ArticlePDF Available

Temporal MODIS Data for Identification of Wheat Crop using Noise clustering Soft Classification Approach

Authors:

Abstract and Figures

In this study, temporal MODIS-Terra MOD13Q1 data have been used for identification of wheat crop uniquely, using the Noise Clustering (NC) soft classification approach. This research also optimizes the selection of date combination and vegetation index for classification of wheat crop. First, a separability analysis is used to optimize the date combination for each case of number of dates and vegetation index. Then these scenes have undergone for NC soft classification. The resolution parameter (δ) was optimized for the NC classifier and found to be a value of 1.6×104 for wheat crop identification. Classified outputs were analyzed by Receiver Operating Characteristics (ROC) analysis for sub-pixel detection. Highest area under the ROC curve was found for SAVI corresponding to the three different phenological stages datasets. From this study, the datasets corresponding to the Sowing, Flowering and Maturity phenological stages of wheat crop were found more suitable to identify it uniquely.
Content may be subject to copyright.
This article was downloaded by: [PRIYADARSHI UPADHYAY]
On: 30 May 2015, At: 23:52
Publisher: Taylor & Francis
Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered
office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK
Click for updates
Geocarto International
Publication details, including instructions for authors and
subscription information:
http://www.tandfonline.com/loi/tgei20
Temporal MODIS data for identification
of wheat crop using noise clustering
soft classification approach
Priyadarshi Upadhyay
a
, S.K. Ghosh
a
& Anil Kumar
b
a
Department of Civil Engineering, Indian Institute of Technology
Roorkee, Roorkee, India
b
Indian Institute of Remote Sensing, Indian Space Research
Organization, Dehradun, India
Accepted author version posted online: 05 May 2015.Published
online: 26 May 2015.
To cite this article: Priyadarshi Upadhyay, S.K. Ghosh & Anil Kumar (2015): Temporal MODIS data
for identification of wheat crop using noise clustering soft classification approach, Geocarto
International, DOI: 10.1080/10106049.2015.1047415
To link to this article: http://dx.doi.org/10.1080/10106049.2015.1047415
PLEASE SCROLL DOWN FOR ARTICLE
Taylor & Francis makes every effort to ensure the accuracy of all the information (the
“Content”) contained in the publications on our platform. However, Taylor & Francis,
our agents, and our licensors make no representations or warranties whatsoever as to
the accuracy, completeness, or suitability for any purpose of the Content. Any opinions
and views expressed in this publication are the opinions and views of the authors,
and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content
should not be relied upon and should be independently verified with primary sources
of information. Taylor and Francis shall not be liable for any losses, actions, claims,
proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or
howsoever caused arising directly or indirectly in connection with, in relation to or arising
out of the use of the Content.
This article may be used for research, teaching, and private study purposes. Any
substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing,
systematic supply, or distribution in any form to anyone is expressly forbidden. Terms &
Conditions of access and use can be found at http://www.tandfonline.com/page/terms-
and-conditions
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
Temporal MODIS data for identication of wheat crop using noise
clustering soft classication approach
Priyadarshi Upadhyay
a
*
,1
, S.K. Ghosh
a
and Anil Kumar
b
a
Department of Civil Engineering, Indian Institute of Technology Roorkee, Roorkee, India;
b
Indian Institute of Remote Sensing, Indian Space Research Organization, Dehradun, India
(Received 4 January 2015; accepted 23 April 2015)
In this study, temporal MODIS-Terra MOD13Q1 data have been used for identica-
tion of wheat crop uniquely, using the noise clustering (NC) soft classication
approach. This research also optimises the selection of date combination and vegeta-
tion index for classication of wheat crop. First, a separability analysis is used to
optimise the date combination for each case of number of dates and vegetation
index. Then, these scenes have undergone for NC soft classication. The resolution
parameter (δ) was optimised for the NC classier and found to be a value of
1.6 × 10
4
for wheat crop identication. Classied outputs were analysed by receiver
operating characteristics (ROC) analysis for sub-pixel detection. Highest area under
the ROC curve was found for soil-adjusted vegetation index corresponding to the
three different phenological stages data sets. From this study, the data sets corre-
sponding to the Sowing, Flowering and Maturity phenological stages of wheat crop
were found more suitable to identify it uniquely.
Keywords: MODIS; NC; separability; resolution parameter; phenology; ROC
1. Introduction
Wheat is a major agriculture crop and amongst one of the most produced cereals over
the world. Timely information of wheat crop at regional scale is quite useful for wheat
crop management and organised economy. The early estimate of wheat crop is useful
for many applications like the policy makers, grain industry, disaster relief and drought
declaration (Potgieter et al.
2010). To estimate the regional distribution of an individual
crop, remote sensing has been proven as an effective tool (Lobell & Asner
2004;Pan
et al.
2012). Since every existing crop has its own unique phenology during the grow-
ing season (Pan et al.
2012), therefore remote sensing data acquired over a period dur-
ing the phenological changes of a crop can be more effective tool to discriminate it
from other classes present in the data. However, the changes due to phenology cannot
be utilised while using single date remote sensing image. Further, due to the small
swath of the high spatial resolution images, large-area crop mapping faces a problem of
high cost and handling of large volume of data. To avoid these problems, at present the
focus is towards the use of high temporal and low spatial resolution satellite data sets.
On the other hand, satellite data-based vegetation indices have been used for many
purposes in remote sensing. Time series MODIS, normalized difference vegetation
*Corresponding author. Email: priyadarshi.529@shooliniuniversity.com
1
Current afliation: Shoolini University, Solan, India
© 2015 Taylor & Francis
Geocarto International, 2015
http://dx.doi.org/10.1080/10106049.2015.1047415
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
index (NDVI) and enhanced vegetation index (EVI) data have been popularly used for
crop mapping (Pringle et al. 2012) and to estimate crop phenology (Sakamoto et al.
2005). Potgieter et al. (2010) provided the early-season information on crop area using
the multi-temporal MODIS 250 m EVI data. The study was aimed to full the require-
ment of the early estimates of net crop production before the harvest. Unsupervised
K-means algorithm was used for the classication. They have estimated the early-
season winter crop area 2 months before the harvest. Pan et al. (
2012) proposed a crop
proportion phenology index (CPPI) to estimate the winter wheat crop area up to
sub-pixel level using MODIS EVI time series area. They have used the phenological
variables from the October to June of next year as input to calculate CPPI. The regres-
sion model was used to estimate the winter wheat crop area. The parameters of CPPI
have been calculated from the inverted form of the regression model using the training
pixels.
The MOD13Q1 product from the MODIS-Terra satellite is a key tool for vegetation
mapping, due to its high temporal resol ution (Pan et al.
2012). However, due to its
moderate spatial resol ution, mixed pixels produce signicant errors in crop area estima-
tion (Foody
2000; Shalan et al. 2003). Fuzziness can be incorporated in the classica-
tion process of such pixel, such that these pixels may have multiple and partial class
membership (Foody et al.
1997). Such a classication is known as soft classication. A
soft classication technique assigns a pixel to different classes according to its area pre-
sent inside the pixel. It yields a number of fraction images equal to the number of land
cover classes. The supervised fuzzy c-means (FCM) (Bezdek et al.
1984), supervised
possibilistic c-means (PCM) (Krishnapuram & Keller
1993), noise clustering (Dave
1991; Dave & Krishnapuram 1997), articial neural networks (Kanellopoulos et al.
1992) and mixture modelling (Kerdiles & Grondona 1996) are commonly used for the
soft classications of satellite data. Amongst these, the rst three are fuzzy set
theory-based classiers.
Earlier, the fuzzy set theory-based soft classiers such as FCM or PCM have been
used in a number of studies (Shalan et al.
2003; Ibrahim et al. 2005 ).To derive accurate
estimates of sub-pixel land cover composition from FCM, it is necess ary to have the
information of all classes in the training stage of classication (Foody
2000). In FCM,
noisy points (i.e. outliers) are grouped with information classes with same overall mem-
bership value of one. Thus, the FCM classication algorithm faces the problem of noise
(outliers). The problem of noise can be resolved in the PCM algorithm by providing
one noise class per good cluster. However, in noise clustering (NC) approach, noise
class can be segregated as a separate information class or one noise class for all clusters
(Dave & Krishnapuram
1997). Thus, unlike the FCM, the presence of untrained classes
does not affect the classication outputs in both PCM and NC (Foody
2000). Further,
unlike the FCM classier, NC and PCM do not follow the probability rule and hence
may be used for the identication of single land cover.
