Automatic canola mapping using time series of sentinel 2 images

Ashourloo, Davoud; Shahrabi, Hamid Salehi; Azadbakht, Mohsen; Aghighi, Hossein; Nematollahi, Hamed; Alimohammadi, Abbas; Matkan, A A

doi:10.1016/j.isprsjprs.2019.08.007

Cited by 81 publications

(74 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have addressed broad area mapping of canola fields by using flowering to discriminate it from other crops, typically using either optical (Ashourloo, Shahrabi, Azadbakht, Aghighi, & Nematollahi, 2019) or radar (McNairn, Jiao, Pacheco, Sinha, & Tan, 2018) observation, or a combination of both (d'Andrimont et. al., 2020; Tian, Meng, Wu, & Niu, 2019).…”

Section: Introductionmentioning

confidence: 99%

Automated detection of phenological transitions for yellow flowering plants such as Brassica oilseeds

Sulik

Long²

2020

Agrosystems Geosci & Env

View full text Add to dashboard Cite

Monitoring crop phenology is crucial for making site‐specific management decisions for crop protection and nutrition. The prominent yellow bloom associated with canola (Brassica napus L.) and similar yellow‐flowering plants can provide cues about spatial differences as well as timing of crop input requirements. The objective of this study was to remotely characterize the phenological development of Brassicaceae oilseeds such as canola and carinata (B. carinata A. Braun) in terms of spectral‐temporal dynamics between vegetation density and yellow flower density. Temporal variation of spectral indices (normalized difference vegetation index [NDVI], normalized difference yellowness index [NDYI], and visible atmospherically resistant index [VARI]) were measured in small plots over the growing season in relation to changes in vegetation density and flower density in winter canola and spring carinata. Phenological change between vegetative and reproductive development could be automatically detected using the difference in the change of the sign of ΔIndex values between VARI and NDYI. An overall accuracy of 85% was obtained when testing the algorithm with Landsat 8 data of canola fields near Olds, AB, Canada. The contrasting behavior between reproductive and vegetation indices across flowering transitions was confirmed for three independent datasets across a range of genetic variation in Brassica oilseeds as well as geographic variation in soil types and management practices. A bivariate time series analysis procedure was developed for automatically estimating flowering transitions based on predictable, relative differences between vegetative and reproductive indices. Researchers and land managers can exploit optimal phenology windows to improve site‐specific models and disease risk assessments.

show abstract

Section: Introductionmentioning

confidence: 99%

Automated detection of phenological transitions for yellow flowering plants such as Brassica oilseeds

Sulik

Long²

2020

Agrosystems Geosci & Env

View full text Add to dashboard Cite

show abstract

“…Many approaches to generating land cover maps using remote sensing data have been investigated. Some seek to classify individual crops using analytical methods and characteristics specific to that crop, such as the canola (Brassica napus L.) mapping in [10], rice (Oryza sativa L.) in [11] and peanuts (Arachis hypogaea L.) in [12]. Recent work uses supervised classification methods such as support vector machines (SVM), random forests (RF) [13] and neural networks [14].…”

Section: Introductionmentioning

confidence: 99%

Land Cover Classification of Nine Perennial Crops Using Sentinel-1 and -2 Data

Brinkhoff

Vardanega²,

Robson

2019

Remote Sensing

View full text Add to dashboard Cite

Land cover mapping of intensive cropping areas facilitates an enhanced regional response to biosecurity threats and to natural disasters such as drought and flooding. Such maps also provide information for natural resource planning and analysis of the temporal and spatial trends in crop distribution and gross production. In this work, 10 meter resolution land cover maps were generated over a 6200 km2 area of the Riverina region in New South Wales (NSW), Australia, with a focus on locating the most important perennial crops in the region. The maps discriminated between 12 classes, including nine perennial crop classes. A satellite image time series (SITS) of freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral imagery was used. A segmentation technique grouped spectrally similar adjacent pixels together, to enable object-based image analysis (OBIA). K-means unsupervised clustering was used to filter training points and classify some map areas, which improved supervised classification of the remaining areas. The support vector machine (SVM) supervised classifier with radial basis function (RBF) kernel gave the best results among several algorithms trialled. The accuracies of maps generated using several combinations of the multispectral and radar bands were compared to assess the relative value of each combination. An object-based post classification refinement step was developed, enabling optimization of the tradeoff between producers’ accuracy and users’ accuracy. Accuracy was assessed against randomly sampled segments, and the final map achieved an overall count-based accuracy of 84.8% and area-weighted accuracy of 90.9%. Producers’ accuracies for the perennial crop classes ranged from 78 to 100%, and users’ accuracies ranged from 63 to 100%. This work develops methods to generate detailed and large-scale maps that accurately discriminate between many perennial crops and can be updated frequently.

show abstract

“…Unlike other crops, rapeseed has two distinct green-up phases: the flowering period and the pod period (Ashourloo et al, 2019;Bargiel, 2017;Mercier et al, 2020;Veloso et al, 2017). The petals of rapeseed decrease the scattering of VV and VH, while the pods increase the scattering intensity of VH (d'Andrimont et al, 2020;Bargiel, 2017;McNairn et al, 2009;Mercier et al, 2020). The NDYI and backscattering (VV and VH) time series of rapeseed in different climate regions (Fig.…”

Section: Optical and Sar Characteristics During The Rapeseed Growing Periodmentioning

confidence: 99%

The RapeseedMap10 database: annual maps of rapeseed at a spatial resolution of 10 m based on multi-source data

Han

Zhang

Luo

et al. 2021

Earth Syst. Sci. Data

View full text Add to dashboard Cite

Abstract. Large-scale, high-resolution maps of rapeseed (Brassica napus L.), a major oilseed crop, are critical for predicting annual production and ensuring global energy security, but such maps are still not freely available for many areas. In this study, we developed a new pixel- and phenology-based algorithm and produced a new data product for rapeseed planting areas (2017–2019) in 33 countries at 10 m spatial resolution based on multiple data. Our product is strongly consistent at the national level with official statistics of the Food and Agricultural Organization of the United Nations. Our rapeseed maps achieved F1 spatial consistency scores of at least 0.81 when compared with the Cropland Data Layer in the United States, the Annual Crop Inventory in Canada, the Crop Map of England, and the Land Cover Map of France. Moreover, F1 scores based on independent validation samples ranged from 0.84 to 0.91, implying a good consistency with ground truth. In almost all countries covered in this study, the rapeseed crop rotation interval was at least 2 years. Our derived maps suggest, with reasonable accuracy, the robustness of the algorithm in identifying rapeseed over large regions with various climates and landscapes. Scientists and local growers can use the freely downloadable derived rapeseed planting areas to help predict rapeseed production and optimize planting structures. The product is publicly available at https://doi.org/10.17632/ydf3m7pd4j.3 (Han et al., 2021).

show abstract

Automatic canola mapping using time series of sentinel 2 images

Cited by 81 publications

References 56 publications

Automated detection of phenological transitions for yellow flowering plants such as Brassica oilseeds

Automated detection of phenological transitions for yellow flowering plants such as Brassica oilseeds

Land Cover Classification of Nine Perennial Crops Using Sentinel-1 and -2 Data

The RapeseedMap10 database: annual maps of rapeseed at a spatial resolution of 10 m based on multi-source data

Contact Info

Product

Resources

About