Jaan Praks | Aalto University (original) (raw)

Papers by Jaan Praks

Research paper thumbnail of Improved Semisupervised UNet Deep Learning Model for Forest Height Mapping With Satellite SAR and Optical Data

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

In this study, we introduce an improved semisupervised deep learning approach, and demonstrate it... more In this study, we introduce an improved semisupervised deep learning approach, and demonstrate its suitability for modeling the relationship between forest structural parameters and satellite remote sensing imagery and producing forest maps. The improved approach is based on a popular UNet model, modified and fine-tuned to improve the forest parameter prediction performance. Within the improved model, squeeze-and-excitation blocks are embedded to recalibrate the multisource features via retrieved channel-wise self-attention and a novel cross-pseudo regression strategy is implemented to train the model in a semisupervised way. The improvement imposes consistency learning on two perturbed network branches: 1) generating regression pseudoreference; 2) expanding the dataset size. For demonstration, we used satellite synthetic aperture radar (SAR) Sentinel-1 and multispectral optical Sentinel-2 images as remote sensing data, complemented with reference data represented by forest tree height as one of the key forest structural variables. The study area is located in a boreal forestland in Central Finland. Proposed approach showed larger accuracy compared to traditional machine learning methods such as random forests and boosting trees, and baseline UNet model. Best accuracy figures for forest tree height were achieved with combined SAR and optical imagery and were as small as 24.1% root-mean-square error (RMSE) on pixel-level and 15.4% RMSE on forest stand level.

Research paper thumbnail of Wet Snow Depth from Tandem-X Single-Pass Insar Dem Differencing

IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

Single pass radar interferometry (sp-InSAR) is a well established technique for generation of dig... more Single pass radar interferometry (sp-InSAR) is a well established technique for generation of digital elevation models (DEM). Differencing two DEMs acquired at different times can reveal topographic changes. However snow depth estimation by DEM differencing is still an ongoing topic in radar research: in contrast to snow free surfaces, the snow surface elevation is difficult to detect either because of microwave penetration into dry snow or because of the weak backscatter return from wet snow which significantly decorrelates the interferometric signal. In this study we demonstrate first results of wet snow depth estimation by differencing sp-InSAR DEMs acquired by the TanDEM-X satellite mission. The results show, in contrast to dry snow, a clear sensitivity to wet snow. However, additionally to a high vertical sensitivity of a few ten centimeters a very low noise-equivalent-sigma-zero (NESZ) is crucial for successful snow depth estimation.

Research paper thumbnail of Opponent

Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Jaan Praks Name of the docto... more Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Jaan Praks Name of the doctoral dissertation Radar polarimetry and interferometry for remote sensing of boreal forest Publisher School of Electrical Engineering

Research paper thumbnail of Abstract book of the Finnish Remote Sensing Days 2013

This paper presents the main results of the ReCover project in state Chiapas, the study site in M... more This paper presents the main results of the ReCover project in state Chiapas, the study site in Mexico. The results include wall-to-wall forest mapping of the state in

Research paper thumbnail of Editorial Summary, Remote Sensing Special Issue "Advances in Remote Sensing for Global Forest Monitoring

Remote. Sens., 2021

The need for timely, spatially, and thematically accurate information regarding forests is increa... more The need for timely, spatially, and thematically accurate information regarding forests is increasing because of the key role of forests in the global carbon balance and sustainable social, economic, ecological, and cultural development [...]

Research paper thumbnail of Separability of Mowing and Ploughing Events on Short Temporal Baseline Sentinel-1 Coherence Time Series

Remote Sensing, 2020

Short temporal baseline regular Synthetic Aperture Radar (SAR) interferometry is a tool well suit... more Short temporal baseline regular Synthetic Aperture Radar (SAR) interferometry is a tool well suited for wide area monitoring of agricultural activities, urgently needed in European Union Common Agricultural Policy (CAP) enforcement. In this study, we demonstrate and describe in detail, how mowing and ploughing events can be identified from Sentinel-1 6-day interferometric coherence time series. The study is based on a large dataset of 386 dual polarimetric Sentinel-1 VV/VH SAR and 351 Sentinel-2 optical images, and nearly 2000 documented mowing and ploughing events on more than 1000 parcels (average 10.6 ha, smallest 0.6 ha, largest 108.5 ha). Statistical analysis revealed that mowing and ploughing cause coherence to increase when compared to values before an event. In the case of mowing, the coherence increased from 0.18 to 0.35, while Sentinel-2 NDVI (indicating the amount of green chlorophyll containing biomass) at the same time decreased from 0.75 to 0.5. For mowing, there was v...

Research paper thumbnail of Detection of Forest Windstorm Damages with Multitemporal SAR Data—A Case Study: Finland

Remote Sensing, 2021

The purpose of this study was to develop methods to localize forest windstorm damages, assess the... more The purpose of this study was to develop methods to localize forest windstorm damages, assess their severity and estimate the total damaged area using space-borne SAR data. The development of the methods is the first step towards an operational system for near-real-time windstorm damage monitoring, with a latency of only a few days after the storm event in the best case. Windstorm detection using SAR data is not trivial, particularly at C-band. It can be expected that a large-area and severe windstorm damage may affect backscatter similar to clear cutting operation, that is, decrease the backscatter intensity, while a small area damage may increase the backscatter of the neighboring area, due to various scattering mechanisms. The remaining debris and temporal variation in the weather conditions and possible freeze–thaw transitions also affect observed backscatter changes. Three candidate windstorm detection methods were suggested, based on the improved k-nn method, multinomial logis...

