1 Remote Sensing Laboratory Dept. of Information Engineering and Computer Science University of...
If you can't read please download the document
1 Remote Sensing Laboratory Dept. of Information Engineering and Computer Science University of Trento Via Sommarive, 14, I-38123 Povo, Trento, Italy 1
1 Remote Sensing Laboratory Dept. of Information Engineering
and Computer Science University of Trento Via Sommarive, 14,
I-38123 Povo, Trento, Italy 1 Remote Sensing Laboratory Dept. of
Information Engineering and Computer Science University of Trento
Via Sommarive, 14, I-38123 Povo, Trento, Italy 2 Institute for
Applied Remote Sensing 3 Institute for Alpine Environment Eurac
Research Viale Druso, 1, I-39100 Bolzano, Italy 4 Department of
Computer, System and Production Engineering Tor Vergata University
Via del Politecnico, 1, I-00133 Rome Italy Luca Pasolli 1,2 Claudia
Notarnicola 2 Lorenzo Bruzzone 1 Giacomo Bertoldi 3 Georg Niedriest
3 Ulrike Tappeiner 3 Marc Zebisch 2 Fabio Del Frate 4 Gaia Vaglio
Laurin 4 Spatial and Temporal Mapping of Soil Moisture Content with
Polarimetric RADARSAT2 SAR Imagery in the Alpine Area Spatial and
Temporal Mapping of Soil Moisture Content with Polarimetric
RADARSAT2 SAR Imagery in the Alpine Area E-mail:
[email protected][email protected] Web:
http://rslab.disi.unitn.it http://www.eurac.edu
Slide 2
2 Introduction Aim of the Work Estimation System Description 1
Analysis of Results Study Area and Dataset 2 3 4 5 Outline
Conclusion6 IEEE International Geoscience and Remote Sensing
Symposium IGARSS 2011 Vancouver, Canada 24-29 July, 2011
Slide 3
Introduction 3 SOFIA: SOil and Forest Information retrieval by
using RADARSAT2 images ESA AO-SOAR 6820 Supported in the framework
of the IRKIS project (Civil Protection Department, Province of
Bolzano) Main Innovative Aspects: Fully-polarimetric RADARSAT2
satellite SAR data Mountain landscape (Alpine area) Advanced
estimation methods Objectives: Estimation of soil moisture content
on bare and vegetated areas (alpine meadows and pastures)
Estimation of vegetation biomass (forest) Investigation on the
influence of soil and vegetation parameters in connection to
natural hazard in Alpine regions. Estimation of soil moisture
content on bare and vegetated areas (alpine meadows and pastures)
IEEE International Geoscience and Remote Sensing Symposium IGARSS
2011 Vancouver, Canada 24-29 July, 2011
Slide 4
Introduction 4 Soil moisture estimation supports various
application domains: drought monitoring flood and landslide
prediction climate change analysis Challenges: non-linearity of the
relationship between microwave signals and soil moisture
sensitivity of microwave signals on different target properties
(moisture content, roughness, vegetation, land use) influence of
topography on the microwave signal acquired by the sensor In a
previous study (Pasolli et al., 2010) RADARSAT2 SAR images have
shown to be promising for the retrieval of soil moisture in Alpine
areas: by integrating the information coming from ancillary data by
exploiting an advanced retrieval algorithm based on the Support
Vector Regression (SVR) method IEEE International Geoscience and
Remote Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011 L. Pasolli, C. Notarnicola, L. Bruzzone, G. Bertoldi, S. Della
Chiesa, V. Hell, G. Niedrist, U. Tappeiner, M. Zebisch, F. Del
Frate, G.V. Laurin, Estimagion of Soil Moisture in an Alpine
catchment with RADARSAT2 images, Applied and Environmental Soil
Science, in press
Slide 5
5 To Further Investigate the Retrieval of Soil Moisture from
RADARSAT2 SAR Images in Alpine Areas 1.By exploiting the
fully-polarimetric capability of RADARSAT2 in combination with
standard and advanced feature extraction/selection methods 2.By
extending the analysis in time and space with the available images
IEEE International Geoscience and Remote Sensing Symposium IGARSS
2011 Vancouver, Canada 24-29 July, 2011 Aim of the Work
Slide 6
Study Area 6 Well known and monitored area Well representative
in terms of Topography Land use Soil moisture content conditions
Mazia Valley, Alto Adige, Italy IEEE International Geoscience and
Remote Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011
Slide 7
Dataset 7 MeadowPasture JuneJulyJuneJuly Min Diel6.73.86.43.2
Max Diel21.82716.225.63 Average Diel16.514.211.27.7 2.Field
measurements: 77 soil dielectric constant measurements on meadows
(blue) and pasture (red) acquired contemporary to satellite
overpasses (3 rd June and 21 st July) RADARSAT2, 21 July 2010
(R=HH, G=HV, B=VV) 1.Satellite SAR images: 4 RADATSAT2 quad-pol
standard mode images (3 rd June, 21 st July, 14 th August, 5 th
October 2010) DEM geocoded, filtered (Frost 7x7) Final pixel size
20 m 3.Ancillary data: NDVI map extracted from MODIS Terra images
(pixel size 250 m) Land use map (meadows, pasture); DEM (pixel size
2.5 m) IEEE International Geoscience and Remote Sensing Symposium
IGARSS 2011 Vancouver, Canada 24-29 July, 2011
Slide 8
Estimation System 8 Data Pre-processing Feature Extraction
& Selection Retrieval Algorithm Polarimetric RADARSAT2 SAR
image Estimated Soil Moisture Content Map Ancillary Data IEEE
International Geoscience and Remote Sensing Symposium IGARSS 2011
Vancouver, Canada 24-29 July, 2011
Slide 9
Estimation System: Retrieval Algorithm 9 Data Pre-processing
