scholarly journals Mapping Woody Volume of Mediterranean Forests by Using SAR and Machine Learning: A Case Study in Central Italy

2021 ◽  
Vol 13 (4) ◽  
pp. 809
Author(s):  
Emanuele Santi ◽  
Marta Chiesi ◽  
Giacomo Fontanelli ◽  
Alessandro Lapini ◽  
Simonetta Paloscia ◽  
...  
Keyword(s):  
Preliminary Investigation ◽  
Central Italy ◽  
Forest Biomass ◽  
Ground Truth ◽  
National Forest Inventory ◽  
Mediterranean Forests ◽  
Alos Palsar ◽  
Laser Altimeter ◽  
Envisat Asar ◽  
L Band

In this paper, multi-frequency synthetic aperture radar (SAR) data at L- and C-bands (ALOS PALSAR and Envisat/ASAR) were used to estimate forest biomass in Tuscany, in Central Italy. The ground measurements of woody volume (WV, in m3/ha), which can be considered as a proxy of forest biomass, were retrieved from the Italian National Forest Inventory (NFI). After a preliminary investigation to assess the sensitivity of backscatter at C- and L-bands to forest biomass, an approach based on an artificial neural network (ANN) was implemented. The ANN was trained using the backscattering coefficient at L-band (ALOS PALSAR, HH and HV polarization) and C-band (Envisat ASAR in HH polarization) as inputs. Spatially distributed WV values for the entire test area were derived by the integration (fusion) of a canopy height map derived from the Ice, Cloud, and Land Elevation Geoscience Laser Altimeter System (ICESat GLAS) and the NFI data, in order to build a significant ground truth dataset for the training stage. The analysis of the backscattering sensitivity to WV showed a moderate correlation at L-band and was almost negligible at C-band. Despite this, the ANN algorithm was able to exploit the synergy of SAR frequencies and polarizations, estimating WV with average Pearson’s correlation coefficient (R) = 0.96 and root mean square error (RMSE) ≃ 39 m3/ha when applied to the test dataset and average R = 0.86 and RMSE ≃ 75 m3/ha when validated on the direct measurements from the NFI. Considering the heterogeneity of the scenario (Mediterranean mixed forests in hilly landscape) and the small amount of available ground measurements with respect to the spatial variability of different plots, the obtained results can be considered satisfactory. Moreover, the successful use of WV from global maps for implementing the algorithm suggests the possibility to apply the algorithm to wider areas or even to global scales.

scholarly journals Comparison of Machine Learning Methods Applied to SAR Images for Forest Classification in Mediterranean Areas

2020 ◽  
Vol 12 (3) ◽  
pp. 369 ◽  
Author(s):  
Alessandro Lapini ◽  
Simone Pettinato ◽  
Emanuele Santi ◽  
Simonetta Paloscia ◽  
Giacomo Fontanelli ◽  
...  
Keyword(s):  
Machine Learning ◽  
Central Italy ◽  
Alos Palsar ◽  
Sar Images ◽  
Random Forest Classification ◽  
Envisat Asar ◽  
Learning Framework ◽  
Forest Classification ◽  
Average Accuracy ◽  
Reference Map

In this paper, multifrequency synthetic aperture radar (SAR) images from ALOS/PALSAR, ENVISAT/ASAR and Cosmo-SkyMed sensors were studied for forest classification in a test area in Central Italy (San Rossore), where detailed in-situ measurements were available. A preliminary discrimination of the main land cover classes and forest types was carried out by exploiting the synergy among L-, C- and X-bands and different polarizations. SAR data were preliminarily inspected to assess the capabilities of discriminating forest from non-forest and separating broadleaf from coniferous forests. The temporal average backscattering coefficient ( σ ¯ °) was computed for each sensor-polarization pair and labeled on a pixel basis according to the reference map. Several classification methods based on the machine learning framework were applied and validated considering different features, in order to highlight the contribution of bands and polarizations, as well as to assess the classifiers’ performance. The experimental results indicate that the different surface types are best identified by using all bands, followed by joint L- and X-bands. In the former case, the best overall average accuracy (83.1%) is achieved by random forest classification. Finally, the classification maps on class edges are discussed to highlight the misclassification errors.