Research paper thumbnail of Assessment of Operational Microsatellite Based SAR for Earth Observation Applications

2018 2nd URSI Atlantic Radio Science Meeting (AT-RASC), 2018

Research paper thumbnail of Mapping Forest Disturbance Due to Selective Logging in the Congo Basin with RADARSAT-2 Time Series

Remote Sensing, 2021

Dense time series of stripmap RADARSAT-2 data acquired in the Multilook Fine mode were used for d... more Dense time series of stripmap RADARSAT-2 data acquired in the Multilook Fine mode were used for detecting and mapping the extent of selective logging operations in the tropical forest area in the northern part of the Republic of the Congo. Due to limited radiometric sensitivity to forest biomass variation at C-band, basic multitemporal change detection approach was supplemented by spatial texture analysis to separate disturbed forest from intact. The developed technique primarily uses multi-temporal aggregation of orthorectified synthetic aperture radar (SAR) imagery that are acquired before and after the logging operations. The actual change analysis is based on textural features of the log-ratio image calculated using two SAR temporal composites compiled of SAR scenes acquired before and after the logging operations. Multitemporal aggregation and filtering of SAR scenes decreased speckle and made the extracted textural features more prominent. The overall detection accuracy was ar...

Research paper thumbnail of Wide-Area Land Cover Mapping With Sentinel-1 Imagery Using Deep Learning Semantic Segmentation Models

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021

Land cover (LC) mapping is essential for monitoring the environment and understanding the effects... more Land cover (LC) mapping is essential for monitoring the environment and understanding the effects of human activities on it. Recent studies demonstrated successful applications of specific deep learning models to small-scale LC mapping tasks (e.g., wetland mapping). However, it is not readily clear which of the existing state-of-the-art models for natural images are the best candidates to be taken for the particular remote sensing task and data. In this article, we answer that question for mapping the fundamental LC classes using the satellite imaging radar data. We took ESA Sentinel-1 C-band SAR images acquired during the whole summer season of 2018 in Finland, which are representative of the land cover in the country. CORINE LC map was used as a reference, and the models were trained to distinguish between the five major CORINE-based classes. We selected seven among the state-of-theart semantic segmentation models so that they cover a diverse set of approaches: U-Net, DeepLabV3+, PSPNet, BiSeNet, SegNet, FC-DenseNet, and FRRN-B, and further fine-tuned them. Upon evaluation and benchmarking, all the models demonstrated solid performance with overall accuracy between 87.9% and 93.1%, with good to a very good agreement (Kappa statistic between 0.75 and 0.86). The two best models were fully convolutional DenseNets (FC-DenseNet) and SegNet (encoder-decoder-skip), with the latter having a much shorter inference time. Overall, our results indicate that the semantic segmentation models are suitable for efficient wide-area mapping using satellite SAR imagery and provide baseline accuracy against which the newly proposed models should be evaluated.

Research paper thumbnail of Multi-Sensor Aboveground Biomass Estimation in the Broadleaved Hyrcanian Forest of Iran

Canadian Journal of Remote Sensing, 2021

In this study, the capability of Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1), and their comb... more In this study, the capability of Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1), and their combination was investigated for estimating aboveground biomass (AGB). A pure stand of Fagus Orientalis located in the Hyrcanian forest of Iran was selected as the study area. The performance of a parametric approach, i.e., Multiple Linear Regression (MLR) model and non-parametric approaches, i.e., k-Nearest Neighbor (k-NN), Random Forest (RF), and Support Vector Regression (SVR), were also evaluated for AGB estimations. Our results indicated that among S2 metrics, the FAPAR canopy biophysical index and NDVI index based on the red-edge band (NIR-b8a) have the highest correlation coefficient (r) of 0.420 and 0.417, respectively. The results of AGB estimation showed that a combination of S2 and S1 datasets using the k-NN algorithm had the best accuracy (R 2 of 0.57 and rRMSE of 14.68%). The best rRMSE using L8, S2, and S1 datasets was 18.95, 16.99, and 19.17% using k-NN, k-NN, and MLR algorithms, respectively. The combination of L8 with S1 dataset also improved the rRMSE relative to L8 and S1 separately by 0.96 and 1.18%, respectively. We concluded that the combination of optical data (L8 or S2) with SAR data (S1) improves the broadleaved Hyrcanian AGB estimation. RÉSUMÉ Dans cette etude, la capacit e de Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1) et leur combinaison ont et e etudi ees pour estimer la biomasse a erienne (AGB). Un peuplement pur de Fagus Orientalis situ e dans la forêt hyrcanienne d'Iran a et e choisi comme zone d' etude. Le rendement d'une approche param etrique, c'est-a-dire, le mod ele de r egression lin eaire multiple (MLR) et les approches non param etriques, c'est-a-dire, k-Nearest Neighbor (k-NN), Random Forest (RF) et Support Vector Regression (SVR), ont et e evalu es pour les estimations de la biomasse. Nos r esultats indiquent que parmi les mesures S2, l'indice biophysique de la canop ee FAPAR et l'indice NDVI bas e sur la bande red-edge (NIR-b8a) ont les coefficients de corr elation les plus elev es (r) soit 0,420 et 0,417 respectivement. Les r esultats de l'estimation de l'AGB montrent qu'une combinaison des donn ees S2 et S1 utilisant l'algorithme k-NN donne la meilleure pr ecision (R2 de 0,57 et rRMSE de 14,68%). Le meilleur rRMSE en utilisant les ensembles de donn ees L8, S2 et S1 etait de 18,95%, 16,99% et 19,17% en utilisant respectivement les algorithmes k-NN, k-NN et MLR. La combinaison des ensembles de donn ees L8 et S1 a egalement am elior e le rRMSE de 0,96% et 1,18% par rapport aux donn ees L8 et S1 s epar ement. En conclusion, la combinaison des donn ees optiques (L8 ou S2) avec les donn ees SAR (S1) am eliore l'estimation de l'AGB de la forêt de feuillus hyrcanienne.

