









































Pa
ge

 
1



Pa
ge

 
1

American Journal of  
Geospatial Technology (AJGT)

Monitoring of  LULC Changes and Forest Loss Using Geospatial Technique: A Case Study 
from Northern Region of  Bangladesh

Tahmina Afroz1,2*, Md. Giashuddin Miah1, Hasan Muhammad Abdullah1, Md. Rafiqul Islam3, Md. Mizanur Rahman4

Volume 1 Issue 2, Year 2022
ISSN: 2833-8006 (Online)

DOI: https://doi.org/10.54536/ajgt.v1i2.907
https://journals.e-palli.com/home/index.php/ajgt

Article Information ABSTRACT

Received: November 9, 2022

Accepted: November 14, 2022

Published: November 16, 2022

Monitoring changes in land use and land cover (LULC) is essential for determining the state 
of  the environment. This study is an attempt to assessing changes in LULC patterns and 
forest cover at northern region (Dinajpur district) of  Bangladesh for the periods 1989–1999, 
1999–2010, 2010–2020 and 1989-2020. Landsat satellite images were applied and supervised 
classification was done. There is a noticeable change found in LULC classes (Built-up, crop/
fallow, forest, homestead and water). The built-up and homestead increased by 210.36% 
and 134.71%; whereas the crop/fallow, forest, and water decreased by 12.27%, 74.99% and 
39.77%, respectively between 1989 to 2020. Forest was narrowed as majority of  forest land 
transferred to homestead (8089.02ha) and crop/fallow (5965.74ha) land in last three decades 
(1989-2020). The findings of  the study help in important policy implications for the sustain-
able LULC management in Dinajpur region of  Bangladesh.

Keywords
Land Transformation, LULC, 
Forest, Remote Sensing

1 Department of  Agroforestry and Environment, Bangabandhu Sheikh Mujibur Rahman Agricultural University, Gazipur 1706,  
  Bangladesh 
2 Department of  Agroforestry and Environmental Science, Sylhet Agricultural University, Sylhet 3100, Bangladesh
3 Department of  Agronomy, Bangabandhu Sheikh Mujibur Rahman Agricultural University, Gazipur 1706, Bangladesh
4 Department of  Soil Science, Bangabandhu Sheikh Mujibur Rahman Agricultural University, Gazipur 1706, Bangladesh
* Corresponding author’s e-mail: tahmina.smriti@gmail.com

INTRODUCTION
Changes in land use and land cover are regarded as 
some of  the most significant environmental problems 
facing the world today (Guan et al., 2011). Such changes 
are typically caused by human activity (for example, 
deforestation, urbanization, agricultural intensification, 
overgrazing, and subsequent land degradation), although 
natural forces can also play a role (Lambin, 1997). These 
anthropogenic changes may have a negative impact on 
the food security, with major social economic impacts 
for the region (Turner et al., 2007). Besides it also 
affects from local to global environment (Minale, 2013; 
Meshesha et al., 2016) with consequences for ecosystem 
functioning and ecosystem services (Meyer and Turner 
1994). Although the resulting changes in land cover are 
crucial for development (Dhinwa et al., 1992), planning 
and administration are thus required prior to any earth 
surface development (Nations, 1992). 
LULC alterations may have had substantial influences on 
forest landscapes as well (Chen et al., 2001). Deforestation, 
reforestation, afforestation, abandoning agricultural 
areas, urban sprawl, and conversion of  wooded lands into 
cropland and grazing are all examples of  LULC changes 
(Kilic et al., 2004). For ecological, social, and economic 
reasons, forest ecosystems are crucial like regulation of  
greenhouse gas emissions, control of  water resources, 
preservation of  soil, cycling of  nutrients, and diversity of  
species and genetics (Rao and Pant 2001). 
Biodiversity loss is mostly caused by changes in forest 
cover (Armsworth et al., 2004; Kilic et al., 2004). In the 
course of  time, the use of  GIS and remote sensing 
technology has increased the significance of  LULC change 
evaluation (Reid et al., 2000). It facilitates in obtaining 
precise and timely data on land use patterns (Arveti et 