In the present research, the NC soft classication approach has been used for the
wheat crop estimation in a test site in India. Wheat production in India comes from a
single growing season. It is sown during OctoberDecember and harvested during
MarchMay (Krishna Kumar et al.
2004). Many studies in literature claimed that EVI
is better for crop identication (Huete et al.
2002; Justice et al. 2002; Houborg et al.
2007) but the robustness is still to be proved (Wardlow & Egbert 2010). Therefore, in
this study, different types of vegetation indices such as simple ratio (SR), NDVI,
soil-adjusted vegetation index (SAVI) and EVI have been selected for wheat crop
identication in a test site in India. The objective of this study were to (i) study the
2 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
effectiveness of the MODIS temporal indices data for wheat crop identication, (ii)
optimise the temporal indices datasets, (iii) optimise the resolution parameter δ for the
NC classication and (iv) assess the accuracy through the receiver operating
characteristic (ROC) analysis of sub-pixel detection.
2. Study area and data used
The study area chosen for this study is located between 29°500N30°352N latitude
and 76°1952E77°2221E longitude in the state of Haryana, India. Important places
within the study are Panipat, Karnal and Asandh as shown in Figure
1. Wheat, mustard
and sugarcane are the main crops grown in this region during NovemberMarch i.e.
the Rabi season. Wheat is the dominating crop in this region having large and homoge-
neous elds. The other major crops are sugarcane, ground nut, paddy and maize.
The average annual temperature for this study area ranges from 22.5 to 25 °C.
According to the Köppen climate classication system, the study area falls under the
semi-arid climatic zones. Geologically, the study area is under Indo-Gangetic plains
category with the rich alluvial soils. Tropical arid soil found in the study area is vary-
ing from the sandy loam to loam (Kaushal et al.
2009). The soil is deposited due to the
downstreams and the rivers and is more fertile. Average annual rainfall in this study
area is about 610 mm (Ahlawat & Sharma
2012). Nearly 70% rainfall occurs in this
Figure 1. Study area boundaries shown from MODIS data.
Geocarto International 3
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
region due to the south-west monsoon from July to September and the remaining
occurs during December to February.
The satellite data used in this research is from MODIS instrument which is operat-
ing on both the Terra and Aqua satellites. It has a viewing swath width of 2330 km
and views the entire surface of Earth in every 12 days. Its detectors measure 36 spec-
tral bands and acquire data at three spatial resolutions 250, 500 and 1000 m (
https://lp
daac.usgs.gov/products/modis_overview). Of 36 spectral bands of MODIS, only 7
bands are of primary use i.e. for vegetation a nd land surface studies. Different land
products are produced at various temporal resolutions. The products are acquired at
daily, 8-day, 16-day, monthly, quart erly, yearly basis. In the present research,
MODIS-Terra MOD13Q1 level-3 product (
https://lpdaac.usgs.gov/products/modis_prod
ucts_table/mod13q1
) with spatial resolution 250 m and a composite period of 16 days
have been used. The Red (B1: 620670 nm), NIR (B2: 841876 nm) and Blue (B3:
459479) of MOD13Q1 have been taken to generate different vegetation indices.
Classication method used in this study requires the information about a few
selected known locations in the satellite imagery as reference data. These known or
reference locations can be used for training the classier and for testing the outputs
(Congalton
1991; Foody 2002; Congalton & Green 2009 ). Therefore, ground samples
were collected for both the training and testing pixels. These training and testing elds
were selected using the random sampling scheme. These ground samples have been
acquired with the help from GPS-based survey data and existing land-use/land-cover
maps.
As a general rule, if the training data is being extracted from n bands, then the
number of training pixels should be greater than 10n for each class (Jensen
1986).
Further, Congalton (
1991) suggested that the minimum number of sample should be
75100 for each class to assess the accuracy of remote sensing data. However, accord-
ing to Congalton and Green (
2009), there is no universally accepted standard for
assessing the accuracy. The ground truth includes the distribution of the phenomenon
to be mapped, sample size, number, type and frequency of collection (Congalton &
Green
2009). At a particular condence level and desired precision, the sample size for
training and testing can be calculated using the formula given by Tortora (
1978).
3. Methodology adopted
In India, wheat production comes from a single growing season. Wheat sowing takes
place during OctoberDecember and harvested during MarchMay (Krishna Kumar
et al.
2004). Verma et al. (2003) for the same area has divided the entire Rabi season
into the seven phenological stages, viz. (i) Crown root initiation stage (meteorological
week numbers 4446), (ii) Tillering stage (meteorological week numbers 4749), (iii)
Jointing stage (meteorological week numbers 5052), (iv) Flowering stage (meteoro-
logical week numbers 13), (v) Milking stage (meteorological week numbers 46), (vi)
Dough stage (meteorological week numbers 79) and (vii) Maturity stage (meteorologi-
cal week numbers 1014). Based on this, the MODIS data were selected between
November 2011 and April 2012.
In this study, one of the aims was to acquire data at a regular interval of 16 days.
However, due to cloud cover, only one scene of 1 November 2011 was available
between November and December 2011. From the January to April 2012, scenes were
available for each 16-day composite period. This period contain information of all
phenological stages of wheat crop from the owering stage up to harvesting stage . The
4 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
major phenological changes occur during this interval only. The details of MODIS data
sets are shown in the Table 1. The dates mentioned in the Table 1 are not the actual
observation dates but the composite dates with a 16-day wi ndow for MODIS.
Figure
2 shows the owchart for the adopted methodology in this research. A eld
visit was carried out on 30 and 31 December 2011 to collect the ground control points
so that the exact positions of training and testing wheat elds can easily be found. The
study area has a larg e extent of homogeneous wheat eld, which can easily be identi-
ed in a 250 m × 250 m pixel. The vegetation indices acquired over a period was used
to generate the temporal spectral indices. Further, the Transform Divergence (TD) fea-
Table 1. Details for the MODIS data.
Day of the year Date Date number Phenological stage
305 01 November 2011 1 Sowing
17 17 January 2012 2 Flowering
33 02 February 2012 3 Milking
49 18 February 2012 4 Dough
65 05 March 2012 5 Maturity
81 21 March 2012 6 Maturity
97 06 April 2012 7 Harvesting
MODIS
01 Nov 2011
17 Jan 2012
02 Feb 2012
18 Feb 2012
05 Mar 2012
21 Mar 2012
06 Apr 2012
Field
information
Ground
truthing / Field
data gathering
SR, NDVI, SAVI and
EVI
Creation of training data
Feature selection
NC soft classification
Preparation of temporal
spectral indices
Optimization of δ
FAR and TP calculation
3D-ROC analysis for sub-pixel
detection
Figure 2. Methodology adopted for wheat crop mapping using NC approach.
Geocarto International 5
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
ture selection method was applied to select the optimised set of temporal spectral
indices. The optimised sets of temporal spectral indices were then used for discrimina-
tion of specic crop using the NC soft classication. The classication was performed
in an in-house java-based Sub-pixel Multi-Spectral Image Classier (Kumar et al.
2006). For the assessment of these soft classied outputs, the ROC analysis has been
used.
3.1. Vegetation indices
The SR which is also known as ratio-bas ed vegetation index was described by Birth
and McVey (
1968). This vegetation index is based on the fact that the vegetation
absorbs well in the red (visible) and reects very efciently in the near infrared spectral
band of the electromagnetic spectrum. It is computed as:
SR ¼
q
NIR
q
R
(1)
where ρ
NIR
reectance at near infra red (NIR) band and ρ
R
is reectance at red band.
A value of SR less than 1.0 is taken as non-vegetation while values greater than 1.0 is
considered as the vegetation. The SR reduces the topographic effects. The major draw -
back in this method is division by zero which gives the innite SR value corresponding
to the zero pixel value in red spect ral band.
Rouse et al. (
1973) introduced the NDVI in order to produce a spectral vegetation
index that separates green vegetation from its background soil brightness using Landsat
MSS digital data. The NDVI has been wi dely used for many vegetation related studies,
for last few decades. It is computed as:
NDVI ¼
q
NIR
q
R
q
NIR
þ q
R
(2)
The NDVI values ranges from 1 to +1. The negative NDVI represents the
non-vegetated area while the positive values represent the vegetated areas. Equation (2)
can be improved by incorporating a soil adjustment factor or inclusion of blue band for
atmospheric correction (Huete & Liu
1994). The soil adjustment factor is included to
minimise the inuence due to soil background. The derived index is known as SAVI in
several studies (Huete & Liu
1994; Running et al. 1994) and expressed as:
SAVI ¼
q
NIR
q
R
ðÞ1 þ LðÞ
q
NIR
þ q
R
þ L
(3)
where L is a canopy background adjustment factor and has a value of 0.5.
The MODIS Land Discipline Group has proposed EVI as a standard satellite veg-
etation product for MODIS Terra and Aqua. It is represe nted by Equation (4):
EVI ¼
q
NIR
q
R
q
NIR
þ C
1
q
R
C
2
q
B
þ L

