Xianfeng Jiao

The Contribution of ALOS PALSAR Multipolarization and Polarimetric Data to Crop Classification

Mapping and monitoring changes in the distribution of cropland provide information that aids sustainable approaches to agriculture and supports early warning of threats to global and regional food security. This paper tested the capability of Phased Array type L-band Synthetic Aperture Radar (SAR) (PALSAR) multipolarization and polarimetric data for crop classification. L-band results were compared with those achieved with a C-band SAR data set (ASAR and RADARSAT-1), an integrated C- and L-band data set, and a multitemporal optical data set. Using all L-band linear polarizations, corn, soybeans, cereals, and hay-pasture were classified to an overall accuracy of 70%. A more temporally rich C-band data set provided an accuracy of 80%. Larger biomass crops were well classified using the PALSAR data. C-band data were needed to accurately classify low biomass crops. With a multifrequency data set, an overall accuracy of 88.7% was reached, and many individual crops were classified to accuracies better than 90%. These results were competitive with the overall accuracy achieved using three Landsat images (88.0%). L-band parameters derived from three decomposition approaches (Cloude-Pottier, Freeman-Durden, and Krogager) produced superior crop classification accuracies relative to those achieved using the linear polarizations. Using the Krogager decomposition parameters from all three PALSAR acquisitions, an overall accuracy of 77.2% was achieved. The results reported in this paper emphasize the value of polarimetric, as well as multifrequency SAR, data for crop classification. With such a diverse capability, a SAR-only approach to crop classification becomes increasingly viable.

The sensitivity of RADARSAT-2 polarimetric SAR data to corn and soybean leaf area index

In this study, quadrature-polarization (quad-pol) RADARSAT-2 data at steep (25o) and shallow (40o) incidence angles were acquired during the 2008 season, imaging 13 corn and soybean fields. The leaf area index (LAI) was derived from optical imagery, and volumetric soil moisture was measured coincident with each overpass. Many synthetic aperture radar (SAR) parameters were significantly correlated with derived corn and soybean LAI. The highest correlations were observed for parameters sensitive to volume scattering (HV, LL, and RR backscatter, pedestal height, and the Freeman–Durden volume-scattering parameter) at the steeper angle. For corn, the minimum correlation coefficient was 0.95. For soybeans, the coefficients were between 0.83 and 0.86. Sensitivity to LAI was lost late in the season, when the derived LAI exceeded 3.0 m2m−2. The derived LAI and the measured soil moisture were used to model several radar parameters (HV backscatter, pedestal height, and the Freeman–Durden volume-scattering parameter) using the water-cloud model. Early in the season, the SAR response was primarily affected by the vegetation, but soil moisture was also an important contributor. When the derived LAI exceeded 1, soil-moisture contributions became minimal. The water-cloud model adequately simulated SAR responses as the canopy developed and LAI increased, demonstrating the potential of polarimetric SAR data for monitoring indicators of crop productivity.

Towards operational radar-only crop type classification: comparison of a traditional decision tree with a random forest classifier

The potential of a random forest (RF) classifier for radar-only crop classifications was evaluated for an eastern and western Canadian site. Overall classification accuracies were improved by approximately 4%–5% over traditional boosted decision trees with gains of up to 7% in the accuracies of specific classes. Accuracies above 85% were obtained for key crops including canola, soybeans, corn, and wheat. Variable importance measures generated by the RF classifier showed that the most important acquisitions occurred in late August to early September at peak biomass and after wheat harvest. The least important images were acquired in May and mid-July. The HV and VV polarizations had the most significant contributions, while the HH polarization contributed little throughout the season, except in late September when the HH response was largely driven by soil conditions. The sensitivity of three RF parameters (number of training pixels, number of trees, and number of variables to select from at each split) was evaluated and shown to have negligible influence on overall accuracy. The RF classifier provided large performance gains in terms of processing time relative to the decision tree classifier. The operational potential and implementation considerations for radar-only Canada-wide crop type mapping are discussed in the context of these results.

TerraSAR-X and RADARSAT-2 for crop classification and acreage estimation

This research outlines a preliminary assessment of the use of TerraSAR-X data for classifying agricultural crop land in Canada. X-Band data were able to identify crops (pasture-forage, soybeans, corn and wheat) to accuracies of 95% once a post-classification filter was applied. These accuracies were achieved using six TerraSAR-X images from 2008 and a decision-tree classification algorithm. Acquisitions began only mid-season and consequently a second full season TerraSAR-X data set is being collected in 2009. C-Band classification accuracies were about 10% lower in comparison. These results clearly demonstrate the potential of X-Band data for crop identification.

