Discriminating indicator grass species for rangeland degradation assessment using hyperspectral data resampled to AISA Eagle resolution

Mansour, Khalid; Mutanga, Onisimo; Everson, Terry; Adam, Elhadi

doi:10.1016/j.isprsjprs.2012.03.006

Cited by 76 publications

(44 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, Thrash and Derry (1999) noted that Cynodon dactylon has been observed to increase away from the piosphere. However, our results corroborate the earlier findings of Mansour et al (2012) and Oluwole et al (2008) who observed that species such as Eragrostis spp. and Sporobolus spp.…”

Section: Cynodon Dactylonsupporting

confidence: 93%

See 1 more Smart Citation

Piospheric influence on forage species composition and abundance in semi-arid Karamoja sub-region, Uganda

et al. 2015

View full text Add to dashboard Cite

Piospheres in semi-arid areas are gradients of animal impacts around watering holes. Few studies have examined the impact dynamics of herbaceous and woody species composition and abundance in relation to piospheres in East Africa. In this study, we identified the trend in piosphere development, assessed piosphere use and change indicators, and identified herbaceous and woody plant structure in relation to piospheres in the Karamoja sub-region, Uganda. Results revealed that piosphere development has been reactionary to drought and/or insecurity events and increased rapidly in the last decade. A diversity of herbaceous and woody plants exists around the piospheres. Use and change indicators revealed high trampling and grazing intensity, high presence of erosion signs and low litter cover. Gradient distance had both positive and negative effects on trampling intensity, percent exposure and plant height, respectively. A negative and positive effect of gradient distance was also observed on different herbaceous and woody forage species leading to the identification of both increaser and decreaser species around the piospheres. Therefore, as concentrated use of the piospheres continues unabated, an outward ripple effect leading to loss and/or increase of undesirable herbaceous and woody species will be felt. This will have an impact on the composition and abundance dynamics of desirable forage species in the sub-region.

show abstract

Section: Cynodon Dactylonsupporting

confidence: 93%

“…These species have previously been used as indicator species of rangeland degradation. For example, Mansour et al (2012) discussed that rangeland condition can be classified using these increaser species; thus moderate condition can be identified using increaser I (e.g. Hyparrhenia spp.…”

Section: Cynodon Dactylonmentioning

confidence: 99%

Piospheric influence on forage species composition and abundance in semi-arid Karamoja sub-region, Uganda

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Also, application of NPP is only one aspect of determining the deterioration of the rangeland ecosystem. Future efforts should be made to assess the change in plant species in the rangeland ecosystem by using hyperspectral remote sensing data (Mansour et al, 2012).…”

Section: Discussionmentioning

confidence: 99%

Monitoring rangeland degradation using a novel local NPP scaling based scheme over the “Three-River Headwaters” region, hinterland of the Qinghai-Tibetan Plateau

Wang

Xia

et al. 2017

Quaternary International

View full text Add to dashboard Cite

Abstract-the "Three-River Headwaters" region (TRHR) rangeland ecosystem is extremely sensitive and fragile, and in recent years has undergone continuous degradation. The vast area and severe nature conditions inhibit data acquisition and field experiments, resulting in different understandings about the spatial characteristics and dynamics of rangeland degradation in the region. Therefore, reliable monitoring method of rangeland degradation is urgently needed for the rangeland protection and management. In this paper, a novel rangeland degradation monitoring scheme based on Local NPP Scaling (LNS) was suggested;A suitable partition program of rangeland productivity unit was set up by using Analytical Hierarchy Process (

show abstract

“…Three supervised classification methods (MLC, RF and SVM) were selected as classifiers, since their efficiency was proven in vegetation mapping in recent studies [34,35].…”

Section: Applied Classification Methodsmentioning

confidence: 99%

Classification of Herbaceous Vegetation Using Airborne Hyperspectral Imagery

et al. 2015

View full text Add to dashboard Cite

Abstract:Alkali landscapes hold an extremely fine-scale mosaic of several vegetation types, thus it seems challenging to separate these classes by remote sensing. Our aim was to test the applicability of different image classification methods of hyperspectral data in this complex situation. To reach the highest classification accuracy, we tested traditional image classifiers (maximum likelihood classifier-MLC), machine learning algorithms (support vector machine-SVM, random forest-RF) and feature extraction (minimum noise fraction (MNF)-transformation) on training datasets of different sizes. Digital images were acquired from an AISA EAGLE II hyperspectral sensor of 128 contiguous bands (400-1000 nm), a spectral sampling of 5 nm bandwidth and a ground pixel size of 1 m. For the classification, we established twenty vegetation classes based on the dominant species, canopy height, and total vegetation cover. Image classification was applied to the original and MNF (minimum noise fraction) transformed dataset with various training sample sizes between 10 and 30 pixels. In order to select the optimal number of the transformed features, we applied SVM, RF and MLC classification to 2-15 MNF transformed bands. In the case of the original bands, SVM and RF classifiers provided high accuracy irrespective of the number of the training pixels. We found that SVM and RF produced the best accuracy when using the first nine MNF transformed bands; involving further features did not increase classification accuracy. SVM and RF provided high accuracies with the transformed bands, especially in the case of the OPEN ACCESS Remote Sens. 2015, 7 2047 aggregated groups. Even MLC provided high accuracy with 30 training pixels (80.78%), but the use of a smaller training dataset (10 training pixels) significantly reduced the accuracy of classification (52.56%). Our results suggest that in alkali landscapes, the application of SVM is a feasible solution, as it provided the highest accuracies compared to RF and MLC. SVM was not sensitive in the training sample size, which makes it an adequate tool when only a limited number of training pixels are available for some classes.

show abstract

Discriminating indicator grass species for rangeland degradation assessment using hyperspectral data resampled to AISA Eagle resolution

Cited by 76 publications

References 48 publications

Piospheric influence on forage species composition and abundance in semi-arid Karamoja sub-region, Uganda

Piospheric influence on forage species composition and abundance in semi-arid Karamoja sub-region, Uganda

Monitoring rangeland degradation using a novel local NPP scaling based scheme over the “Three-River Headwaters” region, hinterland of the Qinghai-Tibetan Plateau

Classification of Herbaceous Vegetation Using Airborne Hyperspectral Imagery

Contact Info

Product

Resources

About