Canadian Prairie Rangeland and Seeded Forage Classification Using Multiseason Landsat 8 and Summer RADARSAT-2

Lindsay, Emily; King, Douglas J.; Davidson, Andrew; Daneshfar, Bahram

doi:10.1016/j.rama.2018.07.005

Cited by 11 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These results are consistent with the rationale that: (1) low biomass crops (soybean) could be more readily misclassified as non-crop when using L-band, leading to relatively poorer accuracy; and (2) high biomass crops (corn) could be more readily classified as a non-crop due to the signal saturating over time resulting in smaller CV. This section compares CV values Rangelands type land cover classes, such as grassland and pastures, are difficult to separate from other land covers [18,[42][43][44][45]. This is also reflected in our results, Figures 7 and 8 show that classifications of grassland and pasture at L-band are a toss-up; overall accuracy would not appreciably change whether we considered it a crop or non-crop a priori (CV values are close to CV thr , Figure 7), whereas in the C-band, those land covers classify much more clearly as non-crop (CV values are clearly lower than CV thr , Figure 7).…”

Section: Comparison Of Coefficient Of Variation To In Situ Biomass Datamentioning

confidence: 99%

Comparison between Dense L-Band and C-Band Synthetic Aperture Radar (SAR) Time Series for Crop Area Mapping over a NISAR Calibration-Validation Site

et al. 2021

View full text Add to dashboard Cite

Crop area mapping is important for tracking agricultural production and supporting food security. Spaceborne approaches using synthetic aperture radar (SAR) now allow for mapping crop area at moderate spatial and temporal resolutions. Multi-frequency SAR data is highly useful for crop monitoring because backscatter response from vegetation canopies is wavelength dependent. This study evaluates the utility of C-band Sentinel-1B (Sentinel-1) and L-band ALOS-2 (PALSAR) data, collected during the 2019 growing season, for generating accurate active crop extent (crop vs. non-crop) classifications over an agricultural region in western Canada. Evaluations were performed against the Agriculture and Agri-Food Canada satellite-based Annual Cropland Inventory (ACI), an open data product that maps land cover across the extent of Canada’s agricultural land. Classifications were performed using the temporal coefficient of variation (CV) approach, where an optimal crop/non-crop delineating CV threshold (CVthr) is selected according to Youden’s J-statistic. Results show that crop area mapping agreed better with the ACI when using Sentinel-1 data (83.5%) compared to PALSAR (73.2%). Analysis of performance by crop reveals that PALSAR’s poorer performance can be attributed to soybean, urban, grassland, and pasture ACI classes. This study also compared CV values to in situ wet biomass data for canola and soybeans, showing that crops with lower biomass (soybean) had correspondingly lower CV values.

show abstract

Section: Comparison Of Coefficient Of Variation To In Situ Biomass Datamentioning

confidence: 99%

Comparison between Dense L-Band and C-Band Synthetic Aperture Radar (SAR) Time Series for Crop Area Mapping over a NISAR Calibration-Validation Site

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The pasture class consisted of areas cleared for grazing, previously used for some form of agriculture production or currently cultivated non-native grasses used for feed or seed production. An important distinction between cropland and cultivated pasture was based on previous findings that these pastures were distinguishable from grasslands and croplands related to earlier spring greenup [37]. However, this has not been widely examined across the prairie region.…”

Section: Change In Cropping Practicesmentioning

confidence: 99%

“…Detection of grassland types as native and non-native is an important need in the prairie region regarding biodiversity and wildlife habitat [2]. Previous research has shown some potential to separate these grasslands and seeded forage pastures to varying degrees using seasonal data [35][36][37] or detecting evidence of plowing with lidar data in [38]. Results show that research is progressing, but data is currently insufficient for assessment across the entire prairie extent.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018

