Performance Evaluation of UAVSAR and Simulated NISAR Data for Crop/Non- crop Classification over Stoneville, MS

Title: Performance Evaluation of UAVSAR and Simulated NISAR Data for Crop/Non- crop Classification over Stoneville, MS

Authors: Kraatz, Simon., Rose, Shannon., Cosh, Michael., Torbick, Nathan., Huang, Xiaodong., and Siqueira, Paul.

Journal: AGU Earth and Space Science

Publication Date: 08 December 2020

DOI: https://doi.org/10.1029/2020EA001363

Citation:  Kraatz, Simon., Rose, Shannon., Cosh, Michael., Torbick, Nathan., Huang, Xiaodong., and Siqueira, Paul. (2021). Performance Evaluation of UAVSAR and Simulated NISAR Data for Crop/Non- crop Classification over Stoneville, MS. AGU Earth and Space Science. https://doi.org/10.1029/2020EA001363

Abstract: 

Synthetic Aperture Radar (SAR) data are well-suited for change detection over agricultural fields, owing to high spatiotemporal resolution and sensitivity to soil and vegetation. The goal of this work is to evaluate the science algorithm for the NASA ISRO SAR (NISAR) Cropland Area product using data collected by NASA's airborne Uninhabited Aerial Vehicle SAR (UAVSAR) platform and the simulated NISAR data derived from it. This study uses mode 129, which is to be used for global-scale mapping. The mode consists of an upper (129A) and lower band (129B), respectively having bandwidths of 20 and 5 MHz. This work uses 129A data because it has a four times finer range resolution compared to 129B. The NISAR algorithm uses the coefficient of variation (CV) to perform crop/noncrop classification at 100 m. We evaluate classifications using three accuracy metrics (overall accuracy, J-statistic, Cohen's Kappa) and spatial resolutions (10, 30, and 100 m) for crop/noncrop delineating CV thresholds (CVthr) ranging from 0 to 1 in 0.01 increments. All but the 10 m 129A product exceeded NISAR's mission accuracy requirement of 80%. The UAVSAR 10 m data performed best, achieving maximum overall accuracy, J-statistic, and Kappa values of 85%, 0.62, and 0.60. The same metrics for the 129A product respectively are: 77%, 0.40, 0.36 at 10 m; 81%, 0.55, 0.49 at 30 m; 80%, 0.58, 0.50 at 100 m. We found that using a literature recommended CVthr value of 0.5 yielded suboptimal accuracy (65%) at this site and that optimal CVthr values monotonically decreased with decreasing spatial resolution.

Evaluating NISAR's cropland mapping algorithm over the conterminous United States using Sentinel-1 data

Title: Evaluating NISAR's cropland mapping algorithm over the conterminous United States using Sentinel-1 data

Authors: Rose, Shannon., Kraatz, Simon., Kellndorfer, Josef., Cosh, Michael., Torbick, Nathan., Huang, Xiaodong., and Siqueira, Paul

Journal: Remote Sensing of Environment

Publication Date: 27 April 2021

DOI: https://doi.org/10.1016/j.rse.2021.112472

Citation: Rose, Shannon., Kraatz, Simon., Kellndorfer, Josef., Cosh, Michael., Torbick, Nathan., Huang, Xiaodong., and Siqueira, Paul. (2021). Evaluating NISAR's cropland mapping algorithm over the conterminous United States using Sentinel-1 data. Remote Sensing of Environment. https://doi.org/10.1016/j.rse.2021.112472

Abstract: 

Accurate knowledge of the distribution, breadth and change in agricultural activity is important to food security and the related trade and policy mechanisms. Routine observations afforded by spaceborne Synthetic Aperture Radar (SAR) allows for high-fidelity monitoring of agricultural parameters at the field scale. Here we evaluate the approach to be used for generating NASA's upcoming NASA ISRO SAR (NISAR) mission's L-band cropland product using Sentinel-1C-band data. This study uses all ascending Sentinel-1A/B data collected over the conterminous United States in 2017 to compute the coefficient of variation (CV) at 150 m × 150 m resolution and evaluates the overall accuracy (OA) of CV-based crop/non-crop classifications at 100 one-by-one degree tiles. We calculate accuracies using two approaches: (a) using a literature-recommended constant CV threshold of 0.5 (CVthr_0.5) and (b) determining optimal CV thresholds for every tile using Youden's J statistic (YJS), CVthr_YJS. These accuracy comparisons are important for determining (1) the viability of using a computationally inexpensive and straightforward approach for cropland classification over large spatial scales/diverse land covers (i.e., can accuracies ≥80% be routinely achieved?), (2) how closely OA0.5 compares to the performance ceiling (OAYJS). This information will help determine whether approach (a) is appropriate and how much potential room of improvement there could be in modifying it. Results for OA0.5 and OAYJS are 81.5% and 86.8%, respectively. A breakdown by census geographic region, showed that OA0.5 (OAYJS) exceeded 80% (90%) in the South and Midwest, but was only 76.1% (73.5%) in the West. The improvement in OAYJS mainly stems from tiles with >40% crop prevalence having about 10% greater OA values. To better examine the potential of the approach for land cover classification, results of approach (b) were also stratified by crop. Approach (b) accurately detected most non-crop classes as non-crop (>80%), but with low OAYJS values for grasslands/pasture, especially in the West. CV values for crop were distinct from non-crop indicating that the approach is suitable for crop/non-crop classifications. Because results CV values have substantial overlap within crop/non-crop classes, indicating the approach is poorly suited for land cover classifications. We also detected a strong geographic dependence of CVthr_YJS: values ranged from about 0.2 at the coasts and gradually increase to about 0.6 in the Central United States, most often falling close to 0.3 and 0.5.

