RETRACTED ARTICLE: Multi-temporal image analysis for LULC classification and change detection

Statement of Retraction We, the Editor and Publisher of the journal European Journal of Remote Sensing, have retracted the following articles that were published in the Special Issue titled “Remote Sensing in Water Management and Hydrology”: Marimuthu Karuppiah, Xiong Li & Shehzad Ashraf Chaudhry (2021) Guest editorial of the special issue “remote sensing in water management and hydrology”, European Journal of Remote Sensing, 54:sup2, 1-5, DOI: 10.1080/22797254.2021.1892335 Jian Sheng, Shiyi Jiang, Cunzhu Li, Quanfeng Liu & Hongyan Zhang (2021) Fluid-induced high seismicity in Songliao Basin of China, European Journal of Remote Sensing, 54:sup2, 6-10, DOI: 10.1080/22797254.2020.1720525 Guohua Wang, Jun Tan & Lingui Wang (2021) Numerical simulation of temperature field and temperature stress of thermal jet for water measurement, European Journal of Remote Sensing, 54:sup2, 11-20, DOI: 10.1080/22797254.2020.1743956 Le Wang, Guancheng Jiang & Xianmin Zhang (2021) Modeling and molecular simulation of natural gas hydrate stabilizers, European Journal of Remote Sensing, 54:sup2, 21-32, DOI: 10.1080/22797254.2020.1738901 Tianyi Chen, Lu Bao, Liu Bao Zhu, Yu Tian, Qing Xu & Yuandong Hu (2021) The diversity of birds in typical urban lake-wetlands and its response to the landscape heterogeneity in the buffer zone based on GIS and field investigation in Daqing, China, European Journal of Remote Sensing, 54:sup2, 33-41, DOI: 10.1080/22797254.2020.1738902 Zhiyong Wang (2021) Research on desert water management and desert control, European Journal of Remote Sensing, 54:sup2, 42-54, DOI: 10.1080/22797254.2020.1736953 Ji-Tao Li & Yong-Quan Liang (2021) Research on mesoscale eddy-tracking algorithm of Kalman filtering under density clustering on time scale, European Journal of Remote Sensing, 54:sup2, 55-64, DOI: 10.1080/22797254.2020.1740894 Wei Wang, R. Dinesh Jackson Samuel & Ching-Hsien Hsu (2021) Prediction architecture of deep learning assisted short long term neural network for advanced traffic critical prediction system using remote sensing data, European Journal of Remote Sensing, 54:sup2, 65-76, DOI: 10.1080/22797254.2020.1755998 Yan Chen, Ming Tan, Jiahua Wan, Thomas Weise & Zhize Wu (2021) Effectiveness evaluation of the coupled LIDs from the watershed scale based on remote sensing image processing and SWMM simulation, European Journal of Remote Sensing, 54:sup2, 77-91, DOI: 10.1080/22797254.2020.1758962 Ke Deng & Ming Chen (2021) Blasting excavation and stability control technology for ultra-high steep rock slope of hydropower engineering in China: a review, European Journal of Remote Sensing, 54:sup2, 92-106, DOI: 10.1080/22797254.2020.1752811 Yufa He, Xiaoqiang Guo, Jun Liu, Hongliang Zhao, Guorong Wang & Zhao Shu (2021) Dynamic boundary of floating platform and its influence on the deepwater testing tube, European Journal of Remote Sensing, 54:sup2, 107-116, DOI: 10.1080/22797254.2020.1762246 Kai Peng, Yunfeng Zhang, Wenfeng Gao & Zhen Lu (2021) Evaluation of human activity intensity in geological environment problems of Ji’nan City, European Journal of Remote Sensing, 54:sup2, 117-121, DOI: 10.1080/22797254.2020.1771214 Wei Zhu, XiaoSi Su & Qiang Liu (2021) Analysis of the relationships between the thermophysical properties of rocks in the Dandong Area of China, European Journal of Remote Sensing, 54:sup2, 122-131, DOI: 10.1080/22797254.2020.1763205 Yu Liu, Wen Hu, Shanwei Wang & Lingyun Sun (2021) Eco-environmental effects of urban expansion in Xinjiang and the corresponding mechanisms, European Journal of Remote Sensing, 54:sup2, 132-144, DOI: 10.1080/22797254.2020.1803768 Peng Qin & Zhihui Zhang (2021) Evolution of wetland landscape disturbance in Jiaozhou Gulf between 1973 and 2018 based on remote sensing, European Journal of Remote Sensing, 54:sup2, 145-154, DOI: 10.1080/22797254.2020.1758963 Mingyi Jin & Hongyan Zhang (2021) Investigating urban land dynamic change and its spatial determinants in Harbin city, China, European Journal of Remote Sensing, 54:sup2, 155-166, DOI: 10.1080/22797254.2020.1758964 Balaji L. & Muthukannan M. (2021) Investigation into valuation of land using remote sensing and GIS in Madurai, Tamilnadu, India, European Journal of Remote Sensing, 54:sup2, 167-175, DOI: 10.1080/22797254.2020.1772118 Xiaoyan Shi, Jianghui Song, Haijiang Wang & Xin Lv (2021) Monitoring soil salinization in Manas River Basin, Northwestern China based on multi-spectral index group, European Journal of Remote Sensing, 54:sup2, 176-188, DOI: 10.1080/22797254.2020.1762247 GN Vivekananda, R Swathi & AVLN Sujith (2021) Multi-temporal image analysis for LULC classification and change detection, European Journal of Remote Sensing, 54:sup2, 189-199, DOI: 10.1080/22797254.2020.1771215 Yiting Wang, Xianghui Liu & Weijie Hu (2021) The research on landscape restoration design of watercourse in mountainous city based on comprehensive management of water environment, European Journal of Remote Sensing, 54:sup2, 200-210, DOI: 10.1080/22797254.2020.1763206 Bao Qian, Cong Tang, Yu Yang & Xiao Xiao (2021) Pollution characteristics and risk assessment of heavy metals in the surface sediments of Dongting Lake water system during normal water period, European Journal of Remote Sensing, 54:sup2, 211-221, DOI: 10.1080/22797254.2020.1763207 Jin Zuo, Lei Meng, Chen Li, Heng Zhang, Yun Zeng & Jing Dong (2021) Construction of community life circle database based on high-resolution remote sensing technology and multi-source data fusion, European Journal of Remote Sensing, 54:sup2, 222-237, DOI: 10.1080/22797254.2020.1763208 Zilong Wang, Lu Yang, Ping Cheng, Youyi Yu, Zhigang Zhang & Hong Li (2021) Adsorption, degradation and leaching migration characteristics of chlorothalonil in different soils, European Journal of Remote Sensing, 54:sup2, 238-247, DOI: 10.1080/22797254.2020.1771216 R. Vijaya Geetha & S. Kalaivani (2021) A feature based change detection approach using multi-scale orientation for multi-temporal SAR images, European Journal of Remote Sensing, 54:sup2, 248-264, DOI: 10.1080/22797254.2020.1759457 LianJun