Evaluation of multisource data for glacier terrain mapping: a neural net approach

Shukla, Anurag; Yousuf, Bisma

doi:10.1080/10106049.2016.1161078

Cited by 21 publications

(19 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature suggests various methods for mapping of supraglacial debris cover from remote sensing data including supervised and unsupervised classification techniques (Aniya et al, 1996;Shukla et al, 2010b;Shukla and Yousuf, 2016), techniques combining thermal and topographical properties (Shukla et al, 2010a;Bhambri et al, 2011), etc. In this study, to extract debris cover extent, we used the artificial neural network (ANN) technique.…”

Section: Methods Appliedmentioning

confidence: 99%

“…In this study, to extract debris cover extent, we used the artificial neural network (ANN) technique. Given the welldefined and well-distributed training sets, a three layer ANN model was iteratively optimized to find the most suitable network parameters and to arrive at the solution with least error (Shukla and Yousuf, 2016). The ANN classifies the debris-covered areas and snow/ice areas efficiently but sometimes fails in deep shadow regions, which were corrected manually during postprocessing.…”

Section: Methods Appliedmentioning

confidence: 99%

See 1 more Smart Citation

Assessing the status of glaciers in part of the Chandra basin, Himachal Himalaya: A multiparametric approach

et al. 2017

Self Cite

View full text Add to dashboard Cite

This study investigates the change in multiple glacier parameters of three valley-type glaciers (Sakchum (SC), Chhota Shigri (CS), and Bara Shigri (BS)) located in Chandra basin, Himachal Himalaya, sharing the same climatic regime, and assesses the control of nonclimatic factors on wholesome glacier response. Multitemporal satellite remote sensing data from Landsat-TM/ETM/OLI (1993-2014), and Terra-ASTER (2002-2014) along with an SRTM digital elevation model were used for extraction of the glacier parameters. Results show that while SC and BS retreated (SC: 10.65 ±2.52 m/y; BS: 15.51 ±2.52 m/y) and lost area (SC: 0.49 ±0.0032 km 2 , BS: 1.18 ±0.0032 km 2), the CS remained relatively stable (retreat rate: 4.06 ±2.52 m/y, area loss: 0.19 ±0.0032 km 2) during 1993-2014. However, results of surface ice velocities (SIV) change (SC: 24.41%, CS: 21.60%, and BS: 28.49%) and surface elevation change (SC:-1.22 m/y, CS:-0.91 m/y and BS:-1.21 m/y) suggest a comparable slowing down and surface lowering from 2002 to 2014. Debris cover also varied substantially (SC: 30.25%, CS: 11.96%, BS: 19.61%) on these glaciers. Results reveal that higher retreat/deglaciation of glaciers was associated with higher altitudinal range, slow SIV in lower ablation zones (LAZ), and glacier hypsometry. Debris cover on glaciers was found to be controlled by slope, higher deglaciation rates, higher SIV in the upper ablation zone (UAZ) coupled with lower SIV in LAZ and surface lowering. Glacier SIV was primarily governed by slope gradient, differential surface lowering, and size of accumulation zone (ACZ). The SIV results confirm the presence of stagnant zones in the lower ablations of SC (<1 km upstream) and BS (<6 km upstream) and a major SIV dropdown in the UAZ (SC: 34.48%, BS: 37.35%), indicating the expansion of stagnant zones farther up. Glacier surface lowering seemed to be influenced by ice-flux, changing spatial distribution of debris cover, presence of supraglacial lakes, and ice cliffs bordering them. Melting around supraglacial lakes and backwasting of ice cliffs may be the prime reasons behind intense mass loss observed in the stagnant zone of the Bara Shigri glacier, where surface lowering was ~32% higher than glacier-wide thinning. Differential surface lowering in glaciers reduced the surface gradient and hence the SIV. Also, rapid surface gradient changes and SIV dropdown in the Sakchum glacier indicate possible development of supraglacial lakes on it in the future. Interestingly, despite close proximity, SC, CS, and BS demonstrate three distinct ablation patterns, reemphasizing the role of nonclimatic factors. Overall, the study states that mutual 3 variation of glacier parameters together with nonclimatic factors exercise a great control on glacier response.

show abstract

Section: Methods Appliedmentioning

confidence: 99%

Section: Methods Appliedmentioning

confidence: 99%

Assessing the status of glaciers in part of the Chandra basin, Himachal Himalaya: A multiparametric approach

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…These along with other ancillary layers [Green/SWIR ratio, KT/Green/SWIR ratio, Normalized Difference Snow Index (NDSI), Snow Grain Size Index (SGI), variance and homogeneity] were used to refine the SPC process (see Table A.1, Supplementary material). These layers were chosen due to their successful application in many studies [22], [32] and their ability to differentiate between compositionally similar and shaded/crevassed facies.…”

