An assessment of image classifiers for generating machine-learning training samples for mapping the invasive Campuloclinium macrocephalum (Less.) DC (pompom weed) using DESIS hyperspectral imagery

Mafanya, Madodomzi; Tsele, Philemon; Zengeya, Tsungai A.; Ramoelo, Abel

doi:10.1016/j.isprsjprs.2022.01.015

Cited by 13 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To increase the purity of the training sample pool, the spectral angle mapper (SAM) 57 – 60 was used to eliminate noisy samples. The reflectance spectrum of noisy samples generated by CI differs from that of the reference rapeseed endmember, making them distinguishable using spectral similarity measures.…”

Section: Methodsmentioning

confidence: 99%

CARM30: China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 using multi-source data

Liu,

Li,

Tao

et al. 2024

Sci Data

View full text Add to dashboard Cite

Rapeseed is a critical cash crop globally, and understanding its distribution can assist in refined agricultural management, ensuring a sustainable vegetable oil supply, and informing government decisions. China is the leading consumer and third-largest producer of rapeseed. However, there is a lack of widely available, long-term, and large-scale remotely sensed maps on rapeseed cultivation in China. Here this study utilizes multi-source data such as satellite images, GLDAS environmental variables, land cover maps, and terrain data to create the China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 (CARM30). Our product was validated using independent samples and showed average F1 scores of 0.869 and 0.971 for winter and spring rapeseed. The CARM30 has high spatial consistency with existing 10 m and 20 m rapeseed maps. Additionally, the CARM30-derived rapeseed planted area was significantly correlated with agricultural statistics (R2 = 0.65–0.86; p < 0.001). The obtained rapeseed distribution information can serve as a reference for stakeholders such as farmers, scientific communities, and decision-makers.

show abstract

Section: Methodsmentioning

confidence: 99%

CARM30: China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 using multi-source data

Liu,

Li,

Tao

et al. 2024

Sci Data

View full text Add to dashboard Cite

show abstract

“…However, in preparation for the upcoming launch of EnMAP (Guanter et al, 2015), the DLR launched an exploratory system to the International Space Station and embedded into the Multi-User-System for Earth Sensing (MUSES) platform in 2018. The DLR Earth Sensing Imaging Spectrometer (DESIS) (Eckardt et al, 2015;Mafanya et al, 2022) provides a unique opportunity to test the potential for monitoring plant species diversity with spaceborne hyperspectral data. It delivers hyperspectral images with 235 spectral bands over the visible and near-infrared regions of 400 ∼ 1000 nm, with a spectral resolution of 2.55 nm and a spatial resolution of 30 m (Eckardt et al, 2015;Alonso et al, 2019;Krutz et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Plant species richness prediction from DESIS hyperspectral data: A comparison study on feature extraction procedures and regression models

Guo¹,

Mokany²,

Ong³

et al. 2023

Preprint

View full text Add to dashboard Cite

The diversity of terrestrial vascular plants plays a key role in maintaining the stability and productivity of ecosystems. Monitoring species compositional diversity across large spatial scales is challenging and time consuming. Airborne hyperspectral imaging has shown promise for measuring plant diversity remotely, but to operationalise these efforts over large regions we need to advance satellite-based alternatives. The advanced spectral and spatial specification of the recently launched DESIS (the DLR Earth Sensing Imaging Spectrometer) instrument provides a unique opportunity to test the potential for monitoring plant species diversity with spaceborne hyperspectral data. This study provides a quantitative assessment on the ability of DESIS hyperspectral data for predicting plant species richness in two different habitat types in southeast Australia. Spectral features were first extracted from the DESIS spectra, then regressed against on-ground estimates of plant species richness, with a two-fold cross validation scheme to assess the predictive performance. We tested and compared the effectiveness of Principal Component Analysis (PCA), Canonical Correlation Analysis (CCA), and Partial Least Squares analysis (PLS) for feature extraction, and Kernel Ridge Regression (KRR), Gaussian Process Regression (GPR), and Random Forest Regression (RFR) for species richness prediction. The best prediction results were r = 0.76 and RMSE = 5.89 for the Southern Tablelands region, and r = 0.68 and RMSE = 5.95 for the Snowy Mountains region. Relative importance analysis for the DESIS spectral bands showed

show abstract

Optimum supervised classification algorithm identification by investigating PlanetScope and Skysat multispectral satellite data of Covid lockdown

Shakya

Ramola

Singh

et al. 2023

Geosystems and Geoenvironment

View full text Add to dashboard Cite

An assessment of image classifiers for generating machine-learning training samples for mapping the invasive Campuloclinium macrocephalum (Less.) DC (pompom weed) using DESIS hyperspectral imagery

Cited by 13 publications

References 54 publications

CARM30: China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 using multi-source data

CARM30: China annual rapeseed maps at 30 m spatial resolution from 2000 to 2022 using multi-source data

Plant species richness prediction from DESIS hyperspectral data: A comparison study on feature extraction procedures and regression models

Optimum supervised classification algorithm identification by investigating PlanetScope and Skysat multispectral satellite data of Covid lockdown

Contact Info

Product

Resources

About