al., 2016) and landscape transformations throughout 
the surface of  the Earth (Estoque & Murayama, 2015). 
Remote sensing is the process of  gathering information 
about certain ground-based objects without physically 
approaching them (Rajendran et al., 2020). GIS is a 
concept that divides the spatial area and assembles 
layers of  data into representations using guides and 3D 
scenes (Niu et al., 2020). Satellite images like Landsat 
images namely MSS, TM and ETM+ are used for LULC 
change detection in everywhere in the world (Akbari et 
al., 2006; Hereher, 2011; Baby, 2015; Chandrashekar et al., 
2018). When compared to point data gathered by in-situ 
survey devices, Landsat images with adequate spectral 
characteristics offer superior information on LULC 
changes (USGS, 2004; Kawakubo et al., 2011). 
The assessment of  land use and cover change has drawn 
the scientific and research community’s attention as the 
world’s population increases (Qian et al., 2007). Otherwise, 
it is crucial to evaluate how land use and cover have 
changed in order to understand the relationship between 
humans and nature. Monitoring the changes in land use 
and land cover (LULC) from the past to the present has 
become easier because to the collaboration of  remote 
sensing technologies and GIS tools (Chughtai et al., 2021). 
The supply of  resources including land, forests, and water 
is drastically decreasing in developing nations. However, 
data on the pace of  decline is frequently insufficient 
(FAO, 2009). 
Moreover, there seems to be a gap between the knowledge 
that is provided and the national decision-making process 
and logical planning. So, the current research objective 
was to monitor how the land use land cover have been 
changed over time using remote sensing and GIS 
technology. Concurrent with this aim is to identify and 

https://doi.org/10.54536/ajgt.v1i2.907
https://journals.e-palli.com/home/index.php/ajgt
mailto:tahmina.smriti%40gmail.com?subject=


Pa
ge

 
2

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

quantify the major LULC classes, to detect changes using 
land conversion matrix.

METHODOLOGY
Study Area
Dinajpur district encompasses between 25°10′ and 26°04′ 
north latitudes and 88°23′ and 89°18′ east longitudes 
which covers 3437.98 square kilometer area of  13 
upazilas. Irregular elevated Barind tract is found here 
and major rivers are the Dhepa, the Punarbhava, and the 
Atrai (Rana et al., 2022). There are two distinct seasons 
in the Northwestern region’s: a wet season from June to 
October and a dry season from November to March. The 

annual average rainfall is between 1500 and 3000 mm, 
with a regional average of  roughly 1583 mm (Murad & 
Islam, 2011). Due to its subtropical location, Bangladesh’s 
northwestern area experiences more extreme temperature 
changes. Maximum temperatures can reach as low as 25°C 
in January and as high as 38°C in April/May. August’s 
lowest temperature is 20°C, while January’s minimum 
ranges from 10 to 20°C (Islam & Miah, 1981). Due to the 
intense monsoon weather and diverse soil types, there is 
a wide range of  vegetation, from grassland to deciduous, 
mixed, and evergreen. The dominant crop in this area is 
rice (Reiman, 1993). Figure 1 represents the study area 
map of  Dinajpur district of  Bangladesh.

Figure 1:  Study area map of Maulvibazar district of Bangladesh.

Collection, processing and classification of  satellite 
images
By ordering ESPA (EROS Science Processing 
Architecture), a total of  eight Landsat satellite imageries 
(1989, 1999, 2010, and 2020) according to specific 
paths and rows were obtained from Earth Explorer 
(earthexplorer.usgs.gov) for the evaluation of  land use 
and land cover change of  Dinajpur over a 31-year period. 

As the image of  Dinajpur district fall under different 
path and row the two images of  same year were mosaic 
through using Q GIS. Table 1 summarizes the Landsat 
data employed in the study. The images were prepared 
through Arc GIS and Q GIS. Then cross tabulation 
matrix of  images between different year (1989-1999, 
1999-2010, 2010-2020 and 1989-2020) was done. 
Remote sensing data classification is a difficult process 

Table 1:  Characteristics of  Satellite Images
Sensor Path/Row Image acquisition date Resolution
Landsat 4-5 TM 138/42 13-Dec-89 30m
Landsat 4-5 TM 139/42 04-Dec-89 30m
Landsat 4-5 TM 138/42 23-Nov-99 30m
Landsat 4-5 TM 139/42 23-Dec-99 30m
Landsat 4-5 TM 138/42 14-Dec-10 30m
Landsat 4-5 TM 139/42 16-Dec-10 30m
Landsat 8 OLI 138/42 02-Dec-20 30m
Landsat 8 OLI 139/42 25-Dec-20 30m

for monitoring LULC change with proper classification, 
suitable quantity of  training sample, accuracy assessment 

by recognizing differences in the state of  a pixel or 
phenomenon (Lu & Weng, 2007; Viana et al., 2019). 