Contribution of L-band SAR to systematic global mangrove monitoring

2014 ◽  
Vol 65 (7) ◽  
pp. 589 ◽  
Author(s):  
Richard Lucas ◽  
Lisa-Maria Rebelo ◽  
Lola Fatoyinbo ◽  
Ake Rosenqvist ◽  
Takuya Itoh ◽  
...  
Keyword(s):  
Policy Development ◽  
Sensor Data ◽  
Global Changes ◽  
Alos Palsar ◽  
Laser Altimeter ◽  
Mangrove Species ◽  
Shuttle Radar Topographic Mission ◽  
International Policies ◽  
The Status ◽  
L Band

Information on the status of and changes in mangroves is required for national and international policy development, implementation and evaluation. To support these requirements, a component of the Japan Aerospace Exploration Agency’s (JAXA) Kyoto and Carbon (K&C) initiative has been to design and develop capability for a Global Mangrove Watch (GMW) that routinely monitors and reports on local to global changes in the extent of mangroves, primarily on the basis of observations by Japanese L-band synthetic aperture radar (SAR). The GMW aims are as follows: (1) to map progression of change within or from existing (e.g. Landsat-derived) global baselines of the extent of mangroves by comparing advanced land-observing satellite 2 (ALOS-2) phased array L-band SAR 2 (PALSAR-2) data from 2014 with that acquired by the Japanese earth resources satellite (JERS-1) SAR (1992–1998) and ALOS PALSAR (2006–2011); (2) to quantify changes in the structure and associated losses and gains of carbon on the basis of canopy height and above-ground biomass (AGB) estimated from the shuttle radar topographic mission (SRTM; acquired 2000), the ice, cloud and land-elevation satellite (ICESAT) geoscience laser altimeter system (GLAS; 2003–2010) and L-band backscatter data; (3) to determine likely losses and gains of tree species diversity through reference to International Union for the Conservation of Nature (IUCN) global thematic layers on the distribution of mangrove species; and (4) to validate maps of changes in the extent of mangroves, primarily through comparison with dense time-series of Landsat sensor data and to use these same data to describe the causes and consequences of change. The paper outlines and justifies the techniques being implemented and the role that the GMW might play in supporting national and international policies that relate specifically to the long-term conservation of mangrove ecosystems and the services they provide to society.

scholarly journals Forest and Forest Change Mapping with C- and L-band SAR in Liwale, Tanzania

2015 ◽  
Vol XL-7/W3 ◽  
pp. 391-395
Author(s):  
J. Haarpaintner ◽  
C. Davids ◽  
H. Hindberg ◽  
E. Zahabu ◽  
R. E. Malimbwi
Keyword(s):  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Optical Data ◽  
Forest Change ◽  
Alos Palsar ◽  
Study Region ◽  
Land Type ◽  
Envisat Asar ◽  
Forest Classification ◽  
L Band

As part of a Tanzanian-Norwegian cooperation project on Monitoring Reporting and Verification (MRV) for REDD+, 2007-2011 Cand L-band synthetic aperture radar (SAR) backscatter data from Envisat ASAR and ALOS Palsar, respectively, have been processed, analysed and used for forest and forest change mapping over a study side in Liwale District in Lindi Region, Tanzania. Land cover observations from forest inventory plots of the National Forestry Resources Monitoring and Assessment (NAFORMA) project have been used for training Gaussian Mixture Models and k-means classifier that have been combined in order to map the study region into forest, woodland and non-forest areas. Maximum forest and woodland extension masks have been extracted by classifying maximum backscatter mosaics in HH and HV polarizations from the 2007-2011 ALOS Palsar coverage and could be used to map efficiently inter-annual forest change by filtering out changes in non-forest areas. Envisat ASAR APS (alternate polarization mode) have also been analysed with the aim to improve the forest/woodland/non-forest classification based on ALOS Palsar. Clearly, the combination of C-band SAR and L-band SAR provides useful information in order to smooth the classification and especially increase the woodland class, but an overall improvement for the wall-to-wall land type classification has yet to be confirmed. The quality assessment and validation of the results is done with very high resolution optical data from WorldView, Ikonos and RapidEye, and NAFORMA field observations.

scholarly journals A METHOD FOR BUILT-UP AREA EXTRACTION USING DUAL POLARIMETRIC ALOS PALSAR

2018 ◽  
Vol IV-5 ◽  
pp. 455-458 ◽  
Author(s):  
S. Sinha ◽  
A. Santra ◽  
S. S. Mitra
Keyword(s):  
Anthropogenic Activities ◽  
Spectral Characteristics ◽  
Ground Truth ◽  
Bare Soil ◽  
High Accuracy ◽  
Synthetic Aperture ◽  
Unique Combination ◽  
Alos Palsar ◽  
Multiple Regions ◽  
L Band