Chen, BalaAnand Muthu & Sivaparthipan cb (2021) Estimating snow depth Inversion Model Assisted Vector Analysis based on temperature brightness for North Xinjiang region of China, European Journal of Remote Sensing, 54:sup2, 265-274, DOI: 10.1080/22797254.2020.1771217 Yajuan Zhang, Cuixia Li & Shuai Yao (2021) Spatiotemporal evolution characteristics of China’s cold chain logistics resources and agricultural product using remote sensing perspective, European Journal of Remote Sensing, 54:sup2, 275-283, DOI: 10.1080/22797254.2020.1765202 Guangping Liu, Jingmei Wei, BalaAnand Muthu & R. Dinesh Jackson Samuel (2021) Chlorophyll-a concentration in the hailing bay using remote sensing assisted sparse statistical modelling, European Journal of Remote Sensing, 54:sup2, 284-295, DOI: 10.1080/22797254.2020.1771774 Yishu Qiu, Zhenmin Zhu, Heping Huang & Zhenhua Bing (2021) Study on the evolution of B&Bs spatial distribution based on exploratory spatial data analysis (ESDA) and its influencing factors—with Yangtze River Delta as an example, European Journal of Remote Sensing, 54:sup2, 296-308, DOI: 10.1080/22797254.2020.1785950 Liang Li & Kangning Xiong (2021) Study on peak cluster-depression rocky desertification landscape evolution and human activity-influence in South of China, European Journal of Remote Sensing, 54:sup2, 309-317, DOI: 10.1080/22797254.2020.1777588 Juan Xu, Mengsheng Yang, Chaoping Hou, Ziliang Lu & Dan Liu (2021) Distribution of rural tourism development in geographical space: a case study of 323 traditional villages in Shaanxi, China, European Journal of Remote Sensing, 54:sup2, 318-333, DOI: 10.1080/22797254.2020.1788993 Lin Guo, Xiaojing Guo, Binghua Wu, Po Yang, Yafei Kou, Na Li & Hui Tang (2021) Geo-environmental suitability assessment for tunnel in sub-deep layer in Zhengzhou, European Journal of Remote Sensing, 54:sup2, 334-340, DOI: 10.1080/22797254.2020.1788994 Hui Zhou, Cheng Zhu, Li Wu, Chaogui Zheng, Xiaoling Sun, Qingchun Guo & Shuguang Lu (2021) Organic carbon isotope record since the Late Glacial period from peat in the North Bank of the Yangtze River, China, European Journal of Remote Sensing, 54:sup2, 341-347, DOI: 10.1080/22797254.2020.1795728 Chengyuan Hao, Linlin Song & Wei Zhao (2021) HYSPLIT-based demarcation of regions affected by water vapors from the South China Sea and the Bay of Bengal, European Journal of Remote Sensing, 54:sup2, 348-355, DOI: 10.1080/22797254.2020.1795730 Wei Chong, Zhang Lin-Jing, Wu Qing, Cao Lian-Hai, Zhang Lu, Yao Lun-Guang, Zhu Yun-Xian & Yang Feng (2021) Estimation of landscape pattern change on stream flow using SWAT-VRR, European Journal of Remote Sensing, 54:sup2, 356-362, DOI: 10.1080/22797254.2020.1790994 Kepeng Feng & Juncang Tian (2021) Forecasting reference evapotranspiration using data mining and limited climatic data, European Journal of Remote Sensing, 54:sup2, 363-371, DOI: 10.1080/22797254.2020.1801355 Kepeng Feng, Yang Hong, Juncang Tian, Xiangyu Luo, Guoqiang Tang & Guangyuan Kan (2021) Evaluating applicability of multi-source precipitation datasets for runoff simulation of small watersheds: a case study in the United States, European Journal of Remote Sensing, 54:sup2, 372-382, DOI: 10.1080/22797254.2020.1819169 Xiaowei Xu, Yinrong Chen, Junfeng Zhang, Yu Chen, Prathik Anandhan & Adhiyaman Manickam (2021) A novel approach for scene classification from remote sensing images using deep learning methods, European Journal of Remote Sensing, 54:sup2, 383-395, DOI: 10.1080/22797254.2020.1790995 Shanshan Hu, Zhaogang Fu, R. Dinesh Jackson Samuel & Prathik Anandhan (2021) Application of active remote sensing in confirmation rights and identification of mortgage supply-demand subjects of rural land in Guangdong Province, European Journal of Remote Sensing, 54:sup2, 396-404, DOI: 10.1080/22797254.2020.1790996 Chen Qiwei, Xiong Kangning & Zhao Rong (2021) Assessment on erosion risk based on GIS in typical Karst region of Southwest China, European Journal of Remote Sensing, 54:sup2, 405-416, DOI: 10.1080/22797254.2020.1793688 Zhengping Zhu, Bole Gao, Renfang Pan, Rong Li, Yang Li & Tianjun Huang (2021) A research on seismic forward modeling of hydrothermal dolomite:An example from Maokou formation in Wolonghe structure, eastern Sichuan Basin, SW China, European Journal of Remote Sensing, 54:sup2, 417-428, DOI: 10.1080/22797254.2020.1811160 Shaofeng Guo, Jianmin Zheng, Guohua Qiao & Xudong Wang (2021) A preliminary study on the Earth’s evolution and condensation, European Journal of Remote Sensing, 54:sup2, 429-437, DOI: 10.1080/22797254.2020.1830309 Yu Gao, Ying Zhang & Hedjar Alsulaiman (2021) Spatial structure system of land use along urban rail transit based on GIS spatial clustering, European Journal of Remote Sensing, 54:sup2, 438-445, DOI: 10.1080/22797254.2020.1801356 Xia Mu, Sihai Li, Haiyang Zhan & Zhuoran Yao (2021) On-orbit calibration of sun sensor’s central point error for triad, European Journal of Remote Sensing, 54:sup2, 446-457, DOI: 10.1080/22797254.2020.1814164 Following publication, the publisher identified concerns regarding the editorial handling of the special issue and the peer review process. Following an investigation by the Taylor & Francis Publishing Ethics & Integrity team in full cooperation with the Editor-in-Chief, it was confirmed that the articles included in this Special Issue were not peer-reviewed appropriately, in line with the Journal’s peer review standards and policy. As the stringency of the peer review process is core to the integrity of the publication process, the Editor and Publisher have decided to retract all of the articles within the above-named Special Issue. The journal has not confirmed if the authors were aware of this compromised peer review process. The journal is committed to correcting the scientific record and will fully cooperate with any institutional investigations into this matter. The authors have been informed of this decision. We have been informed in our decision-making by our editorial policies and the COPE guidelines. The retracted articles will remain online to maintain the scholarly record, but they will be digitally watermarked on each page as ‘Retracted’.