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
3

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

Table 2: Land use land cover classification scheme
Land use/cover 
types

Description

Built-up Industrial, residential, 
transportation, commercial 

Crop/Fallow Crop land, fallow lands, grass land
Homestead The home surrounded by tree, 

pond/crop
Forest Mainly sal forest 
Water River, streams, lakes, pond, River

The  LULC classification and mapping process includes 
the post classification accuracy assessment, which is 
used to evaluate the accuracy of  the classified maps 
(Manandhar, et al., 2009). The accuracy of  a classified map 
should not be less than 80% for accurate interpretability 
and classification (Anderson et al., 1976). In Dinajpur, 
for the years 1989, 1999, 2010 and 2020, the overall 
classification accuracy was 91%, 92%, 90% and 87%, 
and overall kappa statistics were 0.96, 0.94, 0.91 and 0.89, 
respectively. Table 3 represents the value and accuracy 
of  kappa statistic. The accuracy of  classification was 
acceptable.

Table 3: Value and accuracy of  kappa statistic
Kappa statistic Accuracy
<0 Less than Chance Agreement
0.01-0.20 Slight Agreement
0.21-0.40 Fair Agreement
0.41-0.60 Moderate Agreement
0.61-0.80 Substantial Agreement
0.81-0.99 Almost Perfect Agreement

Source: Viera and Garrett (2005)

RESULTS 
Land use land cover (LULC) map in Dinajpur
The LULC map was created to properly identify and 
adjust different classes in the research area. There were 

Figure 2: LULC map Dinajpur during 1989, 1999, 2010 and 2020.

For the time series analysis of  long-term classification, 
atmospherically corrected surface reflectance (SR) 
imageries are essential. In Q GIS multiband/layer 
stacking was done. All of  the multiband images were 
visualized using false color composite. In case of  Landsat 
4-7 TM imagery, RGB 4, 3, 2 and for Landsat 8 OLI 
imagery RGB 5, 4, 3 composites were used, respectively, 
to create false color. Dinajpur district has been chosen as 
an Area of  Interest (AOI) and a shape file was generated 
in Arc GIS, clipped in Q GIS. Accurate training inputs 
from composite images using Q GIS software were also 
generated. Cross-matching was done with spectral images 
through high-resolution Google Earth maps.  Finally, 
the image classification was done through R statistics 
package. The classes of  LULC were divided into five 
groups described in Table 2.

five LULC classes in the study area: built-up, crop/fallow, 
forest, homestead, and water. Figure 2 illustrates the 
classified LULC map for the study area.

Overall LULCC in last three decades 
LULCC is a substantial contributor to planetary change 

and has a profound effect on ecosystem. Based on the 
supervised classification approach it is evident that 
forest areas have diminished remarkably over the study 
area during the study period. In terms of  percentages, 
forest areas stand for 16125.66 ha (4.66%), 10119.33 ha 
(2.92%), 4255.92 ha (1.23%), and 4032.54 ha (1.16%) of  

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
4

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

the study area, respectively, during the years 1989, 1999, 
2010, and 2020 and it was a decreasing trend. The crop/
fallow areas were found to be 286025.4 ha (82.71%), 
267968.61 ha (77.49%), 2529286.31 ha (74.98%), and 
250921 ha (72.56%), respectively, during the years 1989, 
1999, 2010, and 2020. The crop/fallow area has also 
decreased considerably from 1989 to 2020. The water 

Figure 3: Land use land cover change in Dinajpur from1989 to 2020.

be 1943.28 ha, 2989.17 ha, 3541.77 ha, and 6031.26 ha, 
respectively (Figure 3). 

Assessment of  LULC change matrix from 1989 to 
1999
The conversion of  various land use types is known as 
land use and land cover change (LULCC), and it is 
the outcome of  intricate interactions between people 
and the natural world. Among the different land cover 
classes, the persistent area of  built-up, crop/fallow, 
forest, homestead and water were 143.28 ha, 236520.45 

ha, 2340.72 ha, 12671.55 ha and 1906.83 ha, respectively 
from 1989 to 1999. Forest was shrunk due to maximum 
forest land was converted to crop/fallow (7655.31 ha) 
and homestead (5596.56 ha). On the other hand, crop 
fallow was decreased by converting maximum 41101.83 
ha of  homestead. Built-up increased as most of  the crop/
fallow (1916.37 ha) transferred to built-up followed by 
homestead, water and forest. In case of  water, maximum 
water area converted to crop/fallow (3620.34 ha) (Figure 
4). In this decade crop/fallow, forest and water area were 
decreased by 6.31%, 37.25% and 50.78%, respectively. 

