Post-classification Change Detection Research Articles

Time series land use/land cover mapping and change detection to support policies on sustainable environmental and economic management

The upper Tekeze River Basin is facing challenges of widespread deforestation and natural vegetation cover degradation that could exacerbate the water scarcity, food insecurity and extreme poverty in the region. Using remote sensing and GIS, this study quantified the land use land cover change trend in the last three decades and analyzed the current land use / cover statues in the basin. A hybrid classification technique is applied to obtain better classification accuracy. Moreover, for automated cloud and cloud shadow detection the newly developed Mountainous Fmask is used. Using post classification change detection technique, seven major land use/cover classes were identified. These classes remained the dominant classes during the study period, showing marked changes in the area coverage within them. Based on the error matrix statistical indices, the classification accuracies of each class are found to be strong. The overall accuracy and the kappa coefficient for the 2021 map are 91% and 89%, respectively. The techniques used have contributed to improving the accuracy of the classification process and helped the classified images to practically match the ground truths. The analysis revealed settlement expansion by 570.31% in parallel with the expansion of farmland by 52.32% during the period 1991–2021. In contrast, the forestland decreased significantly, by 75.55%. The environmental degradation and unplanned use of land resources could have contributed to why the upper Tekeze basin is experiencing worsening poverty, water scarcity and food insecurity. Thus, land use/cover time series modeling is essential for various purposes, including land use planning and, managing natural resources. In this regards this study provides basic information for implementing sustainable environmental conservation strategies in the area. Furthermore, the applied methodologies may have practical applications in other similar areas.

LAND COVER CHANGE ANALYSIS OF CARRASCAL, MADRID AND CANTILAN MINING SITES IN SURIGAO DEL SUR USING REMOTE SENSING

Abstract. The Philippines is recognized as amongst the natural resource-rich countries which has been evident in the influx of extractive industry investors, most specifically in the mining industry. An example of this is the case of mining sites in the municipalities of Carrascal, Madrid, and Cantilan (CMC) in Surigao del Sur region of the Philippines. In this region, development of mining areas was significantly noticeable in a span of seven (7) years since 2015. With this being an alarming case due to its possible negative impacts on the surrounding communities, this study developed an open-source monitoring system of mining activities using remote sensing technologies employing supervised image classification using the Random Forest algorithm. This study is mainly motivated by the need for a monitoring system to ensure responsible mining practices in the country, most especially since there has been an increasing global clamour for a more environmental-friendly and climate-sensitive and sustainable practices. The methodology developed for this study utilized a post-classification change detection approach in which multitemporal land cover (LC) models were produced to capture the land cover changes. To model the LC changes, land cover models for 2015 and 2022 were produced obtaining overall accuracies between 0.93 to 0.95, respectively. Using these models, changes due to mining development were delineated through a multitemporal overlay analysis approach. This change detection model obtained an F1-score of 0.93 indicating high accuracy and satisfactory performance of the model and consequently, the its potential as a mining site monitoring system to achieve the goal of ensuring responsible mining industry practice in the country.

ENVINet5 deep learning change detection framework for the estimation of agriculture variations during 2012-2023 with Landsat series data.

Remote sensing is one of the most important methods for analysing the multitemporal changes over a certain period. As a cost-effective way, remote sensing allows the long-term analysis of agricultural land by collecting satellite imagery from different satellite missions. Landsat is one of the longest-running world missions which offers a moderate-resolution earth observation dataset. Land surface mapping and monitoring are generally performed by incorporating classification and change detection models. In this work, a deep learning-based change detection (DCD) algorithm has been proposed to detect long-term agricultural changes using the Landsat series datasets (i.e., Landsat-7, Landsat-8, and Landsat-9) during the period 2012 to 2023. The proposed algorithm extracts the features from satellite data according to their spectral and geographic characteristics and identifies seasonal variability. The DCD integrates the deep learning-based (Environment for visualizing images) ENVI Net-5 classification model and posterior probability-based post-classification comparison-based change detection model (PCD). The DCD is capable of providing seasonal variations accurately with distinct Landsat series dataset and promises to use higher resolution dataset with accurate results. The experimental result concludes that vegetation has decreased from 2012 to 2023, while build-up land has increased up to 88.22% (2012-2023) for Landsat-7 and Landsat-8 datasets. On the other side, degraded area includes water (3.20-0.05%) and fallow land (1-0.59%). This study allows the identification of crop growth, crop yield prediction, precision farming, and crop mapping.

