽  
Detection Methods ◽  
Spectral Indices ◽  
Landsat Images ◽  
Flood Monitoring ◽  
Golestan Province ◽  
Digital Methods

Abstract. Assessment of changes of water bodies and vegetation by traditional methods is very difficult and costly. The use of satellite data makes it possible to study water bodies and vegetation more accurately and cost effectively. Accordingly, various digital methods have been developed to discover and detect changes of earth's surface features. Flood is one of the important factors contributing to the destruction of natural resources. The purpose of this research is to evaluate the flood areas in the Aghqala area in Golestan province of Iran. The level of water bodies in the spring of 2018 and 2019 was compared and evaluated based on the NDWI and MNDWI indices using Landsat images. The results showed that water bodies’ area in the spring of 2018 was 24.13 km2 which increased to 185.34 km2 at 2019 using NDWI; while the MNDWI due to the excessive sensitivity to the water considered agriculture wetlands as an area of water bodies. Therefore, the NDWI yielded more logical results. Also, change detection methods based on spectral and radiometric information using indices are more accurate than the classification maps and more changes can be shown. Using satellite imagery to monitor changes is essential to facilitate the planning of natural hazards management.

scholarly journals A simple, robust, and automatic approach to extract water body from Landsat images (case study: Lake Urmia, Iran)

2019 ◽  
Author(s):  
Hadiseh Babaei ◽  
Milad Janalipour ◽  
Nadia Abbaszadeh Tehrani
Keyword(s):  
Saline Lakes ◽  
Continuous Monitoring ◽  
Landsat 8 ◽  
Lake Area ◽  
Spectral Indices ◽  
Lake Urmia ◽  
Landsat Images ◽  
The World ◽  
Study Lake

Abstract Lake Urmia is one of the largest saline lakes in the world, and has a great effect on its surrounding ecosystems as well as the economic, social, and even cultural condition of its basin inhabitants. Hence, continuous monitoring of lake area changes is necessary and unavoidable for better land management and prevention of its degradation. In this study, by using Landsat 8 images and by preforming some essential pre-processing tasks, the area of the lake was estimated using the number of traditional spectral indices and a new one and the automatic Otsu's thresholding method for 5 years (2013–2017). The results showed that this index shows more accurate results than other indices when estimating the area of the lake and can separate water class from land one with an average overall accuracy of 96%.

scholarly journals Mapping the vegetation soil and water region analysis of Tuticorin district using Landsat images

2017 ◽  
Vol 7 (1.3) ◽  
pp. 161
Author(s):  
Cynthia J ◽  
Suguna M ◽  
Senthil S
Keyword(s):  
Satellite Imagery ◽  
Vegetation Index ◽  
Water Bodies ◽  
High Spectral Resolution ◽  
Landsat 8 ◽  
Landsat Images ◽  
Water Region ◽  
Vegetation Region ◽  
Soil And Water ◽  
Water Vegetation

Mapping of water bodies, soil and vegetation region from satellite imagery has been widely explored in the recent past. Several approaches have been developed to detect water bodies and identify the soil types from different satellite imagery varying in spatial, spectral, and temporal characteristics. Due to the introduction of a New Operational Land Imager (OLI) sensor on Landsat 8 with a high spectral resolution and improved signal-to-noise ratio, the quality of imagery sensed is increased. Its imagery produces a better result in classifying the soil and water regions. The current study puts forward an approach to map water bodies, soil and vegetation region from a Landsat satellite imagery using the various processing models. In this study, to identify the water region and soil region, we go with water index, vegetation index and soil index measures. By using reflectance bands, it is easy to analyze the water, vegetation and soil regions. The proposed method accurately and quickly discriminated the water, vegetation and soil region from other land cover features.

scholarly journals Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study

2019 ◽  
Vol 11 (1) ◽  
pp. 74 ◽  
Author(s):  
Yara Mohajerani ◽  
Michael Wood ◽  
Isabella Velicogna ◽  
Eric Rignot
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Satellite Imagery ◽  
Mean Deviation ◽  
Landsat Images ◽  
Detection Techniques ◽  
Current Century ◽  
Trained Neural Network

The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set of Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m (1.89 pixels). We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products.

scholarly journals Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study

2018 ◽  
Author(s):  
Yara Mohajerani ◽  
Michael Wood ◽  
Isabella Velicogna ◽  
Eric Rignot
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Satellite Imagery ◽  
Mean Deviation ◽  
Landsat Images ◽  
Detection Techniques ◽  
Current Century ◽  
Trained Neural Network

The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to robustly and automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on novel images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m. We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products.

Sign in / Sign up

Export Citation Format

Share Document