Section: Research Area and Datasetsmentioning

confidence: 99%

“…Whereas, certain glacier facies lack spectral variability among them due to their compositional similarity (supraglacial/periglacial debris and valley-rock) or glacier's surface morphology (crevassed/ shadowed snow facies and ice facies). This can induce misclassification errors, which can although be reduced by using spectral plus ancillary data in the classification process [18], [22]. Acquisition time of the RD may highly influence the classification accuracy of the glacier facies due to their dynamicity in the input and RD.…”

mentioning

confidence: 99%

On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies

Yousuf

Shukla

Arora

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Subpixel classification (SPC) extracts meaningful information on land-cover classes from the mixed pixels. However, the major challenges for SPC are to obtain reliable soft reference data (RD), use apt input data, and achieve maximum accuracy. This article addresses these issues and applies the support vector machine (SVM) to retrieve the subpixel estimates of glacier facies (GF) using high radiometric-resolution Advanced Wide Field Sensor (AWiFS) data. Precise quantification of GF has fundamental importance in the glaciological research. Efficacy of the approach was first tested on the synthetic data followed by the input AWiFS and reference MultiSpectral Instrument data, including ancillary data. SPC of synthetic data resulted in overall accuracy (OA) of 95%, proving the merit of SVM. Classification accuracy is inversely related to the glacier's surface heterogeneity. Reducing the number of classes enhanced the OA by ∼18%. Source and timing of RD invariably controls the SPC accuracy. OA improved by ∼5% on addressing the issue of temporal gap between input and RD. ∼11% increase in OA with the inclusion of ancillary data confirmed their positive effect on the accuracy. Input and reference fractional area of GF were strongly correlated (r > 0.9) with each other substantiating the results.

show abstract

“…An effective methodology that combines the versatility of OBIA and the robustness of the PBIA could reduce the dependability of multiple kinds of ancillary inputs. Shukla and Yousuf [123] explain the necessity of ancillary inputs for the reduction of misclassification errors. However, this study has successfully mapped facies not only without multiple ancillary inputs, but also without dependence on SWIR bands.…”

Section: Significancesmentioning

confidence: 99%

Explorative Study on Mapping Surface Facies of Selected Glaciers from Chandra Basin, Himalaya Using WorldView-2 Data

2019

View full text Add to dashboard Cite

Mapping of surface glacier facies has been a part of several glaciological applications. The study of glacier facies in the Himalayas has gained momentum in the last decade owing to the implications imposed by these facies on the melt characteristics of the glaciers. Some of the most commonly reported surface facies in the Himalayas are snow, ice, ice mixed debris, and debris. The precision of the techniques used to extract glacier facies is of high importance, as the result of many cryospheric studies and economic reforms rely on it. An assessment of a customized semi-automated protocol against conventional and advanced mapping algorithms for mapping glacier surface facies is presented in this study. Customized spectral index ratios (SIRs) are developed for effective extraction of surface facies using thresholding in an object-based environment. This method was then tested on conventional and advanced classification algorithms for an evaluation of the mapping accuracy for five glaciers located in the Himalayas, using very high-resolution WorldView-2 imagery. The results indicate that the object-based image analysis (OBIA) based semi-automated SIR approach achieved a higher average overall accuracy of 87.33% (κ = 0.85) than the pixel-based image analysis (PBIA) approach. Among the conventional methods, the Maximum Likelihood performed the best, with an overall accuracy of 78.71% (κ = 0.75). The Constrained Energy Minimization, with an overall accuracy of 68.76% (κ = 0.63), was the best performer of the advanced algorithms. The advanced methods greatly underperformed in this study. The proposed SIRs show a promise in the mapping of minor features such as crevasses and in the discrimination between ice-mixed debris and debris. We have efficiently mapped surface glacier facies independently of short-wave infrared bands (SWIR). There is a scope for the transferability of the proposed SIRs and their performance in varying scenarios.

show abstract

Evaluation of multisource data for glacier terrain mapping: a neural net approach

Cited by 21 publications

References 38 publications

Assessing the status of glaciers in part of the Chandra basin, Himachal Himalaya: A multiparametric approach

Assessing the status of glaciers in part of the Chandra basin, Himachal Himalaya: A multiparametric approach

On Drivers of Subpixel Classification Accuracy—An Example From Glacier Facies

Explorative Study on Mapping Surface Facies of Selected Glaciers from Chandra Basin, Himalaya Using WorldView-2 Data

Contact Info

Product

Resources

About