Combination of multiple classifiers by fuzzy integrals: an application to synthetic aperture radar (SAR) data

2005 ◽  
Author(s):  
P. Blonda ◽  
C. Tarantino ◽  
A. D'Addabbo ◽  
G. Satalino ◽  
G. Pasquariello
Keyword(s):  
Synthetic Aperture Radar ◽  
Synthetic Aperture ◽  
Multiple Classifiers ◽  
Sar Data ◽  
Aperture Radar

Multi-Temporal Synthetic Aperture Radar Data for Paddy Crop Area Estimation in Eastern part of Godavari Delta, Andhra Pradesh, India.

2020 ◽  
Vol 8 (3) ◽  
pp. 208-218
Author(s):  
S.K. Tiwari ◽  
Prasada Rao G
Keyword(s):  
Synthetic Aperture Radar ◽  
Cloud Cover ◽  
Andhra Pradesh ◽  
Synthetic Aperture ◽  
Crop Acreage ◽  
The Third ◽  
Godavari Delta ◽  
Sar Data ◽  
Paddy Crop ◽  
Aperture Radar

In the present study, an attempt is made to estimate the area under paddy crop during Rabi, 2013-14 using Microwave satellite data in the eastern part of Godavari delta. Clouds veil nearly the entire sky in both (Kharif & Rabi) seasons of Andhra Pradesh and hinder the estimation of crop acreage through optical satellite sensors. Microwaves can penetrate clouds and be used to detect crops during the day and night, regardless of cloud cover. Radar Imaging SATellite-1 (RISAT-1), microwave sensor, dual-polarization Horizontal-Horizontal (HH), Horizontal-Vertical (HV), Medium Resolution scanSAR Mode (MRS) data (18 m pixel spacing and 37° incidence angle) of three different dates (in December, January, and February) with 25 days interval was used. The backscatter (dB) values of the early, mid, and late-season transplanted stages of paddy crop were used to estimate the paddy crop acreage coupled with ground truth information during different stages of the crop. It was observed that the dB values at the transplanting stage rapidly increased with plant growth in the early season sown areas and mid-season sowed paddy illustrate a dip in dB values in the second date due to change in transplantation and increased backscatter coefficient values in the third date because of crop growth after transplantation. The backscatter signature value of late sowing paddy crop showed first and second dates with high backscatter due to previous crop/vegetation and then a sudden dip in the third date as submerged field ready for transplantation. The dB values of the above stages were used in decision-based classifier to estimate paddy crop acreage. The paddy area was compared at Mandal (sub-district level) estimates observed the significant coefficient of determination (R² = 0.89) between traditional estimates and Synthetic Aperture Radar (SAR) data assessment. This study robustly suggests the utilization of SAR data in agricultural crop monitoring during cloud cover.

Mapping the 2010 Merapi pyroclastic deposits using dual-polarization Synthetic Aperture Radar (SAR) data

2015 ◽  
Vol 158 ◽  
pp. 180-192 ◽  
Author(s):  
Akhmad Solikhin ◽  
Virginie Pinel ◽  
Jean Vandemeulebrouck ◽  
Jean-Claude Thouret ◽  
Muhamad Hendrasto
Keyword(s):  
Synthetic Aperture Radar ◽  
Synthetic Aperture ◽  
Dual Polarization ◽  
Pyroclastic Deposits ◽  
Sar Data ◽  
Aperture Radar

scholarly journals Artificial Neural Network Modeling of High Arctic Phytomass Using Synthetic Aperture Radar and Multispectral Data

2021 ◽  
Author(s):  
Adam Collingwood ◽  
Paul Treitz ◽  
Francois Charbonneau ◽  
David M. Atkinson
Keyword(s):  
Synthetic Aperture Radar ◽  
High Arctic ◽  
Synthetic Aperture ◽  
The Arctic ◽  
Optical Data ◽  
Neural Network Modeling ◽  
Artificial Neural ◽  
Sar Data ◽  
The Relationship ◽  
Aperture Radar

Vegetation in the Arctic is often sparse, spatially heterogeneous, and difficult to model. Synthetic Aperture Radar (SAR) has shown some promise in above-ground phytomass estimation at sub-arctic latitudes, but the utility of this type of data is not known in the context of the unique environments of the Canadian High Arctic. In this paper, Artificial Neural Networks (ANNs) were created to model the relationship between variables derived from high resolution multi-incidence angle RADARSAT-2 SAR data and optically-derived (GeoEye-1) Soil Adjusted Vegetation Index (SAVI) values. The modeled SAVI values (i.e., from SAR variables) were then used to create maps of above-ground phytomass across the study area. SAVI model results for individual ecological classes of polar semi-desert, mesic heath, wet sedge, and felsenmeer were reasonable, with r2 values of 0.43, 0.43, 0.30, and 0.59, respectively. When the outputs of these models were combined to analyze the relationship between the model output and SAVI as a group, the r2 value was 0.60, with an 8% normalized root mean square error (% of the total range of phytomass values), a positive indicator of a relationship. The above-ground phytomass model also resulted in a very strong relationship (r2 = 0.87) between SAR-modeled and field-measured phytomass. A positive relationship was also found between optically derived SAVI values and field measured phytomass (r2 = 0.79). These relationships demonstrate the utility of SAR data, compared to using optical data alone, for modeling above-ground phytomass in a high arctic environment possessing relatively low levels of vegetation.