Figure 4: Sankey diagram showing Land use and land cover change matrix of  Dinajpur from 1989 to 1999.

bodies have reduced significantly over the study area 
from 1989 to 2020 although it was increased from 2010 
to 2020. The area covering water bodies are 7487.37 ha, 
3684.87 ha, 2780.01 ha, and 4509.54 ha, respectively, 
for the same time period. Otherwise, built-up area has 
increased gradually from 1989 to 2020. During the years 
1989, 1999, 2010, and 2020, built-up areas were found to 

Homestead and built-up increased by 53.82% and 
78.39%, respectively (Table 4). 3.4 Assessment of  LULC 
change matrix from 1999 to 2010
From the year 1999 to 2010, homestead and built-

up increased by 24.41% and 18.48%, respectively. In 
the mean while forest and water area were decreased 
by 57.94% and 24.55%, respectively (Table 4). Crop/
fallow was decreased from 267968.61 ha to 259286.31 

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
5

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

ha. Maximum area of  crop/fallow was converted to 
homestead (40182.48 ha) whereas the persistent area of  
crop/fallow was 223565.49 ha. The rate of  decrease of  
crop/fallow per year was 789.3 ha.  

Figure 5: Sankey diagram showing Land use and land cover change matrix of  Dinajpur from 1999 to 2010.

Assessment of  LULC change matrix from 2010 to 
2020
Between 2010 and 2020, built-up, homestead and water 
were increased by 70.28%, 5.75% and 62.21%, whereas 
crop/fallow and forest were decreased by 3.22% and 
5.24%, respectively (Table 4). Around 2044.26 ha of  

forest land transferred to homestead and 917.64 ha of  
forest land transferred to crop/fallow. Besides, majority 
of  crop/fallow land (36781.56 ha) was transferred to 
homestead. Furthermore, built-up was increased by 
converting maximum area of  crop/fallow and (3176.01 
ha) and homestead (2013.57 ha) to Built-up. In the 

Figure 6: Sankey diagram showing Land use and land cover change matrix of  Dinajpur from 2010 to 2020.

In case of  forest, maximum area of  forest transferred 
to homestead (4493.07 ha) and crop/fallow (3474.72 
ha) followed by others classes and the persistent area of  
forest was 1907.55 ha (Figure 5). 

meanwhile, homestead was increased by 436.95 ha 
per year. The persistent area of  built-up, crop/fallow, 
forest, homestead and water were 619.29 ha, 215777.79 
ha, 1166.94 ha, 39900.6 ha and 1703.7 ha, respectively 
(Figure 6).

Assessment of  LULC change matrix from 1989 to 
2020
Forest area has decreased drastically around 74.99% from 
1989 to 2020 (Table 4) due to vast homestead (8089.02ha) 
and crop/fallow (5965.74 ha) expansion. Within this time 

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
6

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

period, only 2105.01 ha has been added as forest area from 
crop/fallow. The overall rate of  reduction of  forest was 
390.10 ha per year (Figure 7). There has been a noticeable 
change in crop/fallow areas over the study area that it was 
decreased by 12.27% (Table 4) while majority of  crop/
fallow converted to homestead (52322.76 ha) (Figure 7). 

Figure 7: Shankey diagram showing Land use and land cover change matrix of  Dinajpur from 1989 to 2020.

Table 4: Relative changes in land use and land cover in Dinajpur

LULC Class
Change (%)
1989 -1999 1999-2010 2010-2020 1989-2020

Built-up 53.82 18.49 70.29 210.36
Crop/fallow -6.31 -3.24 -3.23 -12.27
Forest -37.25 -57.94 -5.25 -74.99
Homestead 78.39 24.41 5.75 134.71
Water -50.79 -24.56 62.21 -39.77

area indicates the growth rate has become more than 
double in recent years. Hence, such an unplanned built-
up and homestead trend will pose a significant threat to 
the environment and living conditions of  the study area. 