Introduction
Land use/land cover (LULC) changes play an essential role in the studies of regional, local and global environmental change (Gupta & Munshi, 1985;Mas, 1999).Land cover refers to how the Earth's surface is covered by forests, wetlands, impervious surfaces, agricultural, and other types of land and water (Prakasam, 2010).Land use refers to how humans use the landscape, whether for development, conservation, or mixed uses.Land use includes recreation areas, wildlife habitats, agricultural land, and built-up land (Reis, 2008).Since the past 100 years, the human population and its influence have increased exponentially on land.Human alterations on the Earth's surface result in changes in the land cover.These changes significantly affect key aspects of Earth system functioning (including the balance of energy, water, and soil).Moreover, the pressure on limited natural resources, which is caused by an increase in population, contributes to changes in the land surface cover (Islam et al., 2018).
There exist numerous sources of LULC changes (Lambin et al., 2001) described forest degradation, agricultural magnification, globalization, and urbanization as the leading causes for regional and global LULC changes.Biophysical attributes, the global climate, and ecosystem activities are associated with significant changes in the land cover (Aansen et al., 2014).(Kaliraj et al., 2017) indicated the necessary information required for understanding the trends in LULC changes in a coastal area.Changes in the LULC are dynamic and continuous.Updated and accurate LULC maps are of considerable significance for proper planning, global change, environment monitoring, and the estimation of forest degradation.Reports related to changes in the LULC play a vital role in the utilization and management of natural resources.
Recently, multispectral and multi-temporal high-and medium-spatial-resolution satellite data have emerged as essential tools for estimating aspects such as the vegetation cover, forest degradation, and urban expansion (Mustafa et al., 2007).Remote sensing and GIS technology provide a platform for studying landscape transformations throughout the surface of the Earth (Estoque & Murayama, 2015).In conventional methods, mapping is performed using available records, field surveys, and maps.Thus, conventional methods are time-consuming and expensive.Moreover, the produced maps become quickly outdated in rapidly changing environments (Dash et al., 2015).In contrast to traditional data acquisition, remotely sensed data provides valuable information in a relatively short time and cost-effective manner.High-resolution satellite imageries or aerial photos are important for studying the LULC changes in large cities.However, such data sets are limitedly available due to financial factors (Dwivedi et al., 2005;Gadrani et al., 2018).However, mediumresolution data, such as the Multi-Spectral Scanner (MSS), TM, and Operational Land Imager (OLI) Landsat data sets, have been used worldwide for LULC change detection analysis (Chandrashekar et al., 2018;Sundarakumar et al., 2012).(Wang et al., 2009) used Landsat TM data to assess the changes in the urban land, bare soil, land under water bodies, and land covered by vegetation in China.(Odindi et al., 2012) Elizabeth, South Africa, between 1990 and2000.Landsat data sets can be obtained free of cost from the United States Geological Survey (USGS) Earth Explorer (http://earthexplorer.usgs.gov)online portal.
Currently, numerous techniques are available for assessing and detecting LULC changes.Among them, remote sensing technology and GIS provide robust tools for acquiring accurate and timely information on land use patterns and their changes (Arveti et al., 2016;Mamun et al., 2013).Remote sensing applications allow land changes to be studied within a limited time and at a low cost.Numerous methods have been developed by many researchers to review changes in the LULC (Jwan Al-doski, 2013;Singh, 1989) including multi-temporal composite image change detection (Carmelo et al., 2012;Eastman & Fulk, 1993).on-screen digitization of change (Sreedhar et al., 2016), vegetation index differencing (Shanmugam & Rajagopalan, 2013), and postclassification change detection (Belal & Moghanm, 2011;Courage et al., 2013;Kafi et al., 2014).
The main contribution of this article is to quantitatively analyse the LULC in Ananthapuramu and its surrounding area from 1978 to 2019 by using multitemporal Landsat imagery.The main intention of this study is to determine the urbanization pressure and changes within the environment.Even though several studies had contributed pertaining towards LULC detection this study made use of integrated remote sensing and GIS techniques to detect LULC changes in the study area.Application of the Quantum inspired image processing in urban surveillance is considered as a vital aspect in the context of analyzing huge image data.