Research paper thumbnail of SodSAR: A Tower-Based 1–10 GHz SAR System for Snow, Soil and Vegetation Studies

Sensors, 2020

We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic A... more We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic Aperture Radar (SAR) aimed at snow, soil and vegetation studies. The instrument is located in the Arctic Space Centre of the Finnish Meteorological Institute in Sodankylä, Finland. The system is based on a Vector Network Analyzer (VNA)-operated scatterometer mounted on a rail allowing the formation of SAR images, including interferometric pairs separated by a temporal baseline. We present the description of the radar, the applied SAR focusing technique, the radar calibration and measurement stability analysis. Measured stability of the backscattering intensity over a three-month period was observed to be better than 0.5 dB, when measuring a target with a known radar cross section. Deviations of the estimated target range were in the order of a few cm over the same period, indicating also good stability of the measured phase. Interforometric SAR (InSAR) capabilities are also discussed, and...

Research paper thumbnail of Long Term Interferometric Temporal Coherence and DInSAR Phase in Northern Peatlands

Remote Sensing, 2020

Peatlands of northern temperate and cold climates are significant pools of stored carbon. Underst... more Peatlands of northern temperate and cold climates are significant pools of stored carbon. Understanding seasonal dynamics of peatland surface height and volume, often referred to as mire breathing or oscillation, is the key to improve spatial models of material flow and gas exchange. The monitoring of this type of dynamics over large areas is only feasible by remote sensing instruments. The objective of this study is to examine the applicability of Sentinel-1 synthetic aperture radar interferometry (InSAR) to characterize seasonal dynamics of peatland surface height and water table (WT) over open raised bog areas in Endla mire complex in central Estonia, characteristic for northern temperate bogs. Our results show that InSAR temporal coherence, sufficient for differential InSAR (DInSAR), is preserved in the open bog over more than six months of temporal baseline. Moreover, the coherence which is lost in a dry summer, make a recovery in autumn correlate with WT dynamics. The relation...

Research paper thumbnail of Sentinel-1 InSAR Coherence for Land Cover Mapping: A Comparison of Multiple Feature-Based Classifiers

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020

This article investigates and demonstrates the suitability of the Sentinel-1 interferometric cohe... more This article investigates and demonstrates the suitability of the Sentinel-1 interferometric coherence for land cover and vegetation mapping. In addition, this study analyzes the Manuscript

Research paper thumbnail of Cropland Classification Using Sentinel-1 Time Series: Methodological Performance and Prediction Uncertainty Assessment

Remote Sensing, 2019

Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the dis... more Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Mult...

Research paper thumbnail of Is Accurate Synoptic Altimetry Achievable by Means of Interferometric GNSS-R?

Remote Sensing, 2019

This paper evaluates the capability of interferometric global navigation satellite system reflect... more This paper evaluates the capability of interferometric global navigation satellite system reflectometry (GNSS-R) to perform sea surface altimetry in a synoptic scenario. Such purpose, which requires the combination of the results from different GNSS signals, constitutes a unique characteristic of this approach. Interferometric GNSS-R group delay altimetry has been proven to be more precise than conventional GNSS-R. However, the self-consistency and accuracy of their synoptic solutions (simultaneous multi-static results) have never been proved before. In our work, we analyze a dataset of GNSS signals reflected off the Baltic Sea acquired during an airborne campaign using a receiver that was developed for such a purpose. Among other features, it enables beamformer capability in post-processing to get multiple and simultaneous GNSS signals under the interferometric approach’s restrictions. In particular, the signals from two GPS and two Galileo satellites, at two frequency bands (L1 an...

Research paper thumbnail of Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

Remote Sensing, 2019

Natural disturbances significantly influence forest ecosystem services and biodiversity. Accurate... more Natural disturbances significantly influence forest ecosystem services and biodiversity. Accurate delineation and early detection of areas affected by disturbances are critical for estimating extent of damage, assessing economical influence and guiding forest management activities. In this study we focus on snow load damage detection from C-Band SAR images. Snow damage is one of the least studied forest damages, which is getting more common due to current climate trends. The study site was located in the southern part of Northern Finland and the SAR data were represented by the time series of C-band SAR scenes acquired by the Sentinel-1 sensor. Methods used in the study included improved k nearest neighbour method, logistic regression analysis and support vector machine classification. Snow damage recordings from a large snow damage event that took place in Finland during late 2018 were used as reference data. Our results showed an overall detection accuracy of 90%, indicating poten...

