An Evaluation of Alternative Image Classification Techniques for the Identification and Mapping of Tropical Savanna Landscape in Northern Australia

Khwaja, Z; Ahmad, Waqar; Williams, Rikkaine J.

doi:10.1080/10106040308542261

Cited by 4 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of remote sensing technologies is particularly suited to applications in northern Australia, owing to the low population density, the harsh climate and vast areas involved (Hill & Carter 1999). Multispectral data such as Landsat TM5 have been used in northern Australia to map vegetation communities across different northern Australian ecosystems (Ahmad et al 1998;Harvey & Hill 2000;Khwaja et al 2003). It has also been used to map woody vegetation cover (Kuhnell et al 1998), and for assessing the impact of tropical cyclones in Australia (Preston 1987;Paling & Kobryn 2005).…”

Section: Introductionmentioning

confidence: 98%

Estimates of tree canopy loss as a result of Cyclone Monica, in the Magela Creek catchment northern Australia

Staben¹,

Evans

2008

Austral Ecology

View full text Add to dashboard Cite

Severe tropical Cyclone Monica impacted the coast of northern Australia in April 2006 with estimated maximum wind gusts of 360 km h -1 . It rapidly moved inland losing intensity and passed over the town of Jabiru as a category 2 system, with maximum wind gusts recorded at 135 km h -1 . The cyclone had a significant impact on the landscapes within the Alligator Rivers Region and significant windthrow of trees occurred.This paper describes the level of impact that category 2 level winds had on tree canopy loss 10 days after cyclone and then again 1 year later. Recovery was assessed using multispectral satellite imagery in sub-catchments of the Magela Creek catchments. A non-linear relationship was fitted between a modified vegetation index (derived from Landsat TM5 satellite data) and percentage tree canopy cover (measured from very high resolution QuickBird satellite data).The results of the non-linear relationship, used to estimate percentage canopy cover, indicate that 10 days after cyclone, there was significant disturbance to tree canopy. However, data 1 year after cyclone show that recovery of canopy across the studied catchments varied between 8% and 19% of the percentage canopy cover that remained after the initial impact of the cyclone. Further analysis in the three sub-catchments using Geographical Information System showed that proportionally, riparian zones and inundated areas in each of the sub-catchments suffered greater loss of tree canopy cover compared with upland areas.

show abstract

Section: Introductionmentioning

confidence: 98%

Estimates of tree canopy loss as a result of Cyclone Monica, in the Magela Creek catchment northern Australia

Staben¹,

Evans

2008

Austral Ecology

View full text Add to dashboard Cite

show abstract

“…This has been demonstrated in a number of studies. 38,[41][42][43] One notable example by Ref. 44 compared multiple images (Landsat and SPOT-5, moderate resolution imaging spectroradiometer, and GeoEye-1) in the savanna environment.…”

Section: Introductionmentioning

confidence: 99%

Investigating accuracies of WorldView-2, Sentinel-2, and SPOT-6 in discriminating morphologically similar savanna woody plant species during a dry season

Fundisi

Tesfamichael

Ahmed

2022

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Accurate assessment of woody species diversity using remote sensing can assist ecologists by providing timely information for ecosystem management. The increasing availability of remotely sensed data necessitates the investigation of accuracies of different sensors in classifying plant species, especially during the dry season when foliage amount is low. WorldView-2, SPOT-6, and Sentinel-2 images were compared in detecting woody species (n ¼ 27) and three coexisting land cover types in a savanna environment during a dry period. Random Forest (RF) and Support Vector Machine (SVM) classifiers were applied to each imagery to make a strong case for the comparison. The overall classification accuracies ranged between 52% and 65% for all images, with the WorldView-2 image performing the best followed by Sentinel-2 and SPOT-6 images. These accuracy rankings were similar for both the RF and SVM classifiers, with the former faring better. Pairwise comparison of the images using McNemar's test showed significant differences between images in their ability to correctly identify woody species. Analysis of band importance revealed better contributions to the classifications of infrared bands for all images. Overall, the findings showed the potential of optical imagery in classifying and monitoring woody species hotspots in savanna environments even during a low photosynthesis season.

show abstract

“…In particular, optical remote sensing utilises the sensitivity of spectra to biochemical and structural characteristics to distinguish vegetation types [12]. Advances in spectral and spatial resolution of remote sensing have allowed for more efficient species diversity estimation in different environments including grasslands (e.g., [7,13], temperate forest (e.g., [14][15][16], wetlands (e.g., [17,18], tropical forest (e.g., [19][20][21] and savanna (e.g., [22][23][24].…”

Section: Introductionmentioning

confidence: 99%

“…The traditional remote sensing-based species classification approaches identify a defined number of classes, irrespective of the spatial resolution of remotely-sensed data [9,21,22,25]. Such approaches, therefore, can underestimate the number of species that potentially exist in a given environment.…”

Section: Introductionmentioning

confidence: 99%

“…Operationally, remotely-sensed data acquired during dry seasons are less affected by clouds and therefore provide readily interpretable information [38]. Ecologically, dry season biodiversity assessment is vital as part of continuous monitoring strategies such as phenological tracking [6,22] and land degradation facing the savanna ecosystem [23,42].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

et al. 2020

View full text Add to dashboard Cite

Remote sensing techniques are useful in the monitoring of woody plant species diversity in different environments including in savanna vegetation types. However, the performance of satellite imagery in assessing woody plant species diversity in dry seasons has been understudied. This study aimed to assess the performance of multiple Gray Level Co-occurrence Matrices (GLCM) derived from individual bands of WorldView-2 satellite imagery to quantify woody plant species diversity in a savanna environment during the dry season. Woody plant species were counted in 220 plots (20 m radius) and subsequently converted to a continuous scale of the Shannon species diversity index. The index regressed against the GLCMs using the all-possible-subsets regression approach that builds competing models to choose from. Entropy GLCM yielded the best overall accuracy (adjusted R 2 : 0.41−0.46; Root Mean Square Error (RMSE): 0.60−0.58) in estimating species diversity. The effect of the number of predicting bands on species diversity estimation was also explored. Accuracy generally increased when three-five bands were used in models but stabilised or gradually decreased as more than five bands were used. Despite the peak accuracies achieved with three-five bands, performances still fared well for models that used fewer bands, showing the relevance of few bands for species diversity estimation. We also assessed the effect of GLCM window size (3×3, 5×5 and 7×7) on species diversity estimation and generally found inconsistent conclusions. These findings demonstrate the capability of GLCMs combined with high spatial resolution imagery in estimating woody plants species diversity in a savanna environment during the dry period. It is important to test the performance of species diversity estimation of similar environmental setups using widely available moderate-resolution imagery.

show abstract

An Evaluation of Alternative Image Classification Techniques for the Identification and Mapping of Tropical Savanna Landscape in Northern Australia

Cited by 4 publications

References 10 publications

Estimates of tree canopy loss as a result of Cyclone Monica, in the Magela Creek catchment northern Australia

Estimates of tree canopy loss as a result of Cyclone Monica, in the Magela Creek catchment northern Australia

Investigating accuracies of WorldView-2, Sentinel-2, and SPOT-6 in discriminating morphologically similar savanna woody plant species during a dry season

Estimation of woody plant species diversity during a dry season in a savanna environment using the spectral and textural information derived from WorldView-2 imagery

Contact Info

Product

Resources

About