G (4)
where ρ
B
is reectance at blue band. The EVI is a modied NDVI with a soil adjust-
ment factor L, gain factor G and tw o coefcients, C
1
and C
2
, which describe the use of
the blue band in correction of the red band for atmospheric aerosol scattering. These
coefcients C
1
, C
2
and L are empirically determined as 6.0, 7.5 and 1.0, respectively,
with G having a value of 2.5 (Huete & Liu
1994; Huete et al. 1997). This algorithm
has improved sensitivity to high biomass regions and improved vegetation monitoring
6 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
through a decoupling of the canopy background signal and a reduction in atmospheric
inuences.
3.2. Feature selection
Feature selection is an important step while classifying with multi-temporal and multi-
spectral remote sensing data. It is an effective method of selecting desired number of
features (or bands) from large sets of multi-spectral or temporal data (Bruzzone &
Serpico
2000). The computational requirement and cost are always dependent on the
number of input feature required for the classication. Therefore, in this study, the fea-
ture selection method has been used to make the suitable combinations of data sets so
that maximum accuracy can be achieved with low cost and less labour.
In this study, TD (Swain & Davis
1978) separability approach has been used.
The TD can be expressed as:
TD
ij
¼ 2000 1 exp
D
ij
8

(5)
where i and j are two signatures (classes) being compared and D
ij
is the divergence.
The divergence D
ij
can be calculated by the following equation.
D
ij
¼
1
2
tr C
i
C
j

C
1
i
C
1
j

þ
1
2
tr C
1
i
C
1
j

u
i
u
j

u
i
u
j

T

(6)
where C
i
is the covariance matrix of class i , u
i
is the mean vector of class i, tr is the
trace function and T is the transpose function of matrix.
The TD values range from 0 to 2000. As a general rule given by Jensen (
1986) that
if TD values for all LU/LC classes for a pair of spectral bands are greater than 1900,
then the classes can be considered to have no overlapping amongst them and that the
separation betw een two informational classes is good. If values vary between 1700 and
1900, then separation is fairly good and if the values of TD are below 1700, then
separation between informational classes is poor.
3.3. NC soft classication approach
The idea of proper handling of noisy points was rst proposed by Ohashi (
1984) (Dave
& Krishnapuram
1997). Further, according to Dave (1991), noise classes (or outliers)
can be segregated from the core information class (or cluster). They do not degrade the
quality of clustering analysis. The main concept of the NC algorithm is to introduce a
single noise information class (c + 1) that contains all noise data points. Originally, NC
has been developed as an unsupervised classier, yet can be modied to be used in the
supervised mode by providing the information class (or cluster) means directly from
the training data set (Foody
2000).
The objective function of the NC can be obtained by adding another term to FCM
for (c + 1)th noise information class as follows (Dave
1991):
J
nc
ðU; V Þ¼
X
c
i¼1
X
N
k¼1
l
ki
ðÞ
m
Dðx
k
; v
i
Þþ
X
N
k¼1
l
k;cþ1

m
d (7)
With Dðx
k
; v
i
Þ¼d
2
ki
¼ x
k
v
i
kk
2
A
¼ðx
k
v
i
Þ
T
Aðx
k
v
i
Þ
Geocarto International 7
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
where d [ 0isaxed parameter. The noise information class has no centre and the
dissimilarity D
k;cþ1
between x
k
and this noise information class can be expressed as
(Miyamoto et al.
2008):
D
k;cþ1
¼ d
The constraints imposed in the objective function of Equation (7) are given by:
l
f
¼
U ¼ l
ki
:
P
cþ1
j¼1
l
kj
¼ 1 ; 1 k N ;
l
ki
2 0; 1½; 1 k N ; 1 i c þ 1
8
<
:
9
=
;
(8)
In Equation (8), U ¼ N c þ 1ðÞmatrix, V ¼ðv
1
...v
c
Þ is the collection of vector of
cluster centres v
i
; l
ki
is a class membership values of a pixel, d
ki
is distance in feature
space between x
k
and v
i
, x
k
is vector (or feature vector) denoting spectral response of a
pixel k, v
i
is a vector (or prototype vector) denoting the cluster centre of class i, c and
N are total number of clusters and pixels, respectively, d is resolution parameter and A
is the weight matrix.
The weight matrix A controls the shape of optimal cluster (Bezdek et al.
1984).
Generally, it takes the following norm:
A ¼ I Euclidean Norm (9)
A ¼ D
1
i
Diagonal Norm (10)
A ¼ C
1
i
Mahalonobis Norm (11)
where I is the identity matrix, D
i
is the diagonal matrix having the diagonal element as
eigen values of covariance matrix and C
i
is given by:
C
i
¼
X
N
k¼1
ðx
k
c
i
Þðx
k
c
i
Þ
T
(12)
where
c
i
¼
X
N
k¼1
x
k
=N (13)
From the objective function of NC, the membership values of information class and
noise are given by Equations (14) and (15), respectively, while Equation (16) gives the
mean value of information classes.
l
ki
¼
X
c
j¼1
Dðx
k
; v
i
Þ
Dðx
k
;
v
j
Þ