ISCE Docker Tools: Automated Radiometric Terrain Correction and Image Coregistration of UAVSAR MLC Data

Title: ISCE Docker Tools: Automated Radiometric Terrain Correction and Image Coregistration of UAVSAR MLC Data

Authors: Kraatz, Simon., Siqueira, Paul., and Rose, Shannon. 

Journal: IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium

Publication Date: 17 February 2021

DOI: https://doi.org/10.1109/IGARSS39084.2020.9324658

Citation: Kraatz, Simon., Siqueira, Paul., and Rose, Shannon. (2021). ISCE Docker Tools: Automated Radiometric Terrain Correction and Image Coregistration of UAVSAR MLC Data. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS39084.2020.9324658

Abstract:

In Summer/Fall 2019, the UAVSAR platform was used to collect dense time series over several agricultural and biomass sites in the southeastern US. This data is to be used for developing ecosystem science algorithms for the upcoming NASA-ISRO SAR (NISAR) mission. Development and testing of these algorithms require routine SAR processing steps such as image co-registration and terrain correction. Because the NISAR mission will use the Interferometric Synthetic Aperture Radar (InSAR) Scientific Computing Environment (ISCE) for data processing from Level 0 through Level 2, we focused on developing a new ISCE workflow to facilitate UAVSAR Multi-Looked-Cross Products (MLC) data processing. The workflows are python scripts and can be readily modified according to user needs. They operate in conjunction with a Docker image of ISCE, which allows data processing on any system that supports Docker (https://www.docker.com/). A defining feature of this workflow is that it usually only requires minimal interaction by the user: the user only needs to provide the desired UAVSAR MLC data and run one docker command to initiate the data processing.

Projecting future land use/land cover by integrating drivers and plan prescriptions: the case for watershed applications

Title: Projecting future land use/land cover by integrating drivers and plan prescriptions: the case for watershed applications

Authors: Wilson, Cyril., Liang, Bingqing., and Rose, Shannon

Journal: GIScience & Remote Sensing

Publication Date: 16 Oct 2018

DOI: https://doi.org/10.1080/15481603.2018.1533158

Citation: Wilson, Cyril., Liang, Bingqing., and Rose, Shannon. (2018). Projecting future land use/land cover by integrating drivers and plan prescriptions: the case for watershed applications. GIScience & Remote Sensing. https://doi.org/10.1080/15481603.2018.1533158

Abstract: 

Watershed planning is a pivotal exercise for all jurisdictions irrespective of size, landscape complexity, or other nuances. As a result of the intricate relationship between land use/land cover (LULC) and water resources, it becomes prudent to not only develop historical and contemporary LULC data for watershed planning purposes, but more importantly, the production of future LULC datasets has the potential to better inform watershed planners. This study explored an optimal workflow that can be adopted for the production of baseline LULC input images from a moderate spatial resolution sensor such as Landsat, and the identification, translation, and configuration of land change drivers and regional comprehensive plan prescriptions in the creation of future LULC data for a regional watershed. The study conducted in the Lower Chippewa River Watershed, Wisconsin, USA demonstrated that an object-based hybrid classification approach resulted in the generation of improved projected images with a 15% increase in area under the curve (AUC) value compared to a pixel-based hybrid classification method even though both methods displayed comparable overall image classification accuracies (≤ 1.8%). Results further displayed that configuring anthropogenic drivers in a trend format rather than individual year values can result in a more efficient training of a multi-layer perceptron neural network – Markov Chain model. The calibrated and validated model demonstrated that on average, residential, commercial, institutional, green vegetation/shrub, and industrial LULC are expected to grow through 2050, though at a slower rate (12%) compared to contemporary period (39%), while forest and agricultural lands are slated to decline (−2%).