Research paper thumbnail of Polarimetric ALOS PALSAR Time Series in Mapping Biomass of Boreal Forests

Remote Sensing, 2017

Here, we examined multitemporal behavior of fully polarimetric SAR (PolSAR) parameters at L-band ... more Here, we examined multitemporal behavior of fully polarimetric SAR (PolSAR) parameters at L-band in relation to the stem volume of boreal forests. The PolSAR parameters were evaluated in terms of their temporal consistency, interdependence and suitability for forest stem volume estimation across several seasonal conditions (frozen, thaw and unfrozen). The satellite SAR data were represented by a time series of PolSAR images acquired during several seasons in the years 2006 to 2009 by the ALOS PALSAR sensor. The study area was in central Finland, and represented a managed area in typical boreal mixed forest land. Utility of different PolSAR parameters, their temporal stability and cross-correlations were studied along with reference stand-level stem volume data from forest inventory. Further, two polarimetric parameters, cross-polarization backscatter and co-polarization coherence, were chosen for further investigation and stem volume retrieval. A relationship between forest stem volume and PolSAR parameters was established using the kNN regression approach. Ways of optimally combining PolSAR images were evaluated as well. For a single scene, best results were observed with polarimetric coherence (RMSE ≈ 38.8 m 3 /ha) for scene acquired in frozen conditions. An RMSE of 40.8 m 3 /ha (42.9%, R 2 = 0.66) was achieved for cross-polarization backscatter in the best case. Cross-polarization backscatter was a better predictor than polarimetric coherence for few summer scenes. Multitemporal aggregation of selected PolSAR scenes improved estimates for both studied PolSAR parameters. Stronger improvement was observed for coherence with RMSE down to 34 m 3 /ha (35.8%, R 2 = 0.77) compared to 38.8-51.6 m 3 /ha (40.8-54.3%) from separate scenes. Finally, the accuracy statistics reached RMSE of 32.2 m 3 /ha (34%, R 2 = 0.79) when multitemporal HHVV coherence was combined with multitemporal HV-backscatter.

Research paper thumbnail of A Study of Landfast Ice with Sentinel-1 Repeat-Pass Interferometry over the Baltic Sea

Remote Sensing, 2017

Mapping of fast ice displacement and investigating sea ice rheological behavior is a major open t... more Mapping of fast ice displacement and investigating sea ice rheological behavior is a major open topic in coastal ice engineering and sea ice modeling. This study presents first results on Sentinel-1 repeat-pass space borne synthetic aperture radar interferometry (InSAR) in the Gulf of Bothnia over the fast ice areas. An InSAR pair acquired in February 2015 with a temporal baseline of 12 days has been studied here in detail. According to our results, the surface of landfast ice in the study area was stable enough to preserve coherence over the 12-day baseline, while previous InSAR studies over the fast ice used much shorter temporal baselines. The advantage of longer temporal baseline is in separating the fast ice from drift ice and detecting long term trends in deformation maps. The interferogram showed displacement of fast ice on the order of 40 cm in the study area. Parts of the displacements were attributed to forces caused by sea level tilt, currents, and thermal expansion, but the main factor of the displacement seemed to be due to compression of the drift ice driven by southwest winds with high speed. Further interferometric phase and the coherence measurements over the fast ice are needed in the future for understanding sea ice mechanism and establishing sustainability of the presented InSAR approach for monitoring dynamics of the landfast ice with Sentinel-1 data.

Research paper thumbnail of Seasonal effects on the estimation of height of boreal and deciduous forests from interferometric TanDEM-X coherence data

Earth Resources and Environmental Remote Sensing/GIS Applications VI, 2015

The aim of this study is to assess the performance of single-pass X-band bistatic SAR interferome... more The aim of this study is to assess the performance of single-pass X-band bistatic SAR interferometric forest height estimation of boreal and temperate deciduous forests under variable seasonal conditions. For this, twelve acquisitions of single-and dual-polarized TanDEM-X coherence images over 118 forest stands were analyzed and compared against LiDAR forest height maps. Strong correlations were found between interferometric coherence magnitude and LiDAR derived forest stand height for pine forests (r 2 =0.94) and spruce forest (r 2 =0.87) as well as for deciduous trees (r 2 =0.94) during leaf-off conditions with temperatures below 0°C. It was found that coherence magnitude based forest height estimation is influenced by leaf-on and leaf-off conditions as well as daily temperature fluctuations, height of ambiguity and effective baseline. These factors alter the correlation and should be taken into account for accurate coherence-based height retrieval. Despite the influence of the mentioned factors, generally a strong relationship in regression analysis between X-band SAR coherence and LiDAR derived forest stand height can be found. Moreover, a simple semi empirical model, derived from Random Volume over Ground model, is presented. The model takes into account all imaging geometry dependent parameters and allows to derive tree height estimate without a priori knowledge. Our results show that X-band SAR interferometry can be used to estimate forest canopy height for boreal and deciduous forests in both summer and winter, but the conditions should be stable.