1
m1
þ
Dðx
k
; v
i
Þ
d

1
m1
"#
1
; 1 i c (14)
l
k;cþ1
¼
X
c
j¼1
d
Dx
k
;
v
j

!
1
m1
þ1
2
4
3
5
1
(15)
8 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
v
i
¼
P
N
k¼1
l
ki
ðÞ
m
x
k
P
N
k¼1
l
ki
ðÞ
m
; 1 i c (16)
The noise class will always remain at a constant distance from all data point. This
constant distance is referred as noise distance and is represented by parameter δ, also
known as resolution parameter.Ifδ is assigned a very small value, then most of the
points will get classied as noise points, while for a large value of δ most of the points
will be classied into other information classes than the noise class (Dave
1991;
Rehm et al.
2007). Thus, the imp ortance of (c + 1)th class is to take the effect of
outliers for classication. The owchart of NC algorithm in supervised mode is shown
in Figure
3.
3.4. Receiver operating characteristic
The ROC, which is based on the NeymanPearson detection theory, is used for the
evaluation of detection performance in signal processing, (Chang et al.
2001; Chang
2010). It is used in the sense either object detected or not, which means it illustrate the
performance of a binary classier. The detection power of NeymanPearson curve is
measured by the area under its corresponding curve. The area is denoted by A
z
and
bounded between ½ and 1. For better detection, it should be closer to 1 (Wang et al.
2005). The 2-D ROC curve is plotted by the false alarm rate (FAR) on one axis
NC (Supervised Mode)
Select δ>0, fix m, c, δ, type of A-norm and training data
Compute the mean value from training data
Input image file(or for pixel k=1 to N)
Compute information class center
i
v
for class i=1 to c
Compute the distances from information class based on the A-norm
Calculate the membership
value of information classes
Write class proportion to file
Calculate the membership
value of noise classes
End
Membership=0.996
Increase value of δ
No
Yes
Figure 3. Flowchart for NC algorithm and optimization of δ.
Geocarto International 9
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
(x-axis) and true positive (TP) rate in another axis (y-axis). On the other hand, the 3-D
ROC curve is plotted by taking the FAR on x-axis, detection threshold (t)iny-axis and
TP rate in z-axis. The 2-D ROC can be used for hard decision produced by the
classier, whereas 3-D ROC for the soft decision (Wang et al.
2005).
The TP and FAR can be dened as follows:
TP ¼
Total number of target pixels detected as target
Total number of target pixels present in the sample
(17)
FAR ¼
Total number of background pixels detected as target
Total number of background pixels present in the sample
(18)
4. Results and discussion
4.1. Temporal variation of vegetation indices
The mean values of SR, NDVI, SAVI and EVI have been calculated from a training
sample consisting of 90 pixels of wheat. Figure
4 shows the mean values of NDVI,
SAVI and EVI, while Figure
5 shows for SR only. It is found that EVI shows the
variation of the indices value more distinctly in comparison with other indices. Further,
the indices values are higher during the owering, milking and dough, with maximum
value occurring around the dough stage.
It is observed that the temporal nature of all the indices curve is identical; however,
the variation can be found within different indices for wheat crop (Figures
4 and 5).
The slope of SR in Figure
5 is much steeper in comparison with all the other indices
curves shown in Figure
4; therefore, it is effective for identication of wheat crop due
to its high temporal variation.
0
0.5
1
1.5
2
NDVI
SAVI
EVI
Flowering
Milking
Dough
Maturity
Harvesting
Sowing
Indices Value
Figure 4. Variation of indices values for NDVI, SAVI and EVI for different phenological stages
of wheat.
10 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
4.2. Feature selection using the separability
The TD separability outputs were generated by varying the number of temporal data
from one to seven. In case of NDVI and SAVI, temporal data combinations of Three,
Four and Five have values equal to the saturation value of 2000. This means any of
the above combination of Three, Four and Five should yield good classication
result. However, it would be good if one combination could be identied to economise
the classication process.
From Table
2, it can be observed for Three, Four and Five data set combina-
tions, the date combinations 1,2,6, 1,2,3,6 and 1,2,3,5,6 ,respec tively, are common
for both NDVI and SAVI. Further, it is observed that all these data set combinations
have at least one date pertaining sowing, owering and maturity stage of wheat
phenology.
4.3. Optimization of resolution parameter (δ) and NC-based classication
For identifying wheat crop, the NC soft classication outputs have been generated by
varying the resolution parameter δ from 1 to 10
5
. The NDVI and SAVI corresponding
to the Three, Four and Five temporal dates, as selected in the Section
4.2, have
been taken for NC classication. The output of NC soft classication is represented in
terms of the fraction image corresponding to the wheat crop. The output membership
values of 75 known pixels have been plotted against the varying values of δ for both
temporal NDVI and SAVI, as shown in Figure
6.
It is observed that the membership value of wheat is near to zero when δ varies
from 1 to 10 and it increases rapidly when δ varies from 10 to 10
3
and thereafter it
increases slowly and then attains a constant value at a xed point, where the member-
ship value is close to 0.996. Any further increment in δ increases the membership val-
ues of non-interest classes which increases the noise in the outputs. Thus, value of
resolution param eter δ corresponding to a xed point yields the best result for wheat
classication. The optimised δ values for identication of wheat crop using MODIS
data are represented in Table
3. The NC soft classication outputs corres ponding to
these δ values are shown in Figure
7. A visual interpretation of the output of NC
0
2
4
6
8
10
12
14
16
SR
Flowering
Milking
Dough
Maturity
Harvesting
Sowing
Index Value
Figure 5. Variation of index value for SR for different phenological stages of wheat.
Geocarto International 11
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
Table 2. The TD separability outputs for different temporal spectral indices.
Data-set combination
SR NDVI SAVI EVI
Date combination TD Date combination TD Date combination TD Date combination TD
One 5 1943 4 1836 4 1836 4 1809
Two 1,4 1998 1,2 1999 1,6 1999 1,2 1994
Three 1,4,5 1999 1,2,6 2000 1,2,6 2000 1,2,3 1996
Four 1,2,4,5 1999 1,2,3,6 2000 1,2,3,6 2000 1,2,3,6 1997
Five 1,2,4,5,7 1999 1,2,3,5,6 2000 1,2,3,5,6 2000 1,2,3,4,6 1997
Six 1,2,3,4,5,7 1999 1,2,3,4,5,6 1999 1,2,3,4,5,6 1999 1,2,3,4,5,6 1997
Seven 1,2,3,4,5,6,7 1997 1,2,3,4,5,6,7 1998 1,2,3,4,5,6,7 1998 1,2,3,4,5,6,7 1996
12 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
(a) NDVI
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
Three
Four
Five
Membershipvalue
log
10
δ
NDVI
01 5234
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
012345
Three
Four
Five
Membershipvalue
log
10
δ
SAVI
(b) SAVI
Figure 6. Optimization of resolution parameter (δ) for wheat crop using MODIS data.
Table 3. Optimised value of log
10
δ for wheat crop MODIS data.
Data-set combination NDVI SAVI
Three 3.84 4.30
Four 4.30 4.30
Five 4.30 4.30
Three
Four
Five
NDVI
SAVI
Value of
µ
1
0
Dataset Combination
Figure 7. NC outputs for the wheat crop using MODIS data.
Geocarto International 13
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
classier (Figure 7) suggests that the wheat crop has been highlighted almost equally
for both the temporal indices.
From the Table
3, it can be observed that the average value of log
10
δ is 4.2 using
MODIS data for identication of wheat crop. This value is equivalent to the δ value of
1.6 × 10
4
and has been considered as an optimised value for identication of wheat
crop using the MODIS data.
4.4. Assessment of accuracy using the ROC
The assessment of accuracy has been done by computing FAR and TP values from the
NC classier outputs. It is observed that for a good detection (or identi cation), a low
value of FAR and a high value of TP is required. Here, wheat has been considered as
the target pixel, while anything different has been assigned as background. 120 sample
points were selected on the basis of eld trip and on the satellite data. Of these 120
sample points, 75 points were wheat and rest as background. For different membership
values ranging between 0 and 1 with an interval of 0.1, FAR and TP values were
calculated for both temporal NDVI and SAVI, as shown in Table
4.
The formulation of TP suggests that it is analogous to overall classication accu-
racy. There is no minimum acceptance rule for the overall classication accuracy,
which is universally applicable (Foody
2008). However, keeping minimum acceptance
value of 85% as per Andersons classication scheme, the threshold membership for
Three, Four and Five temporal data sets has been identied. It is observed that, for
TP = 85% and minimum FAR, the threshold membership value is 0.8 for all temporal
combination, except Three date combination of NDVI, for which it is 0.6 (Table
4).
Further, the 3-D ROC curve showing the variation of TP values with the FAR val-
ues along with the different membership threshold have been plotted for each spectral
index, as shown in Figure
8. The 2-D ROC curves derived from the 3-D ROC curves
are shown in Figure
9. For different date combination, the variation of TP with FAR
can be observed much clearly in 3-D curves. However, the 2-D ROC curves have been
used for the calculation of area under the ROC curves. The area under the 2-D ROC
Table 4. FAR and TP values for identication of wheat crop using NC-based classied temporal
indices of MODIS data.
Threshold
membership
NDVI SAVI
Three Four Five Three Four Five
FAR TP FAR TP FAR TP FAR TP FAR TP FAR TP
1.00 0.00 0.12 0.00 0.14 0.00 0.06 0.00 0.17 0.00 0.11 0.00 0.06
0.90 0.00 0.65 0.00 0.78 0.00 0.77 0.00 0.83 0.00 0.75 0.00 0.78
0.80 0.00 0.75 0.02 0.88 0.02 0.86 0.07 0.94 0.02 0.86 0.04 0.88