Multi-Temporal Polarimetric RADARSAT-2 for Land Cover Monitoring in Northeastern Ontario, Canada

For successful applications of microwave remote sensing endeavors it is essential to understand how surface targets respond to changing synthetic aperture radar (SAR) parameters. The purpose of the study is to examine how two particular parameters, acquisition time and incidence angle, influences the response from various land use/land cover types (forests, urban infrastructure, surface water and marsh wetland targets) using nine RADARSAT-2 C-band fine-beam (FQ7 and FQ21) fully polarimetric SAR data acquired during the 2011 growing season over northern Ontario, Canada. The results indicate that backscatter from steep incidence angle acquisitions was typically higher than shallow angles. Wetlands showed an increase in HH and HV intensity due to the growth of emergent vegetation over the course of the summer. The forest and urban targets displayed little variation in backscatter over time. The surface water target showed the greatest difference with respect to incidence angle, but was also determined to be the most affected by wind conditions. Analysis of the co-polarized phase difference revealed the urban target as greatly influenced by the incidence angle. The observed phase differences of the wetland target for all acquisitions also suggested evidence of double-bounce interactions, while the forest and surface water targets showed little to no phase difference. In addition, Cloude-Pottier and Freeman-Durden decompositions, when analyzed in conjunction with polarimetric response plots, provided supporting information to confidently identify the various targets and their scattering mechanisms.

Agricultural Monitoring in Northeastern Ontario, Canada, Using Multi-Temporal Polarimetric RADARSAT-2 Data

Abstract: The purpose of this research is to analyze how changes in acquisition time and incidence angle affect various C-band synthetic aperture radar (SAR) polarimetric intensities, co-polarized phase information, polarimetric response plots and decomposition parameters for various crops typical of Northern Ontario, Canada. We examine how these parameters may be used to monitor the growth stages of five common cash crops, namely, barley ( Hordeum vulgare ), canola ( Brassica napus ), oat ( Avena sativa ), soybean ( Glycine max ) and wheat ( Triticum spp. ). In total, nine RADARSAT-2 polarimetric images were analyzed across a 14-week period beginning in June and ending in September 2011 using two incidence angles of approximately 26° and 41°. As expected, the backscatter intensities for all targets were found to show a higher response when acquired at the steeper incidence angle (26°). All cash crop targets showed a rise and fall in backscatter response over the course of the growing season, coinciding with changing growth stages. Slight phase differences were observed for cereal crops, possibly due to one of the polarizations penetrating between the rows allowing double-bounce to occur. The polarimetric response plots and decompositions offered insight into the scattering mechanisms of each crop type, generally showing an increase in volume scattering as the crops reached maturity. Specifically, the contributions of the crops increased towards the volume scattering component and zones 4 and 2, as the crops matured in regards to the Freeman-Durden and Cloude-Pottier decompositions respectively. Overall, soybean and canola showed a more similar response in comparison to the cereal cash crops. Although

Contribution of Multi-Frequency, Multi-Sensor, and Multi-Temporal Radar Data to Operational Annual Crop Mapping

Information on agricultural land use (crop inventory) is needed by various organizations on an annual basis. To meet this operational requirement, Agriculture and Agri-Food Canada (AAFC) has carried out a multi-year (2004 - 2007), multi-sensor (Landsat TM, SPOT, RADARSAT-1, ASAR), and multi-site (five provinces: Ontario, Saskatchewan, Alberta, Manitoba, P.E.I.) research activity to develop a robust methodology to inventory crops across Canadas large and diverse agricultural landscapes. Results clearly demonstrated that multi-temporal satellite data can successfully classify crops for a variety of cropping systems across Canada. Overall accuracies of at least 85% were achieved. When available, multi-temporal (2 to 3 scenes acquired at different growth stages) optical data are ideal for crop classification. However due to cloud and haze interference, good optical data are not always obtainable. A SAR-optical combination offers a good alternative. This research has found that when only one optical image is available, the addition of two ASAR images acquired in VV/VH polarization will provide acceptable accuracies. Of particular interest is the observation that with the incorporation of radar, crop inventories can be delivered earlier in the growing season.