Research paper thumbnail of Improved Semisupervised UNet Deep Learning Model for Forest Height Mapping With Satellite SAR and Optical Data

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

In this study, we introduce an improved semisupervised deep learning approach, and demonstrate it... more In this study, we introduce an improved semisupervised deep learning approach, and demonstrate its suitability for modeling the relationship between forest structural parameters and satellite remote sensing imagery and producing forest maps. The improved approach is based on a popular UNet model, modified and fine-tuned to improve the forest parameter prediction performance. Within the improved model, squeeze-and-excitation blocks are embedded to recalibrate the multisource features via retrieved channel-wise self-attention and a novel cross-pseudo regression strategy is implemented to train the model in a semisupervised way. The improvement imposes consistency learning on two perturbed network branches: 1) generating regression pseudoreference; 2) expanding the dataset size. For demonstration, we used satellite synthetic aperture radar (SAR) Sentinel-1 and multispectral optical Sentinel-2 images as remote sensing data, complemented with reference data represented by forest tree height as one of the key forest structural variables. The study area is located in a boreal forestland in Central Finland. Proposed approach showed larger accuracy compared to traditional machine learning methods such as random forests and boosting trees, and baseline UNet model. Best accuracy figures for forest tree height were achieved with combined SAR and optical imagery and were as small as 24.1% root-mean-square error (RMSE) on pixel-level and 15.4% RMSE on forest stand level.

Research paper thumbnail of Wet Snow Depth from Tandem-X Single-Pass Insar Dem Differencing

IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

Single pass radar interferometry (sp-InSAR) is a well established technique for generation of dig... more Single pass radar interferometry (sp-InSAR) is a well established technique for generation of digital elevation models (DEM). Differencing two DEMs acquired at different times can reveal topographic changes. However snow depth estimation by DEM differencing is still an ongoing topic in radar research: in contrast to snow free surfaces, the snow surface elevation is difficult to detect either because of microwave penetration into dry snow or because of the weak backscatter return from wet snow which significantly decorrelates the interferometric signal. In this study we demonstrate first results of wet snow depth estimation by differencing sp-InSAR DEMs acquired by the TanDEM-X satellite mission. The results show, in contrast to dry snow, a clear sensitivity to wet snow. However, additionally to a high vertical sensitivity of a few ten centimeters a very low noise-equivalent-sigma-zero (NESZ) is crucial for successful snow depth estimation.

Research paper thumbnail of Opponent

Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Jaan Praks Name of the docto... more Aalto University, P.O. Box 11000, FI-00076 Aalto www.aalto.fi Author Jaan Praks Name of the doctoral dissertation Radar polarimetry and interferometry for remote sensing of boreal forest Publisher School of Electrical Engineering

Research paper thumbnail of Abstract book of the Finnish Remote Sensing Days 2013

This paper presents the main results of the ReCover project in state Chiapas, the study site in M... more This paper presents the main results of the ReCover project in state Chiapas, the study site in Mexico. The results include wall-to-wall forest mapping of the state in

Research paper thumbnail of Editorial Summary, Remote Sensing Special Issue "Advances in Remote Sensing for Global Forest Monitoring

Remote. Sens., 2021

The need for timely, spatially, and thematically accurate information regarding forests is increa... more The need for timely, spatially, and thematically accurate information regarding forests is increasing because of the key role of forests in the global carbon balance and sustainable social, economic, ecological, and cultural development [...]

Research paper thumbnail of Separability of Mowing and Ploughing Events on Short Temporal Baseline Sentinel-1 Coherence Time Series

Remote Sensing, 2020

Short temporal baseline regular Synthetic Aperture Radar (SAR) interferometry is a tool well suit... more Short temporal baseline regular Synthetic Aperture Radar (SAR) interferometry is a tool well suited for wide area monitoring of agricultural activities, urgently needed in European Union Common Agricultural Policy (CAP) enforcement. In this study, we demonstrate and describe in detail, how mowing and ploughing events can be identified from Sentinel-1 6-day interferometric coherence time series. The study is based on a large dataset of 386 dual polarimetric Sentinel-1 VV/VH SAR and 351 Sentinel-2 optical images, and nearly 2000 documented mowing and ploughing events on more than 1000 parcels (average 10.6 ha, smallest 0.6 ha, largest 108.5 ha). Statistical analysis revealed that mowing and ploughing cause coherence to increase when compared to values before an event. In the case of mowing, the coherence increased from 0.18 to 0.35, while Sentinel-2 NDVI (indicating the amount of green chlorophyll containing biomass) at the same time decreased from 0.75 to 0.5. For mowing, there was v...

Research paper thumbnail of Detection of Forest Windstorm Damages with Multitemporal SAR Data—A Case Study: Finland

Remote Sensing, 2021

The purpose of this study was to develop methods to localize forest windstorm damages, assess the... more The purpose of this study was to develop methods to localize forest windstorm damages, assess their severity and estimate the total damaged area using space-borne SAR data. The development of the methods is the first step towards an operational system for near-real-time windstorm damage monitoring, with a latency of only a few days after the storm event in the best case. Windstorm detection using SAR data is not trivial, particularly at C-band. It can be expected that a large-area and severe windstorm damage may affect backscatter similar to clear cutting operation, that is, decrease the backscatter intensity, while a small area damage may increase the backscatter of the neighboring area, due to various scattering mechanisms. The remaining debris and temporal variation in the weather conditions and possible freeze–thaw transitions also affect observed backscatter changes. Three candidate windstorm detection methods were suggested, based on the improved k-nn method, multinomial logis...