0.70 0.00 0.82 0.11 0.92 0.04 0.91 0.22 0.98 0.07 0.92 0.07 0.92
0.60 0.00 0.85 0.22 0.97 0.18 0.94 0.47 0.98 0.20 0.97 0.20 0.95
0.50 0.04 0.92 0.49 0.98 0.40 0.97 0.60 1.00 0.40 0.98 0.40 0.98
0.40 0.11 0.92 0.60 1.00 0.53 1.00 0.69 1.00 0.58 1.00 0.56 1.00
0.30 0.22 0.97 0.71 1.00 0.64 1.00 0.80 1.00 0.67 1.00 0.64 1.00
0.20 0.51 0.97 0.78 1.00 0.76 1.00 0.87 1.00 0.78 1.00 0.76 1.00
0.10 0.69 0.98 0.89 1.00 0.84 1.00 1.00 1.00 0.89 1.00 0.84 1.00
0.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00
14 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
curve has been calculated using the trape zoid rule. For each spectral index, the area
under the ROC curve (Table
5) shows the detection power of the method used for
detection. The larger the area better is the detection. From the Table
5, it is observed
(a) NDVI (b) SAVI
Figure 8. 3-D ROC curves for identication of wheat crop using NC-based classied temporal
indices of MODIS.
(a) NDVI
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
Three
Four
Five
FAR
TP
NDVI
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
Three
Four
Five
FAR
TP
SAVI
(b) SAVI
Figure 9. 2-D ROC curves for identication of wheat crop using NC-based classied temporal
indices of MODIS.
Table 5. Area under ROC curves for identication of wheat crop using NC-based classied
temporal indices of MODIS data.
Data set combination
Area under the ROC (AUROC)
NDVI SAVI
Three 0.968 0.982
Four 0.974 0.977
Five 0.970 0.974
Geocarto International 15
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
that the areas for ROC curves are above 0.5 for each index. This indicates that the
criterion of NeymanPearson detection curve is fullled by each index.
In case of SAVI, the highest area under the ROC curve is found corresponding to
the temporal date combination Three, a combination of sowing, owering and matu-
rity stages of wheat phenology. Further, the inclusion of milking stage, as in the Four
date combination in SAVI has increased the redundancy and hence decreas ed the accu-
racy marginally. The reason of this decrease is that SAVI is more sensitive to soil
information and during milking stage, soil is visible in the background as leaf area is
small at this phenological stage. When Five date temporal data is used, the accuracy
reduces. The reason for this fall in accuracy is that now two dates corresponding to
same phenology of maturity get included, leading to redundancy. Thus, it can be con-
cluded that SAVI temporal data set combination of Three date is more effective for
identication of wheat crop from MODIS data using the NC classication (Figure
10).
5. Conclusion
The phenological changes for every crop or vegetation type occur in a different manner.
The utility of these phenological changes can be easily veried for wheat identication
from MODIS temporal spectral index data sets. In this study, NC classication
approach was used for the classication of temporal spectral index data sets. The res-
olution parameter (δ) for wheat crop identication using MODIS data was found with
an average value of 1.6 × 10
4
for different spectral index. Amongst the indices used for
the study, NDVI has found that the Four date combination data set is more accurate
with high area under the ROC curve, while SAVI has produce d the high accuracy for
temporal date combination Three. Further, it was observed that, in each case, the three
phenological stages viz. sowing, owering and maturity data are common and hence
found to be more suitable for wheat crop identication. The highest accuracy was
found for the SAVI with temporal date Three, with an area equivalent to 0.982 under
the ROC curve. Thus, it can be concluded that the SAVI temporal data generated from
MODIS, corresponding to sowing, owering and maturity stage of wheat phenol ogy is
effective for the identication of wheat crop for the test site.
Acknowledgements
The authors are thankful to the reviewers for their critical comments and suggestions to improve
the manuscript.
0.88
0.89
0.9
0.91
0.92
0.93
0.94
0.95
0.96
0.97
0.98
0.99
1
NDVI
SAVI
AUROC
Figure 10. AUROC for wheat classication using NDVI and SAVI generated from MODIS data.
16 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
Disclosure statement
No potential conict of interest was reported by the authors.
References
Ahlawat JS, Sharma, PD. 2012. District disaster management plan. Panipat: Government of
India.
Bezdek JC, Ehrlich R, Full W. 1984. FCM: the fuzzy C-means clustering algorithm. Comput
Geosci. 10:191203.
Birth GS, McVey G. 1968. Measuring the color of growing turf with a reectance spectrora-
diometer. Agron J. 60:640643.
Bruzzone L, Serpico SB. 2000. A technique for feature selection in multiclass problems. Int J
Remote Sens. 21:549563.
Chang CI. 2010. Multiparameter receiver operating characteristic analysis for signal detection and
classication. IEEE Sens J. 10:423442.
Chang CI, Ren H, Chiang SS, Ifarraguerri A. 2001. An ROC analysis for subpixel detection.
IEEE 2001 International Geoscience and Remote Sensing Symposium; Jul 2428; Australia.
Congalton RG. 1991. A review of assessing the accuracy of classications of remotely sensed
data. Remote Sens Environ. 37:3546.
Congalton RG, Green K. 2009. Assessing the accuracy of remotely sensed data: principles and
practices. 2nd ed. Boca Raton (FL): Taylor & Francis Group.
Dave RN. 1991. Characterization and detection of noise in clustering. Pattern Recognit Lett.
12:657664.
Dave RN, Krishnapuram R. 1997. Robust clustering methods: a unied view. IEEE Trans Fuzzy
Syst. 5:270293.
Foody GM. 2000. Estimation of sub-pixel land cover composition in the presence of untrained
classes. Comput Geosci. 26:469478.
Foody GM. 2002. Status of land cover classication accuracy assessment. Remote Sens Environ.
80:185201.
Foody GM. 2008. Harshness in image classication accuracy assessment. Int J Remote Sens.
29:31373158.
Foody GM, Lucas RM, Curran PJ, Honzak M. 1997. Non-linear mixture modelling without
end-members using an articial neural network. Int J Remote Sens. 18:937953.
Houborg R, Soegaard H, Boegh E. 2007. Combining vegetation index and model inversion meth-
ods for the extraction of key vegetation biophysical parameters using Terra and Aqua MODIS
reectance data. Remote Sens Environ. 106:3958.
Huete AR, Liu HQ. 1994. An error and sensitivity analysis of the atmospheric- and soil-correct-
ing variants of the NDVI for the MODIS-EOS. IEEE Trans Geosci Remote Sens. 32:897
905.
Huete AR, Liu HQ, Batchily K, van Leeuwen W. 1997. A comparison of vegetation indices over
a global set of TM images for EOS-MODIS. Remote Sens Environ. 59:440451.
Huete A, Didan K, Miura T, Rodriguez EP, Gao X, Ferreira LG. 2002. Overview of the radio-
metric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ.
83:195213.
Ibrahim MA, Arora MK, Ghosh SK. 2005. Estimating and accommodating uncertainty through
the soft classication of remote sensing data. Int J Remote Sens. 26:29953007.
Jensen JR. 1986. Introductory digital image processing: a remote sensing perspective. New Jersey
(NJ): Prentice Hall.
Justice CO, Townshend J, Vermote EF, Masuoka E, Wolfe RE, Saleous N, Roy DP, Morisette JT.
2002. An overview of MODIS Land data processing and product status. Remote Sens Envi-
ron. 83:315.
Kanellopoulos I, Vars A, Wilkinson GG, Mégier J. 1992. Land cover discrimination in SPOT
HRV imagery using an arti
cial neural network: a 20-class experiment. Int J Remote Sens.
13:917924.
Kaushal P, Dubey JK, Sankhyan HP, Sharma D, Thakur J. 2009. Study of survival rate for one
year old plantation of 200809 in panipat district. New Delhi: National Afforestation and
Eco-Development Board (Ministry of Environment and Forests, GOI).
Geocarto International 17
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
Kerdiles H, Grondona MO. 1996. NOAA-AVHRR NDVI decomposition and sub-pixel classica-
tion using linear mixing in the Argentinean Pampa. Int J Remote Sens. 16:13031325.
Krishnapuram R, Keller JM. 1993. A possibilistic approach of clustering. IEEE Trans Fuzzy Syst.
1:429437.
Krishna Kumar K, Rupa Kumar K, Ashrit RG, Deshpande NR, Hansen JW. 2004. Climate
impacts on Indian agriculture. Int J Climatol. 24:13751393.
Kumar A, Ghosh SK, Dadhwal VK. 2006. Sub-pixel land cover mapping: SMIC system. ISPRS
International Symposium on Geospatial Databases for Sustainable Development; September
2730; Goa, India.
Lobell DB, Asner GP. 2004. Cropland distributions from temporal unmixing of MODIS data.
Remote Sens Environ. 93:412422.
Miyamoto S, Ichihashi H, Honda K. 2008. Algorithms for fuzzy clustering, studies in fuzziness
and soft computing, Vol. 229. Berlin: Springer; p. 6566.
Ohashi Y. 1984. Fuzzy clustering and robust estimation in 9th Meet. Hollywood Beach, FL: SAS
User Grp. Int.
Pan Y, Li L, Zhang J, Liang S, Zhu X, Sulla-Menashe D. 2012. Winter wheat area estimation
from MODIS-EVI time series data using the Crop Proportion Phenology Index. Remote Sens
Environ. 119:232242.
Potgieter AB, Apan A, Hammer G, Dunn P. 2010. Early-season crop area estimates for winter
crops in NE Australia using MODIS satellite imagery. ISPRS J Photogramm Remote Sens.
65:380387.
Pringle MJ, Denham RJ, Devadas R. 2012. Identication of cropping activity in central and
southern Queensland, Australia, with the aid of MODIS MOD13Q1 imagery. Int J Appl Earth
Obs Geoinf. 19:276285.
Rehm F, Klawonn F, Kruse R. 2007. A novel approach to noise clustering for outlier detection.
Soft Comput. 11:489494.
Rouse JW, Haas RH, Schell JA, Deering DW. 1973. Monitoring vegetation systems in the Great
Plains with ERTS. In: Third ERTS Symposium, NASA SP-351(1); p. 309317.
Running SW, Justice CO, Salomonson V, Hall D, Barker J, Kaufmann YJ, Strahler AH. 1994.
Terrestrial remote sensing science and algorithms planned for EOS/MODIS. Int J Remote
Sens. 15:35873620.
Sakamoto T, Yokozawa M, Toritani H, Shibayama M, Ishitsuka N, Ohno H. 2005. A crop phe-
nology detection method using time-series MODIS data. Remote Sens Environ. 96:366374.
Shalan MA, Arora MK, Ghosh SK. 2003. An evaluation of fuzzy classications from IRS 1C
LISS III imagery: a case study. Int J Remote Sens. 24:31793186.