DISCUSSION
This study aimed to monitor long-term changes in LULC 
in northern region (Dinajpur district) of  Bangladesh. 
Satellite images were properly used to obtain the objectives. 
LULC was changed significantly having extreme loss of  
forest cover. The built-up area of  the Dinajpur region has 
expanded over time. Population increase was a primary 
driver of  built-up expansion. As a result of  urban growth, 
several locations in Bangladesh have seen considerable 
declines in wetlands, cultivated land, vegetation, and water 
bodies (Dewan and Yamaguchi, 2009). A lot of  factors 
contribute to the built-up expansion and massive flow of  
urban migration, including rapid and unplanned urban 

movement, the concentration of  better employment 
in city areas, and biased placement of  municipal 
infrastructure. Contemporary development of  built up 
impacting the ecology, environment, and biodiversity in 
the surrounding region (Al Rakib et al., 2020; Chakroborty 
et al., 2020; Rahman et al., 2018). Crop/fallow land may 
be termed as agricultural land was shrinking in the study 
area year after year. Maximum crop/fallow land was 
transformed to the homestead. The agricultural land in 
Bangladesh is reducing at 69,000 hectares per annum as a 
result of  increasing industry, unplanned urbanization, and 
an increase in in rural communities. (Khan, 2020). The 
rapid conversion of  agricultural land to non-agricultural 
uses threatens crop production and food security in 
the country (PC, 2009). According to studies, the rate 
of  conversion of  agricultural lands to non-agricultural 
uses is comparatively faster in the twenty-first century 
due to high economic expansion and infrastructural 

The total loss of  water body from 1990 to 2020 is 2977.83 
ha which accounts for a reduction of  about 39.77% over 
the period (Table 4). The growth of  homestead area 
between 1989 to 2020 was about 1486.6 ha/year and the 
persistent area of  homestead was 16506.9 (Figure 7). 
The rate of  expansion of  homestead area over the study 

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
7

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

development (Hasan et al. 2013). The loss of  agricultural 
land has resulted in the degradation of  biodiversity and 
ecosystem services also (Kafy, et al., 2021). Homesteads 
in the Dinajpur region expanded fast, with 26.41 million 
families in Bangladesh utilizing 0.748 million hectares of  
land (Mannan, 2013). 
Forest land in Dinajpur was rapidly declining. The findings 
are consistent with Bangladesh having one of  the highest 
rates of  deforestation in South Asia, at 2600 hectares per 
year (Mac Dicken, 2015; Poffen berger, 2000) and this 
forest loss related impacts on ecosystem health (Halkos 
and Zisiadou, 2018). Deforestation and other disturbances 
cause the world’s forests to release an average of  8.1 billion 
metric tonnes of  carbon dioxide into the atmosphere each 
year. Southeast Asian forests have collectively become a 
net source of  carbon emissions during the last 20 years 
as a result of  deforestation for plantations, uncontrolled 
fires, and peat soil drainage (Nancy and colleagues, 
2021). Biophysical and socioeconomic factors contribute 
to the conversion of  forest to agricultural land and the 
conversion of  agricultural land to forest in both Southeast 
Asia and South Asia (Xu et al., 2019). According to The 
International Union for Conservation of  Nature (IUCN, 
2005), the primary accelerator of  forest decline is human 
activities. Wasige et al. (2015) identified that the forest 
clearing occurring every year is mainly due to agriculture. 
According to Abdullah et al. (2019), forest in Gazipur 
region of  Bangladesh have decreased by 62.67 percent. 
In Bangladesh, naturally regenerating forest was 1845000 
ha during 1990 to 2000, but it reduced to 1816000 ha in 
2010, again reduced to 1725000 ha between 2015-2020 
(FRA 2020) is a major threat for future.  

CONCLUSION
LULC change trends can be assessed and mapped to 
serve as a foundation for long term planning, monitoring, 
and protective actions. Besides, in order to manage and 
grow forest ecosystems sustainably, it is crucial to keep 
track of  changes in forest cover and understand how it 
changes over time. Very high-resolution multispectral 
satellite images, however, may provide more information 
about changes in the region. The LULC change patterns 
were found to differ significantly between the Landsat 
data for the years 1989, 1999, 2010, and 2020 after LULC 
analyses. Built-up and homestead increased every decade 
from 1989 to 2020. On the other hand, crop/fallow and 
forest was narrowed down day by day. Forest land was 
mainly shrinking for maximum transformation of  land 
to homestead and crop/fallow land. So, Stopping the 
growth of  built- up and homestead areas that transform 
agricultural land and forest are all a part of  a broader 
strategy to save this significant geographic and delicate 
environment. This research was conducted in small scale, 
but it should be done in broader aspect and also to predict 
the future land use, method like CA-Markov chain can be 
applied. Thus, the study of  planetary land use patterns is 
critical for dealing with global climate change, achieving 
sustainable development and proper planning of  natural 

resources in future.