Study area
In this research, the LULC changes in the urban and rural parts of Ananthapuramu were determined using remote sensing and GIS technology.The study area is located in the south eastern part of Andhra Pradesh state and the north eastern part of Ananthapur district.Ananthapuramu is considered as one of the major districts in rayalaseema region and its geographical location based on GIS is located at 78°30ʹ and 76°60ʹ East; 15°15ʹ and 13°40ʹ North.It is surrounded by chittoor and kadapa at the east, Kurnool and Bellary on the north, chitradurga and thumkur at the west and kolar at the south.The geographical area of the ananthapur district contributes around 7% of area in the state of Andhra Pradesh with an area of around 19,130 sq.km.In is considered as one among the biggest district in Andhra Pradesh that includes around 11 towns and 972 villages.
Based on its topographical details the district is classified in to three natural regions that include red soils at the southern region, enormous expanse of arid along with the treeless poor red soil at the central region, black cotton soils at the northern region.The major rivers that surpasses through the district include pennar river and chitravathi that are originated from the state of Karnataka.Ananthapur district includes two distinct geological formations, of those the initial one is sedimentary rocks in the eastern part of Tadipatri and archaean rocks at the northen part of Gooty.Later parts of anantapur mostly include gneisses and granites along with the minerals like barites, limestone and diamonds of gem quality.In a generic perspective red and black soils constitute around 76% and 24% of the geographical area respectively.The geographical area of the forest is around 10.3% of the total area with undulating and hilly topography.The climate of this area is categorized as semiarid [19].The study area experiences a maximum temperature of 33°C-45°C in the summer (April-May) and minimum temperature of 15°C in the winter (December-January).It receives rainfall due to the