et al. 2021

Self Cite

View full text Add to dashboard Cite

The prairie region of Canada is a dynamically changing landscape in relation to past and present anthropogenic activities and recent climate change. Improving our understanding of the rate, timing, and distribution of landscape change is needed to determine the impact on wildlife populations and biodiversity, ultimately leading to better-informed management regarding requirements for habitat amount and its connectedness. In this research, we assessed the viability of an approach to detect from–to class changes designed to be scalable to the prairie region with the capacity for local refinement. It employed a deep-learning convolution neural network to model general land covers and examined class memberships to identify land-cover conversions. For this implementation, eight land-cover categories were derived from the Agriculture and Agri-Food Canada Annual Space-Based Crop Inventory. Change was assessed in three study areas that contained different mixes of grassland, pasture, and forest cover. Results showed that the deep-learning method produced the highest accuracy across all classes relative to an implementation of random forest that included some first-order texture measures. Overall accuracy was 4% greater with the deep-learning classifier and class accuracies were more balanced. Evaluation of change accuracy suggested good performance for many conversions such as grassland to crop, forest to crop, water to dryland covers, and most bare/developed-related changes. Changes involving pasture with grassland or cropland were more difficult to detect due to spectral confusion among classes. Similarly, conversion to forests in some cases was poorly detected due to gradual and subtle change characteristics combined with confusion between forest, shrub, and croplands. The proposed framework involved several processing steps that can be explored to enhance the thematic content and accuracy for large regional implementation. Evaluation for understanding connectivity in natural land covers and related declines in species at risk is planned for future research.

show abstract

“…Hoy en día, una gran cantidad de productos derivados de satélites se encuentran en el dominio público o pronto a ser liberados, lo cual los convierte en recursos valiosos y accesibles para ser utilizados por investigadores y tomadores de decisión (Simons et al, 2016). Entre ellos se destacan los productos Landsat, que han sido y continúan siendo de gran aplicación en diferentes análisis temporales de cambios en las coberturas y usos del suelo (Alam et al, 2020;Chen et al, 2021;Jaramillo & Antunes, 2018;Lara & Gandini, 2014;Lindsay et al, 2019;Pflugmacher et al, 2019;Sequeira et al, 2016;Somoza et al, 2021b;Vazquez et al, 2019).…”

Section: Introductionunclassified

Análisis espectral temporal por sistemas ecológicos de la Cuenca Superior del Arroyo Langueyú, Tandil, Región Pampeana Argentina

et al. 2022

View full text Add to dashboard Cite

La transformación de ecosistemas naturales a tierras agropecuarias genera importantes consecuencias ambientales, siendo la Región Pampeana Argentina un claro ejemplo de ello. Esta investigación analizó las transformaciones en los usos y coberturas del suelo observadas en los sistemas ecológicos de la Cuenca Superior del Arroyo Langueyú (Tandil) en los períodos comprendidos por los años 1989-2004 y 2004-2019; y se profundizó en el análisis de los cambios de clase de los usos pastizales y pasturas y agrícolas. Para ello, se seleccionaron y procesaron imágenes satelitales, para generar clasificaciones supervisadas, y se detectaron cambios a través de técnicas de teledetección y sistemas de información geográfica. Las mayores transformaciones en los distintos sistemas se vincularon al aumento continuo del uso agrícola sobre tierras que anteriormente eran pastizales y pasturas, que ahora se ven disminuidas. Finalmente, la metodología aplicada permitió vislumbrar las variaciones más relevantes, obteniendo información de importancia al momento de establecer estrategias para la planificación sustentable de la cuenca.

show abstract

Canadian Prairie Rangeland and Seeded Forage Classification Using Multiseason Landsat 8 and Summer RADARSAT-2

Cited by 11 publications

References 52 publications

Comparison between Dense L-Band and C-Band Synthetic Aperture Radar (SAR) Time Series for Crop Area Mapping over a NISAR Calibration-Validation Site

Comparison between Dense L-Band and C-Band Synthetic Aperture Radar (SAR) Time Series for Crop Area Mapping over a NISAR Calibration-Validation Site

Assessment of Landsat Based Deep-Learning Membership Analysis for Development of from–to Change Time Series in the Prairie Region of Canada from 1984 to 2018

Análisis espectral temporal por sistemas ecológicos de la Cuenca Superior del Arroyo Langueyú, Tandil, Región Pampeana Argentina

Contact Info

Product

Resources

About