Research paper thumbnail of Assessment of Operational Microsatellite Based SAR for Earth Observation Applications

2018 2nd URSI Atlantic Radio Science Meeting (AT-RASC), 2018

Research paper thumbnail of Mapping Forest Disturbance Due to Selective Logging in the Congo Basin with RADARSAT-2 Time Series

Remote Sensing, 2021

Dense time series of stripmap RADARSAT-2 data acquired in the Multilook Fine mode were used for d... more Dense time series of stripmap RADARSAT-2 data acquired in the Multilook Fine mode were used for detecting and mapping the extent of selective logging operations in the tropical forest area in the northern part of the Republic of the Congo. Due to limited radiometric sensitivity to forest biomass variation at C-band, basic multitemporal change detection approach was supplemented by spatial texture analysis to separate disturbed forest from intact. The developed technique primarily uses multi-temporal aggregation of orthorectified synthetic aperture radar (SAR) imagery that are acquired before and after the logging operations. The actual change analysis is based on textural features of the log-ratio image calculated using two SAR temporal composites compiled of SAR scenes acquired before and after the logging operations. Multitemporal aggregation and filtering of SAR scenes decreased speckle and made the extracted textural features more prominent. The overall detection accuracy was ar...

Research paper thumbnail of Wide-Area Land Cover Mapping With Sentinel-1 Imagery Using Deep Learning Semantic Segmentation Models

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021

Land cover (LC) mapping is essential for monitoring the environment and understanding the effects... more Land cover (LC) mapping is essential for monitoring the environment and understanding the effects of human activities on it. Recent studies demonstrated successful applications of specific deep learning models to small-scale LC mapping tasks (e.g., wetland mapping). However, it is not readily clear which of the existing state-of-the-art models for natural images are the best candidates to be taken for the particular remote sensing task and data. In this article, we answer that question for mapping the fundamental LC classes using the satellite imaging radar data. We took ESA Sentinel-1 C-band SAR images acquired during the whole summer season of 2018 in Finland, which are representative of the land cover in the country. CORINE LC map was used as a reference, and the models were trained to distinguish between the five major CORINE-based classes. We selected seven among the state-of-theart semantic segmentation models so that they cover a diverse set of approaches: U-Net, DeepLabV3+, PSPNet, BiSeNet, SegNet, FC-DenseNet, and FRRN-B, and further fine-tuned them. Upon evaluation and benchmarking, all the models demonstrated solid performance with overall accuracy between 87.9% and 93.1%, with good to a very good agreement (Kappa statistic between 0.75 and 0.86). The two best models were fully convolutional DenseNets (FC-DenseNet) and SegNet (encoder-decoder-skip), with the latter having a much shorter inference time. Overall, our results indicate that the semantic segmentation models are suitable for efficient wide-area mapping using satellite SAR imagery and provide baseline accuracy against which the newly proposed models should be evaluated.

Research paper thumbnail of Multi-Sensor Aboveground Biomass Estimation in the Broadleaved Hyrcanian Forest of Iran

Canadian Journal of Remote Sensing, 2021

In this study, the capability of Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1), and their comb... more In this study, the capability of Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1), and their combination was investigated for estimating aboveground biomass (AGB). A pure stand of Fagus Orientalis located in the Hyrcanian forest of Iran was selected as the study area. The performance of a parametric approach, i.e., Multiple Linear Regression (MLR) model and non-parametric approaches, i.e., k-Nearest Neighbor (k-NN), Random Forest (RF), and Support Vector Regression (SVR), were also evaluated for AGB estimations. Our results indicated that among S2 metrics, the FAPAR canopy biophysical index and NDVI index based on the red-edge band (NIR-b8a) have the highest correlation coefficient (r) of 0.420 and 0.417, respectively. The results of AGB estimation showed that a combination of S2 and S1 datasets using the k-NN algorithm had the best accuracy (R 2 of 0.57 and rRMSE of 14.68%). The best rRMSE using L8, S2, and S1 datasets was 18.95, 16.99, and 19.17% using k-NN, k-NN, and MLR algorithms, respectively. The combination of L8 with S1 dataset also improved the rRMSE relative to L8 and S1 separately by 0.96 and 1.18%, respectively. We concluded that the combination of optical data (L8 or S2) with SAR data (S1) improves the broadleaved Hyrcanian AGB estimation. RÉSUMÉ Dans cette etude, la capacit e de Landsat-8 (L8), Sentinel-2 (S2), Sentinel-1 (S1) et leur combinaison ont et e etudi ees pour estimer la biomasse a erienne (AGB). Un peuplement pur de Fagus Orientalis situ e dans la forêt hyrcanienne d'Iran a et e choisi comme zone d' etude. Le rendement d'une approche param etrique, c'est-a-dire, le mod ele de r egression lin eaire multiple (MLR) et les approches non param etriques, c'est-a-dire, k-Nearest Neighbor (k-NN), Random Forest (RF) et Support Vector Regression (SVR), ont et e evalu es pour les estimations de la biomasse. Nos r esultats indiquent que parmi les mesures S2, l'indice biophysique de la canop ee FAPAR et l'indice NDVI bas e sur la bande red-edge (NIR-b8a) ont les coefficients de corr elation les plus elev es (r) soit 0,420 et 0,417 respectivement. Les r esultats de l'estimation de l'AGB montrent qu'une combinaison des donn ees S2 et S1 utilisant l'algorithme k-NN donne la meilleure pr ecision (R2 de 0,57 et rRMSE de 14,68%). Le meilleur rRMSE en utilisant les ensembles de donn ees L8, S2 et S1 etait de 18,95%, 16,99% et 19,17% en utilisant respectivement les algorithmes k-NN, k-NN et MLR. La combinaison des ensembles de donn ees L8 et S1 a egalement am elior e le rRMSE de 0,96% et 1,18% par rapport aux donn ees L8 et S1 s epar ement. En conclusion, la combinaison des donn ees optiques (L8 ou S2) avec les donn ees SAR (S1) am eliore l'estimation de l'AGB de la forêt de feuillus hyrcanienne.