Swain PH, Davis SM, editors. 1978. Remote sensing: the quantitative approach. New York (NY):
McGraw-Hill.
Tortora R. 1978. A note on sample size estimation for multinomial populations. Am Stat.
32:100102.
Verma U, Ruhal DS, Hooda RS, Yadav M, Khera AP, Singh CP, Kalubarme MH, Hooda LS.
2003. Wheat yield modelling using remote sensing and agro meteorological data in Haryana
state. J Indian Soc Agric Stat. 56:190198.
Wang J, Chang CI, Yang SC, Hsu GC, Hsu HH, Chung PC, Guo SM, Lee SK. 2005. 3D ROC
analysis for medical diagnosis evaluation. In: Proceedings of the 27th Annual International
Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), p. 75457548;
Sep 2005; Shanghai, China.
Wardlow BD, Egbert SL. 2010. A comparison of MODIS 250-m EVI and NDVI data for crop
mapping: a case study for southwest Kansas. Int J Remote Sens. 31:805830.
18 P. Upadhyay et al.
Downloaded by [PRIYADARSHI UPADHYAY] at 23:52 30 May 2015
... Various information can be obtained through observation of periodic satellite imagery in the same area. The obtained information could be the information about land use and land cover changes (Celik 2018), information about the phenology of specific vegetation (Upadhyay, Ghosh, and Kumar 2016), even information about the natural disaster phenomenon satellite imagery can provide that (Said et al. 2019). As a matter of fact, it is difficult to obtain images with radiometric consistency. ...
Conference Paper
Full-text available
Relative radiometric normalization (RRN) is one of the radiometric corrections for satellite imagery besides absolute radiometric normalization (ARN). In contrast to the absolute method that corrects various components such as atmospheric condition, earth-sun distance, illumination and viewing angle of satellite to find true reflectance, relative method does not find true reflectance but do the transformation of digital number to fit with reference image digital number or try to find common scale of digital number both of reference and target images instead. Several studies have conducted relative radiometric normalization to solve radiometric inconsistency issues by using pseudo-invariant features (PIFs). PIFs are reference objects that has an insignificant or near stable reflectance value change over time. This study is aimed to evaluate radiometric normalization result for Landsat 8 surface reflectance product that utilized Google Earth Engine platform for the computations. Normalization in this paper applied Multivariate Alteration Detection for PIFs selections. The selection of PIFs is based on data distribution of MAD result, the threshold values for selection are 10%, 15%, 20% and 25% of data distribution. Finally, the normalization used selected PIFs as sample data for calculate the slope and aspect of linear regression. On this study show the normalization result have the highest Pearson correlation value on 25% PIFs blue band which achieve 97.6% then the lowest Pearson correlation on 10% PIFs SWIR1 band which achieve 91.4%. The results suggest that developed approach have a potential solution to deal with inconsistency issues.
... [7][8][9][10][11] 或 FY [12] 卫 星遥感数据, 方法主要依据时间序列 NDVI(Normalized Difference Vegetation Index) [13] 或 EVI(Enhance Vegetation Index) [ [23] , 涉及水稻遥感制图 [24] 、 城市面积变化遥感监测 [25][26] 、 湿地动态监测 [ [ 5 ] 黄青,李丹丹,陈仲新,等.基于 MODIS 数据的冬小麦种植4 研究数据及处理 4.1 Landsat 遥感影像及处理 美国 Landsat 系列卫星由美国宇航局和美国地 质调查局共同管理。自 1972 年起, Landsat 系列卫 星陆续发射了 8 颗 (第 6 颗发射失败) , 目前 Landsat- 7 和 Landsat-8 在运行工作, 但 Landsat-7 自 2013 年 开始出现故障, 导致影像存在条带状损失, 其他卫 星已停止工作。本文以空间分辨率为 30 m 的 Land- sat-8、 Landsat-7 和 Landsat-5 卫星影像为数据源, 提 取河南省 2015 年和 2002 年冬小麦种植分布状况。 Landsat-5/7/8 的时间分辨率为 16 d, 受云雨天气影 响, 仅 1 年关键期内的遥感影像不能够完全覆盖全 省, 同时由于相近年份的冬小麦种植区域变化不 大, 因此将筛选影像的时间向前后推 1-2 年, ...
Article
Full-text available
在省域尺度上,冬小麦遥感识别中存在冬小麦物候不一致、地表环境复杂、数据处理复杂、遥感数据冗余、选择适当的分类样本困难、分类精度低等问题,而遥感数据云平台为解决这些问题提供了良好的数据基础和数据处理能力。以河南省为研究区,以谷歌地球引擎(Google Earth Engine)云平台为支撑,基于2015 年和2002 年前后年份河南省冬小麦识别关键期内的2296 景Landsat 遥感影像,采用NDVI重构增幅算法建立冬小麦大区域遥感快速制图模型,实现了2015 年和2002 年的河南省 冬小麦分布制图。结果表明:2015 年和2002 年冬小麦种植面积分别为56 055.79 km2和47 296.11 km2,与统计数据比,精度达到97%;2002-2015 年,河南省冬小麦种植分布存在明显变化,总体播种面积呈增加趋势,2015 年比2002 年增加8759.69 km2,增幅为18.52%。与传统计算机冬小麦制图方法相比,基于Google Earth Engine 云平台的数据处理和制图效率均获得千倍以上的提升。
... Second, different crops, including winter wheat, were mapped by comparing the similarity in time series profile between a target pixel and reference samples (Qin et al., 2015;Upadhyay et al., 2016;Zhang et al., 2019). Different similarity measures were used, such as time-weighted dynamic time warping (Maus et al., 2016;Dong et al., 2020). ...
Article
Full-text available
Winter wheat is one of the most important staple crops in the world. Accurate and timely information on the spatial distribution and temporal change of winter wheat is critical for food security and environmental sustainability. Multi-temporal images and time series data of medium resolution are widely used in winter wheat mapping. However, relatively long revisit times and image noise often result in a deficiency in full time series data. In this paper, a new spectral index, called the winter wheat index (WWI), using multi-temporal Landsat normalized difference vegetation index (NDVI) data of four key growth stages of winter wheat, was proposed to highlight and map winter wheat. Two distinctive NDVI contrasts, each consisting of an NDVI peak and trough, were identified and used in the WWI. The proposed index was evaluated through qualitative and quantitative analyses as well as winter wheat mapping, and compared with three state-of-the-art methods. To map winter wheat using WWI, a Monte Carlo cross validation procedure was adopted to determine the optimal thresholds of the WWI. Visual comparison showed that winter wheat was highlighted by higher WWI values, whereas other land cover types had lower WWI values. The experimental results from quantitative analysis indicated that WWI achieved better separability between winter wheat and other land cover types than the other comparative indices. The proposed WWI also produced more accurate winter wheat mapping results, compared with the state of art methods. Therefore, the proposed WWI provides a useful variable for winter wheat mapping, which reduced the dependence on full time series data and the use of noise images, and can be applied in other study areas.
... Moderate spatial resolution remotely sensed imagery suffers with mixed pixel problem, and problem of mixed pixels can be handled through the soft computing techniques. Upadhyay et al. (2016) took temporal MODIS-Terra MOD13Q1 data to identify wheat crop using noise clustering soft classification approach. Upadhyay et al. (2014) presented a novel soft classification approach to extract moist deciduous forest from MODIS temporal data, and the moist deciduous forest was identified by taking seven-date temporal MODIS data. ...
Article
Full-text available
In this study, temporal multispectral Sentinel-2A/B data have been used for identification of burnt paddy field using temporal Class-Based Sensor-Independent Indices Database using modified possibilitic fuzzy classification approach. The practice of stubble burning was found in Patiala site of Punjab State, and it was analysed and detected in temporal dataset of Sentinel 2A/B from 30 Sep 2018 to 19 Nov 2018. The result showed that stubble burning was started in a more frequent way from 20 Oct 2018 to 19 Nov 2018. The maximum stubble burnt was identified between 30 Oct 2018 and 19 Nov 2018. Stubble burnt paddy field area can be used in further estimation of pollution inlet to the atmosphere.
... The frequent remote sensing data with coarse resolution, such as NOAA/AVHRR (1.1 km), SPOT/VEGETATION (1.15 km), and TERRA/MODIS (250-1 000 m), provide a feasible tool to delineate vegetation phenology and monitor crop types (Pan et al. 2015). The rapid availability of these data is necessary for the accurate and operational crop acreage estimations and mapping over large regions (Xiao et al. 2005;Wardlow and Egbert 2008;Geerken 2009;Upadhyay et al. 2016). However, these types of images do not provide sufficiently detailed spatial change characteristics. ...
Article
Full-text available
Timely crop acreage and distribution information are the basic data which drive many agriculture related applications. For identifying crop types based on remote sensing, methods using only a single image type have significant limitations. Current research that integrates fine and coarser spatial resolution images, using techniques such as unmixing methods, regression models, and others, usually results in coarse resolution abundance without sufficient detail within pixels, and limited attention has been paid to the spatial relationship between the pixels from these two kinds of images. Here we propose a new solution to identify winter wheat by integrating spectral and temporal information derived from multi-resolution remote sensing data and determine the spatial distribution of sub-pixels within the coarse resolution pixels. Firstly, the membership of pixels which belong to winter wheat is calculated using a 25-m resolution resampled Landsat Thematic Mapper (TM) image based on the Bayesian equation. Then, the winter wheat abundance (acreage fraction in a pixel) is assessed by using a multiple regression model based on the unique temporal change features from moderate resolution imaging spectroradiometer (MODIS) time series data. Finally, winter wheat is identified by the proposed Abundance-Membership (AM) model based on the spatial relationship between the two types of pixels. Specifically, winter wheat is identified by comparing the spatially corresponding 10×10 membership pixels of each abundance pixel. In other words, this method takes advantage of the relative size of membership in a local space, rather than the absolute size in the entire study area. This method is tested in the major agricultural area of Yiluo Basin, China, and the results show that acreage accuracy (Aa) is 93.01% and sampling accuracy (As) is 91.40%. Confusion matrix shows that overall accuracy (OA) is 91.4% and the kappa coefficient (Kappa) is 0.755. These values are significantly improved compared to the traditional Maximum Likelihood classification (MLC) and Random Forest classification (RFC) which rely on spectral features. The results demonstrate that the identification accuracy can be improved by integrating spectral and temporal information. Since the identification of winter wheat is performed in the space corresponding to each MODIS pixel, the influence of differences of environmental conditions is greatly reduced. This advantage allows the proposed method to be effectively applied in other places.