Acknowledgments 
The authors are thankful to the Ministry of  Science and 
Technology for funding this research through the NST 
fellowship. We are also grateful to the United States 
Geological Survey (USGS) for providing the Landsat 
archives.

Conflicts of  Interest
The authors declare no conflicts of  interest.

REFERENCES
Abdullah, H. M., Islam, I., Miah, M. G., & Ahmed, Z. 

(2019). Quantifying the spatiotemporal patterns of  
forest degradation in a fragmented, rapidly urbanizing 
landscape: a case study of  Gazipur, Bangladesh. Remote 
Sensing Applications: Society and Environment, 13, 457-
465.

Akbari, M., Mamanpoush, A. R., Gieske, A., Miranzadeh, 
M., Torabi, M., & Salemi, H. R., (2006). Crop and land 
cover classification in Iran using Landsat 7 imagery. 
International Journal of  Remote Sensinag, 27(19), 4117-
4135.

Al Rakib A., Akter, K. S., Rahman, M. N., Arpi, S., 
Kafy, A-A., (2020). Analyzing the pattern of  land 
use land cover change and its impact on land 
surface temperature: a remote sensing approach in 
Mymensingh, Bangladesh. 1st Int. Student Res. Conf. 
2020

Anderson, J. R., (1976). A land use and land cover 
classification system for use with remote sensor data 
(Vol. 964). US Government Printing Office.

Armsworth, P. R., Kendall, B. E., & Davis, F. W. 
(2004). An introduction to biodiversity concepts 
for environmental economists. Resource and Energy 
Economics, 26, 115–136.

Arveti, N., Etikala, B., & Dash, P. (2016). Land use/
Land cover analysis based on various comprehensive 
geospatial data sets: A case study from Ananthapuramu 
area, South India. Advances in Remote Sensing, 5(2), 73–
82. https://doi.org/10.4236/ars.2016.52006 

Baby, S., (2015). Monitoring the coastal land use land 
cover changes (LULCC) of  Kuwait from spaceborne 
LANDSAT sensors.

Chakroborty, S., Al Rakib, A., Al Kafy, A., (2020). 
Monitoring water quality based on community 
perception in the Northwest Region of  Bangladesh, 
in: 1st International Student Research Conference- 2020. 
Dhaka

Chandrashekar, A., Somanath, T., Praveen Kumar, R., 
Vikas, K., & Saumitra M., (2018). Changing land 
trajectories: A case study from India using a remote 
sensing based approach. European Journal of  Geography, 
7(2), 61–71. http://www.eurogeographyjournal.
eu/ar ticles/04_CHANGING%20LAND%20
TRAJECTORIES%20A%20CASE%20STUDY%20
FROM%20INDIA%20USING%20REMOTE%20

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
8

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

SENSING%20BASED%20APPROACH.pdf
Chen, L., Wang, J., Fu, B., & Qiu, Y., (2001). Land-use 

change in a small catchment of  northern Loess Plateau, China. 
Agriculture, Ecosystems and Environment, 86, 163–172.

Chughtai, A. H., Abbasi, H., & Karas, I. R., (2021). A 
review on change detection method and accuracy 
assessment for land use land cover. Remote Sensing 
Applications: Society and Environment, 22, 100482.

Dewan, A. M., & Yamaguchi, Y., (2009). Using remote 
sensing and GIS to detect and monitor land use 
and land cover change in Dhaka Metropolitan of  
Bangladesh during 1960–2005. Environmental monitoring 
and assessment, 150(1), 237-249.

Dhinwa, P., Pathan, S., Sastry, S., Rao, M., Majumder, K., 
Chotani, M. & Sinha, R., (1992). Land use change 
analysis of  Bharatpur district using GIS. J. Indian Soc. 
Rem. Sens. 20 (4), 237–250. 

Estoque, R. C., & Murayama, Y., (2015). Intensity and 
spatial pattern of  urban land changes in the megacities 
of  Southeast Asia. Land Use Policy, 48, 213–222. 
https://doi.org/10.1016/j.landusepol.2015.05.017

FAO. Sustaining Communities, Livestock and Wildlife; 
FAO: Rome, Italy, 2009.