R E T R A C T E D
southwest monsoon (June-September) as well as the northeast monsoon (November-December).

Methodology
This study specifically focused on interpreting the changes in the land use through satellite imagery and demographic data.The quantitative method of change detection was used in this research.In the change detection method, each satellite image is classified.The resulting LULC maps obtained after the classification are then compared according to the pixel-by-pixel approach by using a change detection matrix.The methodology adopted in this study is as follows: (1) data collection, (2) pre-processing, (3) LULC classification scheme, (4) selection of training data samples, (5) image classification, (6) accuracy assessment, and (7) change detection.Every step except the data collection step was performed using ERDAS Imagine 14 software and Arc Map 10.1.Figure 2 depicts the flow chart that illustrates the methodology included in this present study.

Data collection
(TIRS) data set.The Landsat data sets were downloaded free of cost from the USGS Earth Explorer online archive (freely downloadable worldwide).The Landsat MSS data set has four spectral bands (4-7) with a spatial resolution of 60 m, and the Landsat 8 OLI data set has nine spectral bands (2-7) with a spatial resolution of 30 m.These data sets were used for preparing the LULC map.The downloaded data was in the Geo tiff file format.Each image band exhibits intensity values for a certain wavelength in the form of a greyscale image of the study area.The spectral characteristics of the Landsat data are listed in Table 1.Images with cloud cover and undesired shade significantly reduce the accuracy result of classification.Therefore, good-quality and cloud-free scenes were used in this research.
Quantum GIS is an open-source framework that enables efficient collection of image data from various sources that include the vector, database and raster, which are used in the context of building a single project for seamless spatial analysis (Vivekananda andChenna Reddy, 2018, 2019).This process enhances the capability of the data collection that meets the requirements and basic functionalities of GIS.Additionally, Quantum GIS is considered as an option for improving the features through plugins using python language which is regarded as and programmer-friendly nowadays.Application of quantum GIS leads to the efficient development of a systematic model to process multi-temporal images for LULC.

Image subsetting and pre-processing
Image analysis enables information to be extracted from data sets.A scanned toposheet image is not georeferenced to the surface of the Earth (Manonmani & Mary Divya Suganya, 2010).Therefore, the toposheet was georeferenced to longitudes and latitudes by using well-distributed Ground Control Points (GCPs) and projected to the Geographic (Lat/Lon) WGS 1984 datum.Finally, the study area was clipped from the georeferenced toposheet.
The satellite imagery was overlaid in one file (single layer) by using the layer stack tool of ERDAS software.Due to this process, a False Colour Composite (FCC)

R E T R A C T E D
the reference image, the Landsat MSS image was registered and projected to the Universal Transverse Mercator (UTM) WGS 1984 datum and resampled to a resolution of 30 m by using the nearest neighborhood classification.The study area was masked and clipped from the registered multitemporal images by using the subset tool of ERDAS Imagine 14.Each subset image was enhanced using the histogram equalization technique to improve spectral responses.The 120-km2 subset area of 1978 and 2018 (Figure 3) was obtained from the Landsat MSS and Landsat OLI data sets, respectively.The images of the subset area were used for subsequent analysis and image classification.

