Moist deciduous forest identification using temporal MODIS data — A comparative study using fuzzy based classifiers

Upadhyay, Priyadarshi; Ghosh, S. K.; Kumar, Anil

doi:10.1016/j.ecoinf.2013.07.002

Cited by 11 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 shows that Doon valley occasionally faces winter rainfall. Therefore similar rise in NDVI values was also observed by Upadhyay et al, (2013). However, they used coarser spatial resolution datasets to understand the phenology of MDF.…”

Section: Establish Relationship Between Multi-temporal Ndvi and Phenomentioning

confidence: 85%

“…Since major phenological changes for MDF takes place from November to April (Jeganathan et al, 2010b) and a recent study of Upadhyay et al, (2013) Temporal time series of Landsat-8 derived surface reflectance NDVI were acquired from United States Geological Survey (USGS). We acquired 7 scenes of processed NDVI from Nov-2013 to Apr-2014 and 5 scenes from Nov-2014 to Apr-2015.…”

Section: Acquisition and Preprocessing Of Remote Sensing Datastesmentioning

confidence: 99%

See 1 more Smart Citation

Phenology Analysis of Forest Vegetation to Environmental Variables During Pre- And Post-Monsoon Seasons in Western Himalayan Region of India

Khare¹,

Latifi²,

Ghosh³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:To assess the phenological changes in Moist Deciduous Forest (MDF) of western Himalayan region of India, we carried out NDVI time series analysis from 2013 to 2015 using Landsat 8 OLI data. We used the vegetation index differencing method to calculate the change in NDVI (NDVI change ) during pre and post monsoon seasons and these changes were used to assess the phenological behaviour of MDF by taking the effect of a set of environmental variables into account. To understand the effect of environmental variables on change in phenology, we designed a linear regression analysis with sample-based NDVI change values as the response variable and elevation aspect, and Land Surface Temperature (LST) as explanatory variables. The Landsat-8 derived phenology transition stages were validated by calculating the phenology variation from Nov 2008 to April 2009 using Landsat-7 which has the same spatial resolution as Landsat-8. The Landsat-7 derived NDVI trajectories were plotted in accordance with MODIS derived phenology stages (from Nov 2008 to April 2009) of MDF. Results indicate that the Landsat -8 derived NDVI trajectories describing the phenology variation of MDF during spring, monsoon autumn and winter seasons agreed closely with Landsat-7 and MODIS derived phenology transition from Nov 2008 to April 2009. Furthermore, statistical analysis showed statistically significant correlations (p < 0.05) amongst the environmental variables and the NDVI change between full greenness and maximum frequency stage of Onset of Greenness (OG) activity.. The major change in NDVI was observed in medium (600 to 650 m) and maximum (650 to 750 m) elevation areas. The change in LST showed also to be highly influential. The results of this study can be used for large scale monitoring of difficult-to-reach mountainous forests, with additional implications in biodiversity assessment. By means of a sufficient amount of available cloud-free imagery, detailed phenological trends across mountainous forests could be explained.

show abstract

Section: Establish Relationship Between Multi-temporal Ndvi and Phenomentioning

confidence: 85%

Section: Acquisition and Preprocessing Of Remote Sensing Datastesmentioning

confidence: 99%

Phenology Analysis of Forest Vegetation to Environmental Variables During Pre- And Post-Monsoon Seasons in Western Himalayan Region of India

Khare¹,

Latifi²,

Ghosh³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…There are different kinds of soft and hard classifiers such as conventional maximum likelihood classifiers (MLC), linear mixture models (LMM). 8,9 Theoretical fuzzy set classifiers-commonly used are Fuzzy c-means (FCM) clustering 10 and the possibilistic c-means (PCM) clustering, as well as modified versions of possibilistic classification, 11 algorithms based on support vector machines (SVM) and also neural networks and their advanced versions. 12 To assign membership values to each pixel to represent a target classes, a fuzzy-based classification technique was devised.…”

Section: Introductionmentioning

confidence: 99%

“…5 The main disadvantages of PCM were sensitivity toward good initialization, coincident cluster problem, and neglecting the membership that creates the category centroid on the brink of data points. 5,11,13 The heterogeneity was present within the crop field due to variation in spectral reflectance from each individual crop, also it was caused by shadow, variability in irrigation and fertilizer application, etc. To reduce the effect of the heterogeneity within the category, "individual sample as mean" approach was proposed for different statistical parameters in Fuzzy classification.…”

Section: Introductionmentioning

confidence: 99%

“…Mainly representing the “degree of belongingness” or “compatibility,” or “typicality.” 15 , 16 The possibilistic c-mean (PCM) algorithm was proposed to estimate absolutely the membership values for every class independently of all other classes 5 . The main disadvantages of PCM were sensitivity toward good initialization, coincident cluster problem, and neglecting the membership that creates the category centroid on the brink of data points 5 , 11 , 13 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Handling heterogeneity within castor crop fields through “Individual Sample as Mean” training parameter approach

Murugan

Kumar

2023

J. Appl. Rem. Sens.

Self Cite

View full text Add to dashboard Cite

.The high temporal resolution data has a great opportunity for specific crop mapping. The recent advancement in remote sensing data had a good impact on crop classification and mapping. In this research work, modified possibilistic c-means (MPCM) fuzzy machine learning approach has been applied for castor crop mapping, using sentinel 2A/2B satellite temporal images and local convolution as adaptive modified possibilistic local information c-means (ADMPLICM) algorithm was applied to remove isolated unwanted pixels. In training sample parameter “individual sample as mean” method was used to handle heterogeneity within the castor fields. The class-based sensor independent normalized difference vegetation index (CBSI-NDVI), normalized difference vegetation index (Red-NIR), and modified NDVI were produced, then separability analysis was conducted for the selecting optimum temporal date for castor crop mapping. The heterogeneity effect within the field was studied using variance parameters, and its values were observed low within the castor crop field. While considering the “individual sample as mean” training parameter approach on CBSI-NDVI, the variance of the target was decreased from 0.019 to 0.016. The identified castor field variance was close to the training field based on their high membership values and these fields had low mean membership difference (MMD) value. MMD values of castor training class with other crop classes were very high (0.425 – Isabgol, 0.502 – wheat, 0.259 – Fenugreek, 0.809 – Mustard, and 0.569 – Cumin), which indicates other crops were distinguished very well.

show abstract

Performance Evaluation of Kernel-Based Supervised Noise Clustering Approach

SenGupta

Kumar

Dwivedi

2019

J Indian Soc Remote Sens

View full text Add to dashboard Cite

Moist deciduous forest identification using temporal MODIS data — A comparative study using fuzzy based classifiers

Cited by 11 publications

References 47 publications

Phenology Analysis of Forest Vegetation to Environmental Variables During Pre- And Post-Monsoon Seasons in Western Himalayan Region of India

Phenology Analysis of Forest Vegetation to Environmental Variables During Pre- And Post-Monsoon Seasons in Western Himalayan Region of India

Handling heterogeneity within castor crop fields through “Individual Sample as Mean” training parameter approach

Performance Evaluation of Kernel-Based Supervised Noise Clustering Approach

Contact Info

Product

Resources

About