... Temporal characteristics are also a widely used feature for crop mapping (Li et al., 2014;Siachalou et al., 2015;Jin et al., 2016). Time series image data, such as NOAA/AVHRR (1.1 km), SPOT/VEGETATION (1.15 km), and TERRA/MODIS (250 m-1000 m), can characterize crop phenology and are used to identify crop types based on temporal change information (Qin et al., 2015;Upadhyay et al., 2015). Pan et al. (2012) proposed a Crop Proportion Phenology Index (CPPI) following the concept of a Vegetation Index using the peaks and troughs of EVI time series curve to assess the quantitative relationship between the MODIS vegetation index time series and winter wheat crop area. ...
Article
Crop acreage and its spatial distribution are a base for agriculture related works. Current research combining medium and low spatial resolution images focuses on data fusion and unmixing methods. The purpose of the former is to generate synthetic fine spatial resolution data instead of directly solving the problem. In the latter, high-resolution data is only used to provide endmembers and the result is usually an abundance map rather than the true spatial distribution data. To solve this problem, this paper designs a conceptual model which divides the study area into different types of pixels at a MODIS 250 m scale. Only three types of pixels contain winter wheat, i.e., pure winter wheat pixels (PA), the mixed pixels comprising winter wheat and other vegetation (MA) and the mixed pixels comprising winter wheat and other crops (MB). Different strategies are used in processing them. (1) Within the pure cultivated land pixels, the Kullback–Leibler (KL) divergence is employed to analyze the similarity between unknown pixels and the pure winter wheat samples on the temporal change characteristics of NDVI. Further PA is identified. (2) For MA, a proposed reverse unmixing method is firstly used to extract the temporal change information of cultivated land components, after which winter wheat is identified from the cultivated land components as previously described. (3) For MB which only appears on the border of PA, a mask is created by expanding the PA and temporal difference is utilized to identify winter wheat under the mask. Finally, these three results are integrated at a TM scale with the aid of 25 m resolution land use data. We applied the proposed solution and obtained a good result in the main agricultural area of the Yiluo River Basin. The identified winter wheat planting acreage is 161,050.00 hm². The result is validated based on the five-hundred random validation points. Overall accuracy is 94.80% and Kappa coefficient is 0.85. This demonstrates that the temporal information reflecting crop growth is also an important indicator, and the KL divergence makes it more convenient in identifying winter wheat. This research provided a new perspective for the combination of low and medium spatial resolution remote sensing images. The proposed solution can also be effectively applied in other places and countries for the crop which has a clear temporal change characteristic that is different from others.
Thesis
In this study the Local Information methods have been deployed with possibilistic fuzzy based classifiers by adding spatial constraints, fuzzy factor, local similarity measure/pixel spatial attraction model and Markov Random Field (MRF) model in order to preserve image details and aiming to provide robustness to noise and outliers. Local Information correlates the information between a pixel and its adjacent pixels in the image space. This research work presents a unique Possibilistic c-Means with spatial constraints (PCM-S), Possibilistic Local Information c-Means (PLICM), Adaptive Possibilistic Local Information c-Means (ADPLICM), Modified Possibilistic c-Means with spatial constraints (MPCM-S), Modified Possibilistic Local Information c-Means (MPLICM), Adaptive Modified Possibilistic Local Information c-Means (ADMPLICM) algorithms in a supervised way. These algorithms can overcome the limitations of PCM, MPCM, PCM-MRF and MPCM-MRF algorithm by incorporating local information through local convolution. PCM-S and MPCM-S has been deployed by adding spatial constraints through local convolution (NR) and (𝛼) to supervise the effect of the neighbours term in conventional PCM and MPCM algorithms respectively, PLICM and MPLICM have been deployed by adding fuzzy factor (G) in conventional PCM and MPCM algorithms respectively to preserve more image details, ADPLICM and ADMPLICM have deployed by adding local similarity measures and pixel spatial attraction model (Sir) to sustain image details and aiming to provide robustness to noise in conventional PCM and MPCM algorithms respectively. Three experiments have been conducted to optimize, test and validate the proposed algorithms i.e. Mean Membership Difference (MMD), Root Mean Square Error (RMSE) and Fuzzy Error Matrix (FERM)/MIN-PROD respectively. MMD has been calculated on original classified image for independent accuracy to optimize the parameters of proposed algorithms for Landsat-8 and Formosat-2 satellite imagery, RMSE has been calculated between original and noisy classified image for Formosat-2 satellite imagery in which MPCM-S produces least RMSE. FERM and MIN-PROD composite operators have been used with respect to soft reference data. The result depicts that proposed PCM and MPCM classifier with local information can improve the fuzzy overall accuracy and fuzzy kappa by incorporating local information for remotely sensed imagery. Therefore, it was found that PCM with ADPLICM with Euclidean norm in possibilistic based fuzzy classifier and MPCM-S with ADPLICM classifier with Euclidean norm in modified possibilistic fuzzy classifier performs better as compared to other proposed algorithms. The MPCM-S algorithm after training and optimisation for temporal multispectral Sentinel�2A/B data has been used for identification of burnt paddy field using temporal class based sensor independent indices database. The practice of Stubble burning was found in Patiala Site of Punjab State and it is analysed and detected in temporal dataset of Sentinel 2A/B from 30 Sep, 2018 to 19 Nov, 2018. The result showed that stubble burning was started in more frequent way from 20 Oct, 2018 to 19 Nov, 2018. Keywords: Local Information, Image Classification, Temporal Indices, Mean Membership Difference, Fuzzy Error Matrix, Fuzzy Kappa and Stubble Burning.
Article
In this research work, a novel approach of ‘Individual Sample as Mean’ (ISM) based Noise Clustering has been proposed, where each sample is taken as an input parameter in training the model. When compared to the existing method which uses statistical mean for training, this proposed technique is far superior and robust, the efficiency of which has been demonstrated using Pigeon Pea crop mapping. The issue of spectral overlap of Pigeon Pea with other crops in vicinity is overcome by adopting a temporal approach. In order to fill the void in multi-temporal data availability, dual sensor approach was implemented. Different vegetation indices have been tested in reducing data dimensionality and the temporal datasets were optimized so as to capture the unique growth phenology of the Pigeon Pea crop. A new technique of ‘Class Based Sensor Independent – Modified Soil-Adjusted Vegetation Index 2 (CBSI-MSAVI2)’ has been proposed in this research work for the purpose of dimensionality reduction which ensures the maximum enhancement of target crop class in temporal domain. Based on an evaluation of classification results using Mean Membership Difference (MMD) method, the proposed ISM-Based NC appears to have produced superior results for Pigeon Pea since the test fields had membership values that were closer to those of the training fields. The MMD for ISM-Based NC was around 0.0013 whereas for the usual Mean-Based approach the value was at around 0.0071 respectively for Pigeon Pea crop fields. It was also noted that variance was zero in outputs generated by the ISM-based NC approach thereby proving the efficiency of the same in suppressing heterogeneity within the field.
Chapter
Full-text available
The quality of training data in terms of precision is instrumental in delivering a good performance for a supervised or a semi-supervised machine learning algorithm. The role of training data becomes more crucial for applications based on remote sensing data due to its distinct characteristics and limited amount of training data. In this paper, we present an effective approach for collection of precise training data from remote sensing images applied for a soft machine learning (softML) algorithm. The objective function of a fuzzy c-means algorithm was used to implement a softML algorithm driven by different spectral similarity measures for image classification and identification of wheat crop from remote sensing images. The spectral similarity measures selected for driving the softML algorithm were stochastic, deterministic as well as hybrid in nature. The training data for the soft computing algorithm were collected using manual and the proposed automatic mode. The manual training data were obtained by field survey of the study area, and the automatic training data were derived using a stochastic region growing algorithm. The precision of the training data obtained from both the modes were assessed by computing the classification accuracy for multiple classes using a fuzzy error matrix and analysis of membership distribution plots of the target wheat crop. Results from the experiments suggest that the proposed approach for automatic training data collection from remote sensing images results in an increment of the overall accuracy of classification for the softML algorithm. Also, the analysis of membership frequency distribution plots of the target wheat crop suggests greater precision of the training data collected by the proposed automatic mode. The increment in the frequency of the greater membership values and reduction in lower values indicated more accurate identification of the wheat crop using automatic mode of training the softML algorithm.