Image classification scheme
The USGS Level I LULC classification scheme was used in this study.The study area was broadly classified into five different classes.The detailed description of the classes is provided in Table 2.Each class was derived according to texture, tone, and color (Radhakrishnan et al., 2014).These classes were assigned to pixels in image classification.

Selection of training data samples
Data sets were trained using different band combinations of the satellite images, field survey data, and Google Earth data.The satellite image of the Ananthapuramu region and the Landsat 8 subset image were linked and synced using the Google Earth tool of ERDAS software.This process enabled the unique features in the study area to be recognized.Different band combinations were used to determine the color tone of a specific class.The band combination 5-4-3 was used for vegetation, forests, crops, wetlands analysis.The band combination 7-6-4 was used for analyzing the built-up land.Data sets were trained according to the tone of the pixel color.
Training sites were created in the imagery by drawing polygons, which were placed in an AoI (Area of Interest) layer.To train each specific class, 15 polygons were brought and placed in the signature editor.These 15 polygons were merged and specified by a particular class name.The signature editor file was then saved as a signature file (.sig format).Two signature files were developed in this study to train the two data sets (1978 and 2018).Finally, the trained data sets were used in the supervised image classification process.

Image classification
Multi-temporal Landsat images of the study area were used to study and classify the land cover types.Remote sensing includes three main image classification techniques: unsupervised classification, supervised classification, and object-based image classification.The Maximum Likelihood Classifier (MLC) algorithm of supervised classification was used in this study.The MLC has been widely used for the classification of medium-resolution satellite imagery (Anil et al., 2011;Bayarsaikan et al., 2009;Brahabhatt et al., 2000;Ratnaparkhi et al., 2016;Zubair Iqbal & Javed Iqbal, 2018).The spectral signature files developed for all the classes were used during classification.
The classification was performed using the MLC.This algorithm, according to ERDAS, computes the weighted distance D W of an unknown vector X belonging to one of the known class "i" is based on the Bayesian equation: Where c is particular class, ai is Percent probability of any pixel is a member of class i.The datasets obtained from Landsat are classified based on the dates in which they are received.Then, a majority filter with a 4 × 4 size kernel was applied to the classified data to minimize the salt and pepper effect (Kantakumar et al., 2016;Lillesand & Kiefer, 1999).The classified images generated after using the majority filter display the LULC types of the study area.The classified images were compared with each other to determine the variation in the LULC pattern.
In the context of Quantum inspired image processing, initially, the input image is transformed into 8 × 8 and 16 × 16 blocks, further in which a twodimensional Discrete Cosine transformation is applied on each block.In this context, the coefficients of DCT are transmitted, coded and quantized.

Classification accuracy assessment
After generating the classified images, the accuracy of the classified images was determined using the ERDAS Imagine 14 software.Classification accuracy assessment is an essential step after image classification.The accuracy assessment tool of the supervised classifier randomly generated 176 and 324 reference points through stratified random sampling of the 1978 and 2018 classified images, respectively.Each point had a specific color and pixel value, which were automatically identified by the software.The classes in the classified image were considered as reference classes.Randomly generated points were then identified, and the corresponding class was assigned by the user manually.The error matrix and kappa statistics for the two classified images were generated from the selfgenerated report section of ERDAS Imagine 14.This process was performed for two classified images (i.e., 1978 and 2018).The error matrix indicates the accuracy of classification (Foody, 2002).The rows represent the classes resulting from the classified image, whereas the columns represent the classes identified by the user from the reference values.The diagonal cells of the error matrix indicate the total number of correctly identified pixels for each class of the reference and classified data.The off-diagonal cells represent the incorrectly identified pixels, which indicate the error between reference data and classified data.
There are two types of errors, namely omission and commission error, are occurred during the classification process.Errors of commission occurred when a classification process assigns pixels to a specific class that doesn't belong to it.The number of pixels that are mistakenly assigned to a class was found in column cells of the class above and below the main diagonal.The Producer's accuracy also described the number of errors of commission.For every class, errors of omission occurred when pixels that belong to one class, are included in other classes.In the confusion matrix, the number of omitted pixels was found in the row cells to the left and the right from the main diagonal.The user's accuracy is another indicator characterizing the errors of omission.The adopted equations calculated producer's efficiency and User's accuracy: (2) The overall accuracy and kappa coefficient of the two data sets were calculated using the following equations.
Where N represents the total number of pixels, r represents the number of classes, x kk represents the total pixels in row "k" and column "k," x k+ represents total samples in a row "k," and x +k represents the total samples in column "k" in the error matrix.