Research paper thumbnail of SodSAR: A Tower-Based 1–10 GHz SAR System for Snow, Soil and Vegetation Studies

Sensors, 2020

We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic A... more We introduce SodSAR, a fully polarimetric tower-based wide frequency (1–10 GHz) range Synthetic Aperture Radar (SAR) aimed at snow, soil and vegetation studies. The instrument is located in the Arctic Space Centre of the Finnish Meteorological Institute in Sodankylä, Finland. The system is based on a Vector Network Analyzer (VNA)-operated scatterometer mounted on a rail allowing the formation of SAR images, including interferometric pairs separated by a temporal baseline. We present the description of the radar, the applied SAR focusing technique, the radar calibration and measurement stability analysis. Measured stability of the backscattering intensity over a three-month period was observed to be better than 0.5 dB, when measuring a target with a known radar cross section. Deviations of the estimated target range were in the order of a few cm over the same period, indicating also good stability of the measured phase. Interforometric SAR (InSAR) capabilities are also discussed, and...

Research paper thumbnail of Long Term Interferometric Temporal Coherence and DInSAR Phase in Northern Peatlands

Remote Sensing, 2020

Peatlands of northern temperate and cold climates are significant pools of stored carbon. Underst... more Peatlands of northern temperate and cold climates are significant pools of stored carbon. Understanding seasonal dynamics of peatland surface height and volume, often referred to as mire breathing or oscillation, is the key to improve spatial models of material flow and gas exchange. The monitoring of this type of dynamics over large areas is only feasible by remote sensing instruments. The objective of this study is to examine the applicability of Sentinel-1 synthetic aperture radar interferometry (InSAR) to characterize seasonal dynamics of peatland surface height and water table (WT) over open raised bog areas in Endla mire complex in central Estonia, characteristic for northern temperate bogs. Our results show that InSAR temporal coherence, sufficient for differential InSAR (DInSAR), is preserved in the open bog over more than six months of temporal baseline. Moreover, the coherence which is lost in a dry summer, make a recovery in autumn correlate with WT dynamics. The relation...

Research paper thumbnail of Sentinel-1 InSAR Coherence for Land Cover Mapping: A Comparison of Multiple Feature-Based Classifiers

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020

This article investigates and demonstrates the suitability of the Sentinel-1 interferometric cohe... more This article investigates and demonstrates the suitability of the Sentinel-1 interferometric coherence for land cover and vegetation mapping. In addition, this study analyzes the Manuscript

Research paper thumbnail of Cropland Classification Using Sentinel-1 Time Series: Methodological Performance and Prediction Uncertainty Assessment

Remote Sensing, 2019

Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the dis... more Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Mult...

Research paper thumbnail of Is Accurate Synoptic Altimetry Achievable by Means of Interferometric GNSS-R?

Remote Sensing, 2019

This paper evaluates the capability of interferometric global navigation satellite system reflect... more This paper evaluates the capability of interferometric global navigation satellite system reflectometry (GNSS-R) to perform sea surface altimetry in a synoptic scenario. Such purpose, which requires the combination of the results from different GNSS signals, constitutes a unique characteristic of this approach. Interferometric GNSS-R group delay altimetry has been proven to be more precise than conventional GNSS-R. However, the self-consistency and accuracy of their synoptic solutions (simultaneous multi-static results) have never been proved before. In our work, we analyze a dataset of GNSS signals reflected off the Baltic Sea acquired during an airborne campaign using a receiver that was developed for such a purpose. Among other features, it enables beamformer capability in post-processing to get multiple and simultaneous GNSS signals under the interferometric approach’s restrictions. In particular, the signals from two GPS and two Galileo satellites, at two frequency bands (L1 an...

Research paper thumbnail of Boreal Forest Snow Damage Mapping Using Multi-Temporal Sentinel-1 Data

Remote Sensing, 2019

Natural disturbances significantly influence forest ecosystem services and biodiversity. Accurate... more Natural disturbances significantly influence forest ecosystem services and biodiversity. Accurate delineation and early detection of areas affected by disturbances are critical for estimating extent of damage, assessing economical influence and guiding forest management activities. In this study we focus on snow load damage detection from C-Band SAR images. Snow damage is one of the least studied forest damages, which is getting more common due to current climate trends. The study site was located in the southern part of Northern Finland and the SAR data were represented by the time series of C-band SAR scenes acquired by the Sentinel-1 sensor. Methods used in the study included improved k nearest neighbour method, logistic regression analysis and support vector machine classification. Snow damage recordings from a large snow damage event that took place in Finland during late 2018 were used as reference data. Our results showed an overall detection accuracy of 90%, indicating poten...