scholarly journals Mapping potential signs of gas emissions in ice of Lake Neyto, Yamal, Russia, using synthetic aperture radar and multispectral remote sensing data

2021 ◽  
Vol 15 (4) ◽  
pp. 1907-1929
Author(s):  
Georg Pointner ◽  
Annett Bartsch ◽  
Yury A. Dvornikov ◽  
Alexei V. Kouraev
Keyword(s):  
Synthetic Aperture Radar ◽  
Synthetic Aperture ◽  
The Arctic ◽  
Lake Ice ◽  
Gas Emissions ◽  
L Band ◽  
Optical Imagery ◽  
Sar Data ◽  
Sar Imagery ◽  
Aperture Radar

Abstract. Regions of anomalously low backscatter in C-band synthetic aperture radar (SAR) imagery of lake ice of Lake Neyto in northwestern Siberia have been suggested to be caused by emissions of gas (methane from hydrocarbon reservoirs) through the lake’s sediments. However, to assess this connection, only analyses of data from boreholes in the vicinity of Lake Neyto and visual comparisons to medium-resolution optical imagery have been provided due to a lack of in situ observations of the lake ice itself. These observations are impeded due to accessibility and safety issues. Geospatial analyses and innovative combinations of satellite data sources are therefore proposed to advance our understanding of this phenomenon. In this study, we assess the nature of the backscatter anomalies in Sentinel-1 C-band SAR images in combination with very high resolution (VHR) WorldView-2 optical imagery. We present methods to automatically map backscatter anomaly regions from the C-band SAR data (40 m pixel spacing) and holes in lake ice from the VHR data (0.5 m pixel spacing) and examine their spatial relationships. The reliability of the SAR method is evaluated through comparison between different acquisition modes. The results show that the majority of mapped holes (71 %) in the VHR data are clearly related to anomalies in SAR imagery acquired a few days earlier, and similarities to SAR imagery acquired more than a month before are evident, supporting the hypothesis that anomalies may be related to gas emissions. Further, a significant expansion of backscatter anomaly regions in spring is documented and quantified in all analysed years 2015 to 2019. Our study suggests that the backscatter anomalies might be caused by lake ice subsidence and consequent flooding through the holes over the ice top leading to wetting and/or slushing of the snow around the holes, which might also explain outcomes of polarimetric analyses of auxiliary L-band Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) data. C-band SAR data are considered to be valuable for the identification of lakes showing similar phenomena across larger areas in the Arctic in future studies.

scholarly journals Inundation Extent Mapping by Synthetic Aperture Radar: A Review

2019 ◽  
Vol 11 (7) ◽  
pp. 879 ◽  
Author(s):  
Xinyi Shen ◽  
Dacheng Wang ◽  
Kebiao Mao ◽  
Emmanouil Anagnostou ◽  
Yang Hong
Keyword(s):  
Synthetic Aperture Radar ◽  
Optical Sensors ◽  
Risk Mitigation ◽  
Numerical Models ◽  
Synthetic Aperture ◽  
Spatiotemporal Resolution ◽  
Urban Flood ◽  
Inundation Mapping ◽  
Sar Data ◽  
Aperture Radar

Recent flood events have demonstrated a demand for satellite-based inundation mapping in near real-time (NRT). Simulating and forecasting flood extent is essential for risk mitigation. While numerical models are designed to provide such information, they usually lack reference at fine spatiotemporal resolution. Remote sensing techniques are expected to fill this void. Unlike optical sensors, synthetic aperture radar (SAR) provides valid measurements through cloud cover with high resolution and increasing sampling frequency from multiple missions. This study reviews theories and algorithms of flood inundation mapping using SAR data, together with a discussion of their strengths and limitations, focusing on the level of automation, robustness, and accuracy. We find that the automation and robustness of non-obstructed inundation mapping have been achieved in this era of big earth observation (EO) data with acceptable accuracy. They are not yet satisfactory, however, for the detection of beneath-vegetation flood mapping using L-band or multi-polarized (dual or fully) SAR data or for urban flood detection using fine-resolution SAR and ancillary building and topographic data.

Sign in / Sign up

Export Citation Format

Share Document