FRA, (2020). GLOBAL FOREST RESOURCES 
ASSESSMENT 2020. Country Report Bangladesh 
Rome, 2020.from 29 October to 10 November 2001, 
addendum, 2.

Guan, D., Li, H., Inohae, T., Su, W., Nagaie, T., & Hokao, 
K., (2011). Modeling urban land use change by the integration 
of  cellular automaton and Markov model. Ecological 
Modelling, 222, 3761-3772.

Halkos, G. & Zisiadou, A. (2018). Relating environmental 
performance with socioeconomic and cultural factors. 
Environ. Econ. Policy Stud. 20(1), 69–88.

Hasan, M. N., Hossain, M. S., Bari, M. A., & Islam, M. 
R., (2013). Agricultural land availability in Bangladesh. 
Dhaka: Soil Resource Development Institute.

Hereher, M. E., (2011). Mapping coastal erosion at 
the Nile Delta western promontory using Landsat 
imagery. Environmental Earth Sciences, 64(4), 1117-1125.

Islam, M. A., Miah, M. M. Bangladesh in maps. Univ. of  
Dacca (1981). 77

IUCN. Rapid Environmental Appraisal of  Developments 
in and Around Murree Hills; IUCN Pakistan: Karachi 
City, Pakistan, 2005. 

Kafy, A. A., Naim, N. H., Khan, M. H. H., Islam, M. A., 
Al Rakib, A., Al-Faisal, A., & Sarker, M. H. S., (2021). 
Prediction of  urban expansion and identifying its 
impacts on the degradation of  agricultural land: a 
machine learning-based remote-sensing approach 
in Rajshahi, Bangladesh. In Re-envisioning Remote 
Sensing Applications (85-106). CRC Press.

Kawakubo, F. S., Morato, R. G., Nader, R. S., & Luchiari, 
A., (2011). Mapping changes in coastline geomorphic 
features using Landsat TM and ETM+ imagery: 
Examples in southeastern Brazil. International journal 
of  remote sensing, 32(9), 2547-2562.

Khan, S., (2020., November 11). Worries over farmland 

depletion. The Financial Express. Retrieved December 
19, 2021, from https://thefinancialexpress.com.bd/
views/worries-over-farmland-depletion-1605105883

Kilic, S., Evrendilek, F., Berberoğlu, S., & Demirkesen, 
A. C., (2004). Environmental monitoring of  land-
use and land-cover changes in Amik Plain, Turkey. 
In Geo-Imagery Bridging Continents, XXth ISPRS 
Congress. Istanbul, Turkey.

Lambin, E. F., (1997). Modelling and monitoring land-
cover change processes in tropical regions. Progress in 
Physical Geography, 21, 375-393.

Lu, D., & Weng, Q., (2007). A survey of  image 
classification methods and techniques for improving 
classification performance. International Journal 
of  Remote Sensing, 28(5), 823–870. https://doi.
org/10.1080/01431160600746456

MacDicken, K. G., (2015). Global forest resources 
assessment 2015: what, why and how?. Forest Ecology 
and Management, 352, 3-8.

Manandhar, R., Odeh, I. O. A., & Acnev, T., (2009). 
Improving the accuracy of  land use and land cover 
classification of  Landsat data using post-classification 
enhancement. Remote Sensing, 1, 330–344.

Mannan, M., (2013). Plant biodiversity in the Hoar 
homesteads of  Bangladesh. International Research 
Journal of  Applied Life Sciences, 2(5).

Meshesha, T. W.; Tripathi, S. K. & Khare, D. M., (2016). 
Analyses of  land use and land cover change dynamics 
using GIS and remote sensing during 1984 and 2015 
in the Beressa Watershed Northern Central Highland 
of  Ethiopia. Model. Earth Syst. Environ. 2, 1–12.

Meyer W. B. and Turner B.  L. II., (1994). Changes in 
land use and land cover: a global perspective, Cambridge: 
Cambridge University Press, 549.

Minale, A. S., (2013). Retrospective analysis of  land 
cover and use dynamics in Gilgel Abbay Watershed 
using GIS and remote sensing technique, Northwestern 
Ethiopia. Int. J. Geosci. 4, 1003–1008.

Murad, H., & Islam, A. K. M. S., (2011, January). Drought 
assessment using remote sensing and GIS in north-
west region of  Bangladesh. In Proceedings of  the 3rd 
International conference on water & flood management, 797-
804.