Feature Extraction & Selection Retrieval Algorithm Polarimetric
RADARSAT2 SAR image Estimated Soil Moisture Content Map Ancillary
Data Aim: to define the mapping between the input features and the
target biophysical variable Support Vector Regression (SVR)
technique trained on Field Reference Samples Multi-objective Model
Selection Approach Ground Truth Features from Remotely Sensed Image
SVR Learning SVR Estimation Performance Evaluation Model Selection
Reference Samples Training Set Validation Set SVR Parameters
Config. Estimation Perform. (MSE, R 2 ) K-Fold Cross Validation
Multi-Objective Model Selection Features from Ancillary Data
Training Phase Sub-Sample Generator Estimation Operational Phase
Input Features (Image + Ancillary) SVR Estimator Output SMC Value
IEEE International Geoscience and Remote Sensing Symposium IGARSS
2011 Vancouver, Canada 24-29 July, 2011
Slide 10
Estimation System: Features Extraction and Selection 10 Data
Pre-processing Feature Extraction & Selection Retrieval
Algorithm Polarimetric RADARSAT2 SAR image Estimated Soil Moisture
Content Map Ancillary Data Aim: to extract and select from the
remotely sensed data the most relevant information for the
estimation problem considered Features Extraction Standard
Intensity&Phase SAR processing Polarimetric backscattering
coefficients Polarimetric Combinations: Span (HH+HV+2HV),
Polarization Ratio (HH/VV) and Linear Depolarization Ratio (HV/VV)
Polarimetric phase difference (PPD) and interferometric coherence
Polarimetric Decompositions H/A/ decomposition General purpose
feature extraction techniques Independent Component Analysis (ICA)
Features Selection Sequential Forward Selection (SFS) strategy with
performance evaluation on a subset of reference samples IEEE
International Geoscience and Remote Sensing Symposium IGARSS 2011
Vancouver, Canada 24-29 July, 2011
Slide 11
11 Experiment 1: Assessment of the Estimation System with the
proposed Feature Extraction & Selection strategies 60 reference
samples for training/tuning the estimation system according to a
5-fold cross validation procedure Retrieval Algorithm Settings: SVR
with Gaussian RBF kernel function Hyper-parameters ranges: 10 -3
< < 10 3, 10 -3 < C < 10 3, 10 -3 < < 10
Multi-objectives model selection according to RMSE and R 2 quality
metrics Performance assessment on 17 independent test reference
samples according to: Root Mean Squared Error (RMSE) Determination
coefficient (R 2 ) Slope and Intercept of the linear tendency line
between estimated and measured target values Experimental Setup
Experiment 2: Assessment of Spatially and Temporally Distributed
Soil Moisture Estimates in the Alpine Area Exploitiation of the
estimation system configuration identified in Experiment 1
Generation of soil moisture content maps associated with RADARSAT 2
SAR images time series acquired during summer 2010 Qualitative and
quantitative assessment with prior knowledge on the area and field
station measurements IEEE International Geoscience and Remote
Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011
Slide 12
11 Results: Experiment 1 IEEE International Geoscience and
Remote Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011 Selected FeaturesRMSER2R2 SlopeIntercept Reference
HH2.790.790.772.13 HH HV/VV featuresICA1 ICA4 features A featuresHH
feature Intensity & Phase Features HH HV/VV2.550.820.82.37 ICA
Features ICA1 ICA42.660.810.861.53 Cloude Decomposition Features A
3.10.730.763.09
Slide 13
11 Results: Experiment 2 IEEE International Geoscience and
Remote Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011 Estimated Soil Moisture Content Map, June 2010
Slide 14
Estimated dielectric constant Map, October 2010 14 Results:
Experiment 2 IEEE International Geoscience and Remote Sensing
Symposium IGARSS 2011 Vancouver, Canada 24-29 July, 2011 Estimated
dielectric constant Map, August 2010Estimated dielectric constant
map, July 2010 Estimated Dielectric constant Map, June 2010
Slide 15
Conclusion 15 The potential of fully-polarimetric RADARSAT 2
SAR images in combination with an advanced retrieval algorithm has
been investigated for the mapping in space and time of soil
moisture in the Alpine area 1.Polarimetric features are effective
for improving the retrieval of soil moisture in the challenging
Alpine environment Generally, they allow one to reduce the
ambiguity in the data and increase the accuracy of the estimation
The HH HV/VV configuration has shown to be the most suitable in
this specific operative conditions 2.The achieved results suggest
the potential of the proposed estimation system in combination with
RADARSAT 2 SAR data for the retrieval of soil moisture in Alpine
areas Good capability to reproduce the spatial patterns of the
desired target parameter Good agreement with the measured temporal
trends of soil moisture Future work Investigation of the proposed
estimation system in combination with higher geometrical resolution
polarimetric SAR data Integration of data from different sensors
(e.g., L-Band SAR images) IEEE International Geoscience and Remote
Sensing Symposium IGARSS 2011 Vancouver, Canada 24-29 July,
2011
Slide 16
16 Thank you for the Attention!! Questions?
[email protected][email protected] IEEE
International Geoscience and Remote Sensing Symposium IGARSS 2011
Vancouver, Canada 24-29 July, 2011