Assessing relationships between Radarsat-2 C-band and structural parameters of a degraded mangrove forest

Relationships were assessed between mangrove structural data (leaf area index (LAI), stem density, basal area, diameter at breast height (DBH)) collected from 61 stands located in a black mangrove (Avicennia germinans)-dominated forest and both single polarized ultra-fine (3 m) and multipolarized fine beam (8 m) Radarsat-2 C-band synthetic aperture radar (SAR) data. The stands examined included representatives from the four types of mangroves that typify this degraded system, specifically: predominantly dead mangrove, poor-condition mangrove, healthy dwarf mangrove, and tall healthy mangrove. The results indicate that the selection of the spatial resolution (3 m vs. 8 m) of the incidence angle (27–39°) and the polarimetric mode greatly influence the relationship between the SAR and mangrove structural data. Moreover, the extent of degradation, i.e. whether dead stands are considered, also determines the strength of the relationships between the various SAR and mangrove parameters. When dead stands are included, the strongest overall relationships between the ultra-fine backscatter (incidence angle of ∼32°) and the various structural parameters were found using the horizontal-horizontal (HH) polarization/horizontal-vertical (HV) polarization ratio. However, if the dead stands are not included, then significant relationships with the ultra-fine data were only calculated with the HH data. Similar results were observed using the corresponding incidence angle (∼33°) of the fine beam data. When a shallower incidence angle was considered (∼39°), fewer and weaker relationships were calculated. Moreover, no significant relationships were observed if the dead stands were excluded from the sample at this incidence angle. The highest correlation coefficients using the steepest incidence (∼27°) were found with the co-polarized (HH, vertical-vertical (VV) polarization) modes. Several polarimetric parameters (entropy, pedestal height, surface roughness, alpha angle) based on the decomposition of the scattering matrix of the fine beam mode at this incidence angle were also found to be significantly correlated to mangrove structural data. The highest correlation (R = 0.71) was recorded for entropy and LAI. When the dead stands were excluded, volume scattering was found to be the most significant polarimetric parameter. Finally, multiple regression models, based on texture measures derived from both the grey level co-occurrence matrix (GLCM) and the sum and difference histogram (SADH) of the ultra-fine data, were developed to estimate mangrove parameters. The results indicate that only models derived from the HH data are significant and that several of these were strong predictors of all but stem density.

In-season crop inventory using multi-angle and multi-pass RADARTSAT-2 SAR data over the Canadian prairies

In response to the increasing demand on in-season crop inventory, this study presents results of early season crop identification and acreage estimates based on a random forest classifier using RADARSAT-2 fine quad (FQ) SAR data. Thirty RADARSAT-2 FQ SAR scenes acquired over Indian Head, Canada, during the 2009 AgriSAR campaign led by the European Space Agency (ESA) were analyzed. Consistent with results from other researches, this study revealed that the highest classification accuracies are achieved in mid to late season (early July to mid August) when most of the crops experiencing vegetative growth and early reproduction. In addition by incorporating multi-beam images, an increase in classification accuracy of 2% to 12% can be achieved. For images acquired close in time, shallower incidence angles usually give better classification accuracy compared with steeper incidence angles. In order to achieve optimal classification performance, both multi-temporal and multi-beam acquisitions should be combined. For major crops such as canola, spring wheat, lentil, and field peas, over 85% accuracies can be reached early in the growing season (early July) when multi-temporal multi-beam RADARSAT-2 FQ data are used.

Rice identification and change detection using TerraSAR-X data

Rice is the staple grain in China and accounts for about 42% of the nations food production. Most of Chinas paddy rice production is located in the southern provinces of the country where cloud cover and frequent rain severely limit opportunities for optical satellite acquisitions. The small field sizes, typical of paddy rice, also challenge the exploitation of satellite data for monitoring rice production. Synthetic aperture radar (SAR) sensors are able to successfully acquire data under most atmospheric conditions, and the change in backscatter, from rice emergence through to crop maturity and harvest, permits the detection of rice fields using SAR imagery. Recently launched sensors, including TerraSAR-X, can provide data at spatial resolutions suitable for rice monitoring in southern China. The objective of this study was to assess TerraSAR-X imagery for identification of late rice and to develop a change detection methodology to quantify changes in rice acreages. The lowlands of the Xuwen study site in Guangdong Province are dominated by rice paddies. Results of this analysis revealed that the TerraSAR-X data were able to identify rice paddies with a 96% accuracy and acreage change to an accuracy of 99%.