Nancy Harris and David Gibbs., (January 21, 2021). 
Forests Absorb Twice As Much Carbon As They 
Emit Each Year.

Nations, U., (1992). Agenda 21. United Nations 
Conference on Environment & Development Rio de 
Janeiro, Brazil. 

Niu, B., Lan, J., Shao, Y., & Zhang, H., (2020). A dual-
branch extraction and classification method under 
limited samples of  hyperspectral images based on 
deep learning. Remote Sensing, 12(3), 536.

PC., (2009). Steps towards change. Planning Commission, 
National Strategy for Accelerated Poverty Reduction II 
(Revised). Dhaka: Government of  the People’s 
Republic of  Bangladesh.

Poffen berger, M., (2000). Communities and forest 

https://journals.e-palli.com/home/index.php/ajgt


Pa
ge

 
9

https://journals.e-palli.com/home/index.php/ajgt

Am. J. Geo Spat. Technol. 1(2) 1-9, 2022

management in South Asia. IUCN.
Qian, J., Zhou, Q., Hou, Q., (2007). Comparison of  pixel-

based and object-oriented classification methods 
for extracting built-up areas in arid zone. In: Paper 
Presented at the ISPRS Workshop on Updating Geo-
Spatial Databases with Imagery & the 5th ISPRS 
Workshop on DMGISs.

Rahman, M. S., Mohiuddin, H., Kafy, A. A., Sheel, P. K., 
& Di, L., (2019). Classification of  cities in Bangladesh 
based on remote sensing derived spatial characteristics. 
Journal of  Urban Management, 8(2), 206-224.

Rajendran, G. B., Kumarasamy, U. M., Zarro, C., 
Divakarachari, P. B., & Ullo, S. L., (2020). Land-use 
and land-cover classification using a human group-
based particle swarm optimization algorithm with an 
LSTM Classifier on hybrid pre-processing remote-
sensing images. Remote Sensing, 12(24), 4135.

Rana, M. S. P., Hossain, M. A., & Nasher, N. R., (2022). 
Identification of  groundwater potential zone using 
geospatial techniques of  agriculture dominated 
area in Dinajpur district, Bangladesh. Environmental 
Challenges, 7, 100475.

Rao, K. S., & Pant, R., (2001). Land use dynamics and 
landscape change pattern in a typical micro watershed 
in the mid elevation zone of  central Himalaya, India. 
Agriculture, Ecosystems and Environment, 86, 113–123.

Reid, R. S., Kruska, R. L., Muthui, N., Taye, A., Wotton, 
S., Wilson, C.J., Mulatu, W. J. L. E., (2000). Land-use 
and land-cover dynamics in response to changes in 

climatic, biological and socio-political forces: the case 
of  southwestern Ethiopia, 15(4), 339–355.

Reimann, K. U., & Hiller, K., (1993). Geology of  
Bangladesh.

Turner, B. L., Lambin, E. F., & Reenberg, A., (2007). 
The emergence of  land change science for global 
environmental change and sustainability. PNAS, 104, 
20666-20671.

USGS., (2004). Phase 2 gap-fill algorithm: SLC-off  
gap-filled products gap-fill algorithm methodology. 
Retrieved from http://www.landsat.usgs.gov/
documents/L7SLCGapFilled Method.pdf  (accessed 
20.01.2015).

Viana, C. M., Oliveira, S., Oliveira, S. C., & Rocha, J., 
(2019). Land use/land cover change detection and 
urban sprawl analysis. Spatial Modeling in GIS and 
R for Earth and Environmental Sciences. https://doi.
org/10.1016/b978-0-12-815226-3.00029-6

Viera, A. J., & Garrett, J. M., (2005). Understanding 
interobserver agreement: the kappa statistic. Fam med, 
37(5), 360-363.

Wasige, J. E.; Groen, T. A.; Smaling, E.; Jetten, V., 
Monitoring basin-scale land cover changes in Kagera 
Basin of  Lake Victoria using ancillary data and remote 
sensing. Int. J. Appl. Earth Obs. Geoinf., 21, 32–42.

Xu, X., Jain, A. K., & Calvin, K. V., (2019). Quantifying 
the biophysical and socioeconomic drivers of  changes 
in forest and agricultural land in South and Southeast 
Asia. Global change biology, 25(6), 2137-2151.

https://journals.e-palli.com/home/index.php/ajgt