Change detection
Remote-sensing-and GIS-based change detection approaches are widely used due to their costeffectiveness and high temporal resolution.The postclassification comparison technique, which is based on maximum likelihood supervised classification, is the most commonly used method for detecting LULC changes.A high overall classification accuracy has been achieved with this technique for a variety of data (Muttitanon & Tripathi, 2005;Torahi & Rai, 2011).
The percentage change (C %) in each land-use class was calculated by dividing the change in a class by the coverage area in the base year and multiplying by 100, by the simple equation.
Where: i = Number of classes in an image C i = Magnitude of change in class "i."

Results and discussion
The data sets of the Ananthapuramu region (Landsat MSS for 1978 and Landsat 8 OLI for 2018) were registered using the AutoSync workstation module in ERDAS IMAGINE 14.The data sets were registered by georeferencing the images with latitude and longitude values from the already georeferenced SOI toposheet of the study area.After registration, both the data sets were trained through visual interpretation.The identified classes were digitized by drawing polygons to produce signature files.In the next step, supervised classification was performed according to the signature file in ERDAS Imagine 14 for producing the LULC maps.The accuracy assessment results for the two data sets are presented in Tables 3 and 4. The area occupied by different classes in both years was obtained from the attribute table.After-image classification, the post-classification comparison technique was performed, where a LULC map from one data set (1978) was compared with a LULC map from another data set (2018).According to the comparison, the changes occurring between the two study years are presented quantitatively.After-image classification, maps were prepared on a 1:50,000 scale by using Arc Map 10.1.

LULC pattern of Ananthapuramu in 1978
The LULC map layout generated from the Landsat MSS data set is displayed in Figure 4.The land categories for the year 1978, and their statistics are listed in Table 3.According to the results, the largest category was agriculture land (47.83 km 2 , 39.84% of the total area), followed by forest (37.66 km 2 , 31.38% of the total area).The remaining land use categories were settlements with homestead trees (6.81 km 2 , 5.7% of the total area), barren land/other lands (17.87 km 2 , 14.89% of the total area), and water (9.83 km 2 , 8.19% of the total area).

LULC pattern of Ananthapuramu in 2019
The classified image for 2018 (Figure 5) was produced using the Landsat 8 data set.According to the 2018 results, the land area mainly comprised barren land/ other lands (41.55 km 2 , 34.63% of the total land), followed by settlement land (31.55 km 2 , 26.29% of the total area).The land-use categories were forest land (26.08 km 2 , 21.67% of the total area), agriculture land (18.25 km 2 , 15.21% of the total area), and water bodies (2.65 km 2 , 2.21% of the total area).The landuse categories for 2018 and their statistics are listed in Table 4. From 1978 to 2018, the LULC patterns changed considerably.

Kappa coefficient and overall accuracy for the 1978 and 2018 images
Accuracy assessment was performed for the 1978 and 2018 LULC maps.For the 1978 LULC map, 175 pixels were selected randomly.The 1978 LULC map had an overall kappa statistic of 0.785 and an overall accuracy of 81.25% (Table 3).The producer's accuracy for each class was higher than or equal to 80%.The user's accuracy for three (water For the 2018 LULC map, 324 pixels were selected randomly.The overall kappa statistics and overall accuracy of the 2018 LULC map were 0.857 and 87.46 %, respectively (Table 4).The producer's accuracy of each class was higher than 80%.The user's accuracy of all the classes except barren/ other lands (77%) was more than 80%.The accuracy of each class was observed to be satisfactory in the two classifications.The overall classification accuracy results and kappa statistics for the 1978 and 2018 LULC maps are presented in Tables 3  and 4, respectively.

Change detection from 1978 to 2018
The area under the LULC classes and its changes from 1978 to 2018 are presented in Table 5. Figure 3 displays the spatial expansion of the built-up area.In 1978, the area covered by built-up land was minimal and mainly located in the center of the study area.Positive and negative changes were observed over 40 years in the area under the LULC categories.The water bodies, forest, and agriculture land categories exhibited a decrease in their area, whereas the built-up land and barren land/ other land categories exhibited an increase in their area.As presented in Table 5, the most substantial changes in area were observed for the built-up/other land categories, followed by the water bodies, agriculture land, and forest categories.