Article
Full-text available
Spectral-trend-agrometeorological yield models for four zones in Haryana state were developed using district level area weighted Normalized Difference Vegetation Index (NDVI), trend predicted yield and meteorological indices like Growing Degree Days (GDD), Temperature Difference (TD) and Rainfall Accumulated over critical growth phases of wheat. Meteo~ological indices calculated were integrated over seven phenological stages of wheat viz. (i) Crown Root Initiation Stage (ii) Tillering Stage (iii) Jointing Stage (iv) Flowering Stage (v) Milking Stage (vi) Dough Stage and (vii) Maturity stage. Districts in Haryana were grouped into four zones (clusters of districts) based on their physiography/soils and agro-climatic conditions. Trend predicted yields were obtained using historical yield time series data and spectro-trend yield relationship incorporated in the agro­ meteorological yield models. Remote sensing based model predicted yield were compared with Bureau of Economic & Statistics (BES) by computing Relative Deviation (RD%). The results indicated that the prediction capability for district level wheat yield has improved significantly using these zonal yield models.
Article
Full-text available
A method is described for determining the sample size required for a specified precision simultaneous confidence statement about the parameters of a multinomial population. The method is based on a simultaneous confidence interval procedure due to Goodman, and the results are compared with those obtained by separately considering each cell of the multinomial population as a binomial.
Article
Many methods of analysing remotely sensed data assume that pixels are pure, and so a failure to accommodate mixed pixels may result in significant errors in data interpretation and analysis. The analysis of data containing a large proportion of mixed pixels may therefore benefit from the decomposition of the pixels into their component parts. Methods for unmixing the composition of pixels have been used in a range of studies and have often increased the accuracy of the analyses. However, many of the methods assume linear mixing and require end-member spectra, but mixing is often non-linear and end-member spectra are difficult to obtain. In this paper, an alternative approach to unmixing the composition of image pixels, which makes no assumptions about the nature of the mixing and does not require end-member spectra, is presented. The method is based on an artificial neural network (ANN) and shown in a case study to provide accurate estimates of sub-pixel land cover composition. The results of this case study showed that accurate estimates of the proportional cover of a class and its areal extent may be made. It was also shown that there was a tendency for the accuracy of the unmixing to increase with the complexity of the network and the intensity of training. The results indicate the potential to derive accurate information from remotely sensed data sets dominated by mixed pixels.
Article
Concept and rationale with respect to the quantitative approach to remote sensing are examined, taking into account approaches used for conveying information in remote sensing data, details regarding the information obtained from multispectral data, and a system plan for the quantitative approach. Radiation and instrumentation in remote sensing are considered along with the fundamentals of pattern recognition in remote sensing, data-processing methods and systems, biological and physical considerations in applying computer-aided analysis techniques to remote sensor data, the application of the quantitative approach, and the acquisition of useful information from multispectral image data.
Article
Cropping activity has an importance that extends beyond farming communities, to governments, private industries, and to scientific research. We have developed a remote sensing-based method to detect arable cropping activity in central and southern Queensland, Australia, based on time series analysis of the NDVI layer of MODIS-Terra MOD13Q1 (250-m pixel) imagery. Local auto-regression was used to characterise phenological cycles in the NDVI time series. A random forest was then used to model three broad classes of agricultural vegetation (Grazing, Summer Cropping and Winter Cropping), as a function of phenological metrics and the local variance of the NDVI time series. The latter was found to be the most important distinguishing factor between the three classes. Pixel-by-pixel predictions of the random forest were obtained bi-annually for the study area over a 10-year period. Moderate agreement was seen between the predictions of the random forest and (independent) visual interpretation of Landsat imagery (Cohen's index of agreement, κc, of 0.59). We then demonstrated how the random forest's predictions can be used to define the consistency of cropping activity at the spatial scale of an individual farm property; when compared with (independent) visual interpretation of Landsat imagery the agreement was also moderate (κc = 0.68). In comparison with other crop-mapping approaches in the literature, our results have been achieved: (i) without restricting the method to annual NDVI time series; (ii) without assuming that the time series is regularly spaced and periodic; (iii) by considering only the ‘greening-up’ phase of the phenological cycles.
Article
A modified version of the fuzzy k-means clustering is proposed for gelling the robustness (the resistance) against a few outliers. Some numerical examples are presented for illustrating the intui­ tively appropriate interpretation the modified method provides, and it is pointed out that the estimator of the typical value (the population mean) obtained in one-cluster case is equivalent to a kind of M -estimator.
Article
One of the main phases in the development of a system for the classié cation of remote sensing images is the deé nition of an e Ä ective set of features to be given as input to the classié er. In particular, it is often useful to reduce the number of features available, while saving the possibility to discriminate among the diÄ erent land-cover classes to be recognized. This paper addresses this topic with reference to applications that involve more than two land-cover classes (multiclass problems). Several criteria proposed in the remote sensing literature are considered and compared with one another and with the criterion presented by the authors. Such a criterion, unlike those usually adopted for multiclass problems, is related to an upper bound to the error probability of the Bayes classié er. As the objective of feature selection is generally to identify a reduced set of features that minimize the errors of the classié er, the aforementioned property is very important because it allows one to select features by taking into account their e Ä ects on classié cation errors. Experiments on two remote sensing datasets are described and discussed. These experiments coné rm the e Ä ectiveness of the proposed criterion, which performs slightly better than all the others considered in the paper. In addition, the results obtained provide useful informa- tion about the behaviour of di Ä erent classical criteria when applied in multiclass cases.
Article
A single−beam spectrophotometer was used to measure the spectral reflectance properties of growing turf. From the data a two−wavelength reflectance ratio R745/R675 was developed, for an objective index of turf color. This ratio changed from 3.0 for light green turf color to 6.5 for dark green turf color. (visual rating of 4 to 10, respectively). A two−filter instrument (Ratiospect) was used to measure this index on eight samples of turf of three species. A correlation of 0.984 was obtained between the Ratiospect readings and a visual score of turf color. Please view the pdf by using the Full Text (PDF) link under 'View' to the left. Copyright © . .
Article
Land cover mapping is perhaps the most important application of remote sensing data. The abundance of mixed pixels (representing uncertainties in class allocation), particularly in coarse spatial resolution images, has always been known to lead to difficulties in producing accurate land cover classifications. Soft classification methods may help in quantifying uncertainties in areas of transition between various types of land cover. This study aims to estimate and accommodate uncertainties in all stages of a supervised classification process (i.e. training, allocation and testing) so as to produce accurate and meaningful land cover classifications. Three soft classification methods have been used—a probabilistic maximum likelihood classifier and the two classifiers based on fuzzy set theory (fuzzy c‐means and possibilistic c‐means). Uncertainty and accuracy measures based on a fuzzy error matrix have been adopted to evaluate each classifier. All of the classifiers show an increase in classification accuracy when uncertainty is appropriately accounted for in all stages of the supervised classification. In particular, the possibilistic c‐means classifier produced the highest map and individual class accuracy and has been found to be more robust to the existence of uncertainties in the datasets. The approach suggested in this paper can be used to generate accurate land cover maps, even in the presence of uncertainties in the form of mixed pixels in remote sensing images.