Research paper thumbnail of Polarimetric ALOS PALSAR Time Series in Mapping Biomass of Boreal Forests

Remote Sensing, 2017

Here, we examined multitemporal behavior of fully polarimetric SAR (PolSAR) parameters at L-band ... more Here, we examined multitemporal behavior of fully polarimetric SAR (PolSAR) parameters at L-band in relation to the stem volume of boreal forests. The PolSAR parameters were evaluated in terms of their temporal consistency, interdependence and suitability for forest stem volume estimation across several seasonal conditions (frozen, thaw and unfrozen). The satellite SAR data were represented by a time series of PolSAR images acquired during several seasons in the years 2006 to 2009 by the ALOS PALSAR sensor. The study area was in central Finland, and represented a managed area in typical boreal mixed forest land. Utility of different PolSAR parameters, their temporal stability and cross-correlations were studied along with reference stand-level stem volume data from forest inventory. Further, two polarimetric parameters, cross-polarization backscatter and co-polarization coherence, were chosen for further investigation and stem volume retrieval. A relationship between forest stem volume and PolSAR parameters was established using the kNN regression approach. Ways of optimally combining PolSAR images were evaluated as well. For a single scene, best results were observed with polarimetric coherence (RMSE ≈ 38.8 m 3 /ha) for scene acquired in frozen conditions. An RMSE of 40.8 m 3 /ha (42.9%, R 2 = 0.66) was achieved for cross-polarization backscatter in the best case. Cross-polarization backscatter was a better predictor than polarimetric coherence for few summer scenes. Multitemporal aggregation of selected PolSAR scenes improved estimates for both studied PolSAR parameters. Stronger improvement was observed for coherence with RMSE down to 34 m 3 /ha (35.8%, R 2 = 0.77) compared to 38.8-51.6 m 3 /ha (40.8-54.3%) from separate scenes. Finally, the accuracy statistics reached RMSE of 32.2 m 3 /ha (34%, R 2 = 0.79) when multitemporal HHVV coherence was combined with multitemporal HV-backscatter.

Research paper thumbnail of A Study of Landfast Ice with Sentinel-1 Repeat-Pass Interferometry over the Baltic Sea

Remote Sensing, 2017

Mapping of fast ice displacement and investigating sea ice rheological behavior is a major open t... more Mapping of fast ice displacement and investigating sea ice rheological behavior is a major open topic in coastal ice engineering and sea ice modeling. This study presents first results on Sentinel-1 repeat-pass space borne synthetic aperture radar interferometry (InSAR) in the Gulf of Bothnia over the fast ice areas. An InSAR pair acquired in February 2015 with a temporal baseline of 12 days has been studied here in detail. According to our results, the surface of landfast ice in the study area was stable enough to preserve coherence over the 12-day baseline, while previous InSAR studies over the fast ice used much shorter temporal baselines. The advantage of longer temporal baseline is in separating the fast ice from drift ice and detecting long term trends in deformation maps. The interferogram showed displacement of fast ice on the order of 40 cm in the study area. Parts of the displacements were attributed to forces caused by sea level tilt, currents, and thermal expansion, but the main factor of the displacement seemed to be due to compression of the drift ice driven by southwest winds with high speed. Further interferometric phase and the coherence measurements over the fast ice are needed in the future for understanding sea ice mechanism and establishing sustainability of the presented InSAR approach for monitoring dynamics of the landfast ice with Sentinel-1 data.

Research paper thumbnail of Seasonal effects on the estimation of height of boreal and deciduous forests from interferometric TanDEM-X coherence data

Earth Resources and Environmental Remote Sensing/GIS Applications VI, 2015

The aim of this study is to assess the performance of single-pass X-band bistatic SAR interferome... more The aim of this study is to assess the performance of single-pass X-band bistatic SAR interferometric forest height estimation of boreal and temperate deciduous forests under variable seasonal conditions. For this, twelve acquisitions of single-and dual-polarized TanDEM-X coherence images over 118 forest stands were analyzed and compared against LiDAR forest height maps. Strong correlations were found between interferometric coherence magnitude and LiDAR derived forest stand height for pine forests (r 2 =0.94) and spruce forest (r 2 =0.87) as well as for deciduous trees (r 2 =0.94) during leaf-off conditions with temperatures below 0°C. It was found that coherence magnitude based forest height estimation is influenced by leaf-on and leaf-off conditions as well as daily temperature fluctuations, height of ambiguity and effective baseline. These factors alter the correlation and should be taken into account for accurate coherence-based height retrieval. Despite the influence of the mentioned factors, generally a strong relationship in regression analysis between X-band SAR coherence and LiDAR derived forest stand height can be found. Moreover, a simple semi empirical model, derived from Random Volume over Ground model, is presented. The model takes into account all imaging geometry dependent parameters and allows to derive tree height estimate without a priori knowledge. Our results show that X-band SAR interferometry can be used to estimate forest canopy height for boreal and deciduous forests in both summer and winter, but the conditions should be stable.