Water bodies
The area under water bodies declined from 9.83 km 2 in 1978 to 2.65 km 2 in 2018, which represents a net decrease of 7.18 km 2 .The area under water bodies decreased due to the conversion of water bodies into other land and the reduction in the rainfall received by the study area over the past 40 years.

Agriculture land
The area under agriculture land decreased from 47.83 km 2 in 1978 to 18.25 km 2 in 2018, which represents a net decrease of 29.58 km 2 .The available agriculture land within the study area rapidly decreased during the study period.The area under agricultural land decreased due to the demand for urban shelter and socio-economic development activities inside the study area.Another reason for the decrease is that farmers in the study area have neglected to farm and reserved their lands for other businesses.

Built-up land
The area under built-up land increased from 6.81 km 2 in 1978 to 31.55 km 2 in 2018, which represents a net increase of 24.74 km 2 .The area under built-up land increased due to the rise in population, tourism activities, and the demand for shelter by inhabitants.Another reason for the growth is that the study area is a center point to reach the world-famous Tirumala temple.

Forest land
The

Conclusion and future work
In this research, remote sensing and GIS were integrated for quantifying and understanding the LULC changes in Ananthapuramu over 40 years from 1978 to 2018.The technique used in this study is simple and inexpensive.The extent of land-use changes in Ananthapuramu was determined using multitemporal satellite imagery.In this study, classification accuracy was measured using the confusion matrix.
The overall classification accuracy of this study was acceptable.Significant changes in the LULC were observed in the study area between 1978 and 2018.During these 40 years, the area under built-up land and other land increased considerably, whereas the area under agriculture land and water bodies drastically decreased.The causes of the LULC changes in the study area include the decrease in agricultural activities and the increase in built-up activities.The LULC changes may not have a considerable environmental impact on the study area.However, the LULC changes should be closely monitored in the future for the sustainability of the environment.Further, the work could be extended by using the various machines and deep learning algorithms like CNN, R-CNN that could enhance the performance of the algorithm.

Disclosure statement
No potential conflict of interest was reported by the authors.(+) Indicates an increase and (−) indicates a decrease in the area under a LULC class over 40 years .
EUROPEAN JOURNAL OF REMOTE SENSING 197

Figure 1 .
Figure 1.(a) Study area indicated in India Map.(b) Enlarged Image of Study area.
Figure 3. (a) FCC images of the study area 1978 Landsat MSS image.(b) FCC images of the study area 2018 Landsat OLI-TIRS image.

Figure 2 .
Figure 2. Flowchart demonstrating the methodology followed in present study.
The post-classification comparison technique involves classifying images and comparing the corresponding classes to determine the areas where change has occurred.In a comparative study of different techniques, the postclassification comparison technique had the highest classification accuracy.(Landsat 8 dataset, 2019; Sun & Wang, 2009; Team, 2014) used the post-classification comparison technique based on the MLC algorithm to verify the land-use changes in the Datong basin, China, through Landsat data.In this study, two registered and independently classified images were used to calculate the changes in LULC.The degree of accuracy of the results depends on the accuracy of the thematic maps prepared through image classification.The magnitude of change (C) in each class was determined using the following equation:

Figure 5 .
Figure 5. LULC map of the study area in 2018, which indicates the level of urban expansion from 1978 to 2018.

Figure 4 .
Figure 4. LULC map of the study area in 1978, which indicates a relatively small built-up area.

Table 1 .
Spectral characteristics of the Landsat data used for assessing the LULC changes in the study area.

Table 2 .
Image classification details.
Areas with or without sparse vegetation that are likely to change or be converted to other users in the future.This category includes land without crops, land with barren rock, and sand areas along rivers/stream beaches 5 Water Areas covered by water, including rivers, reservoirs, ponds, lakes, and streams.EUROPEAN JOURNAL OF REMOTE SENSING 193

Table 3 .
Confusion matrix indicating the overall accuracy and Kappa statistics of the 1978 LULC map of the study area.

Table 4 .
Confusion matrix indicating the overall accuracy and Kappa statistics of the 2018 LULC map of the study area., built-up land, and forest) categories was more than 80%.The agriculture land and barren/ other land categories have a user's accuracy of 68.25% and 77.77%, respectively. bodies

Table 5 .
The area under each LULC class in the 1978 and 2018 data sets and change in the area of each LULC class over 40 years (in km 2 and percentage).