<p><strong>Abstract.</strong> Mapping of the built-up area is a task of exigency as the area supports varieties of anthropogenic activities and is important for several ecosystem services. The task becomes more complicated owing to similarities in spectral characteristics with the bare soil. A new radar-based approach is proposed using Synthetic Aperture Radar (SAR) HH/HV dual polarized L-band ALOS PALSAR data. Sigma nought (&amp;sigma;<sup>0</sup>) values are extracted from the HH and HV polarized data. HH and HV sigma nought images are ratioed and normalized and then equated together in a unique combination to generate an index that is developed, cross-checked and validated over multiple regions, with simultaneous inputs from Ground truth (GT) data. Maps developed using the index is classified into built-up and non built-up areas, where the results show that the proposed method is very effective for built-up area detection. The approach adopted in this study is acceptable due to its high accuracy, simplicity and reliability; and hence easy to replicate.</p>

scholarly journals Growing Stock Volume Retrieval from Single and Multi-Frequency Radar Backscatter

Forests ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 944
Author(s):  
Mihai A. Tanase ◽  
Ignacio Borlaf-Mena ◽  
Maurizio Santoro ◽  
Cristina Aponte ◽  
Gheorghe Marin ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Temporal Frequency ◽  
National Forest Inventory ◽  
Easy Access ◽  
Estimation Errors ◽  
Growing Stock ◽  
L Band ◽  
Stock Volume ◽  
Global Datasets ◽  
Relative Root

While products generated at global levels provide easy access to information on forest growing stock volume (GSV), their use at regional to national levels is limited by temporal frequency, spatial resolution, or unknown local errors that may be overcome through locally calibrated products. This study assessed the need, and utility, of developing locally calibrated GSV products for the Romanian forests. To this end, we used national forest inventory (NFI) permanent sampling plots with largely concurrent SAR datasets acquired at C- and L-bands to train and validate a machine learning algorithm. Different configurations of independent variables were evaluated to assess potential synergies between C- and L-band. The results show that GSV estimation errors at C- and L-band were rather similar, relative root mean squared errors (RelRMSE) around 55% for forests averaging over 450 m3 ha−1, while synergies between the two wavelengths were limited. Locally calibrated models improved GSV estimation by 14% when compared to values obtained from global datasets. However, even the locally calibrated models showed particularly large errors over low GSV intervals. Aggregating the results over larger areas considerably reduced (down to 25%) the relative estimation errors.

Land subsidence characteristics of Bandung Basin as revealed by ENVISAT ASAR and ALOS PALSAR interferometry

2014 ◽  
Vol 154 ◽  
pp. 46-60 ◽  
Author(s):  
Linlin Ge ◽  
Alex Hay-Man Ng ◽  
Xiaojing Li ◽  
Hasanuddin Z. Abidin ◽  
Irwan Gumilar
Keyword(s):  
Land Subsidence ◽  
Alos Palsar ◽  
Envisat Asar

A Digital Terrain Modeling Method in Urban Areas by the ICESat-2 (Generating precise terrain surface profiles from photon-counting technology)

2021 ◽  
Vol 87 (4) ◽  
pp. 237-248
Author(s):  
Nahed Osama ◽  
Bisheng Yang ◽  
Yue Ma ◽  
Mohamed Freeshah
Keyword(s):  
Urban Areas ◽  
Spatial Clustering ◽  
Photon Counting ◽  
Ground Surface ◽  
Ground Truth ◽  
Surface Model ◽  
Laser Altimeter ◽  
Ground Truth Data ◽  
Urban Scenes ◽  
Terrain Surface

The ICE, Cloud and land Elevation Satellite-2 (ICES at-2) can provide new measurements of the Earth's elevations through photon-counting technology. Most research has focused on extracting the ground and the canopy photons in vegetated areas. Yet the extraction of the ground photons from urban areas, where the vegetation is mixed with artificial constructions, has not been fully investigated. This article proposes a new method to estimate the ground surface elevations in urban areas. The ICES at-2 signal photons were detected by the improved Density-Based Spatial Clustering of Applications with Noise algorithm and the Advanced Topographic Laser Altimeter System algorithm. The Advanced Land Observing Satellite-1 PALSAR –derived digital surface model has been utilized to separate the terrain surface from the ICES at-2 data. A set of ground-truth data was used to evaluate the accuracy of these two methods, and the achieved accuracy was up to 2.7 cm, which makes our method effective and accurate in determining the ground elevation in urban scenes.

scholarly journals Integrated radar and lidar analysis reveals extensive loss of remaining intact forest on Sumatra 2007–2010

2015 ◽  
Vol 12 (22) ◽  
pp. 6637-6653 ◽  
Author(s):  
M. B. Collins ◽  
E. T. A. Mitchard
Keyword(s):  
Average Rate ◽  
Forest Biomass ◽  
Forest Monitoring ◽  
Synthetic Aperture ◽  
Lidar Data ◽  
Above Ground Biomass ◽  
Swamp Forest ◽  
L Band ◽  
Field Plots ◽  
Change Map

Abstract. Forests with high above-ground biomass (AGB), including those growing on peat swamps, have historically not been thought suitable for biomass mapping and change detection using synthetic aperture radar (SAR). However, by integrating L-band (λ = 0.23 m) SAR from the ALOS and lidar from the ICESat Earth-Observing satellites with 56 field plots, we were able to create a forest biomass and change map for a 10.7 Mha section of eastern Sumatra that still contains high AGB peat swamp forest. Using a time series of SAR data we estimated changes in both forest area and AGB. We estimate that there was 274 ± 68 Tg AGB remaining in natural forest (&amp;geq; 20 m height) in the study area in 2007, with this stock reducing by approximately 11.4 % over the subsequent 3 years. A total of 137.4 kha of the study area was deforested between 2007 and 2010, an average rate of 3.8 % yr−1. The ability to attribute forest loss to different initial biomass values allows for far more effective monitoring and baseline modelling for avoided deforestation projects than traditional, optical-based remote sensing. Furthermore, given SAR's ability to penetrate the smoke and cloud which normally obscure land cover change in this region, SAR-based forest monitoring can be relied on to provide frequent imagery. This study demonstrates that, even at L-band, which typically saturates at medium biomass levels (ca. 150 Mg ha−1), in conjunction with lidar data, it is possible to make reliable estimates of not just the area but also the carbon emissions resulting from land use change.

scholarly journals Multi-Sensor InSAR Analysis of Progressive Land Subsidence over the Coastal City of Urayasu, Japan

2018 ◽  
Vol 10 (8) ◽  
pp. 1304 ◽  
Author(s):  
Yusupujiang Aimaiti ◽  
Fumio Yamazaki ◽  
Wen Liu
Keyword(s):  
Synthetic Aperture Radar ◽  
Survey Data ◽  
Land Subsidence ◽  
Ground Deformation ◽  
Tohoku Earthquake ◽  
Synthetic Aperture ◽  
Alos Palsar ◽  
The 2011 Tohoku Earthquake ◽  
L Band ◽  
Aperture Radar

In earthquake-prone areas, identifying patterns of ground deformation is important before they become latent risk factors. As one of the severely damaged areas due to the 2011 Tohoku earthquake in Japan, Urayasu City in Chiba Prefecture has been suffering from land subsidence as a part of its land was built by a massive land-fill project. To investigate the long-term land deformation patterns in Urayasu City, three sets of synthetic aperture radar (SAR) data acquired during 1993–2006 from European Remote Sensing satellites (ERS-1/-2 (C-band)), during 2006–2010 from the Phased Array L-band Synthetic Aperture Radar onboard the Advanced Land Observation Satellite (ALOS PALSAR (L-band)) and from 2014–2017 from the ALOS-2 PALSAR-2 (L-band) were processed by using multitemporal interferometric SAR (InSAR) techniques. Leveling survey data were also used to verify the accuracy of the InSAR-derived results. The results from the ERS-1/-2, ALOS PALSAR and ALOS-2 PALSAR-2 data processing showed continuing subsidence in several reclaimed areas of Urayasu City due to the integrated effects of numerous natural and anthropogenic processes. The maximum subsidence rate of the period from 1993 to 2006 was approximately 27 mm/year, while the periods from 2006 to 2010 and from 2014 to 2017 were approximately 30 and 18 mm/year, respectively. The quantitative validation results of the InSAR-derived deformation trend during the three observation periods are consistent with the leveling survey data measured from 1993 to 2017. Our results further demonstrate the advantages of InSAR measurements as an alternative to ground-based measurements for land subsidence monitoring in coastal reclaimed areas.

Forest Biomass Retrieval From L-Band SAR Using Tomographic Ground Backscatter Removal

2018 ◽  
Vol 15 (7) ◽  
pp. 1030-1034 ◽  
Author(s):  
Erik Blomberg ◽  
Laurent Ferro-Famil ◽  
Maciej J. Soja ◽  
Lars M. H. Ulander ◽  
Stefano Tebaldini
Keyword(s):  
Forest Biomass ◽  
L Band
Sign in / Sign up

Export Citation Format

Share Document