Multi-decadal coastal change detection using remote sensing: the Mediterranean coast of Egypt between El-Dabaa and Ras El-Hekma

A key source of information for many decision support systems is identifying land use and land cover (LULC) based on remote sensing data. Land conservation, sustainable development, and water resource management all benefit from the knowledge obtained from detecting changes in land use and land cover. The present study aims to investigate the multi-decadal coastal change detection for Ras El-Hekma and El-Dabaa area along the Mediterranean coast of Egypt, a multi-sectoral development area. Besides, the superiority of the area is highly dependent on its proximity to three development projects: the tourism and urban growth pole at Ras El-Hekma, the beachfront Alamain New Mega City, and the Nuclear Power Plant at El Dabaa. This study utilized multi-spectral Landsat satellite images covering 1990, 2010, and 2020 to perceive the post-classification change detection analysis of the land use and land cover changes (LULCC) over 30 years. The results of the supervised classification from 1990 to 2020 showed a 47.33 km2 (4.13%) expansion of the agricultural land area, whereas the bare soil land area shrunk to 73.13 km2 (6.24%). On the other hand, the built-up activities in the area launched in 2010 and escalated to 20.51 km2(1.77%) in 2020. The change in land use reveals the shift in the economic growth pattern in the last decade toward tourism and urban development. Meanwhile, it indicates that no conflict has yet arisen regarding the land use between the expanded socioeconomic main sectors (i.e., agriculture, and tourism). Therefore, the best practices of land use management and active participation of the stakeholders and the local community should be enhanced to achieve sustainability and avoid future conflicts. An area-specific plan including resource conservation measures and the provision of livelihood alternatives should be formulated within the National Integrated Coastal Zone Management (ICZM) plan with the participation of the main stakeholders and beneficiaries. The findings of the present work may be considered useful for sustainable management and supportive to the decision-making process for the sustainable development of this area.

Land Cover and Landscape Structural Changes Using Extreme Gradient Boosting Random Forest and Fragmentation Analysis

Land use and land cover change constitute a significant driver of land degradation worldwide, and machine-learning algorithms are providing new opportunities for effectively classifying land use and land cover changes over time. The aims of this study are threefold: Firstly, we aim to compare the accuracies of the parametric classifier Naïve Bayes with the non-parametric classifier Extreme Gradient Boosting Random Forest algorithm on the 2020 LULC dataset. Secondly, we quantify land use and land cover changes in the Cradle of Humankind from 1990 to 2020 using the Extreme Gradient Boosting Random Forest algorithm and post-classification change detection. Thirdly, the study uses landscape metrics to examine landscape structural changes occurring in the same area due to fragmentation. The classification results show that while Naïve Bayers and XGB Random Forest produce classification results of high accuracy, the XGB Random Forest Classifier produced superior results compared to the Naïve Bayers Classifier. From 1990 to 2020, bare ground/rock outcrop significantly increased by 39%, and open bush by 32%. Indigenous forests and natural grasslands lost area (26% and 12%, respectively). The results from this study indicate increasing land cover fragmentation and attest to land degradation, as shown by increases in bare ground and a reduction in indigenous forest and natural grassland. The decline in indigenous forests and natural grassland indicates the degradation of native vegetation, considered as prehistoric plant food sources. The high classification results also attest to the efficacy of the XGBRFClassifier executed in GEE. Land degradation evident in the nature reserve has long-term ecological consequences, such as loss of habitat, biodiversity decline, soil erosion, and alteration of local ecosystems, which together diminish the aesthetic value of the heritage site and negatively impact its tourism value. Consequently, it destroys crucial local economies and threatens sustainable tourism.

Mapping and monitoring of spatio-temporal land use and land cover changes and relationship with normalized satellite indices and driving factors

ABSTRACT Climate change has become a severe threat all around the world. Pakistan is also affected by climate change. It has become a severe problem in any part of the country. It is land degradation caused by climatic disturbance and anthropogenic activities. In this study, we used Landsat TM for the years 1980 and 1990, Landsat ETM+ for the years 2000 and 2010, and Landsat OLI/TIRS for the year 2020 were classified using the Maximum Likelihood Classification (MLC) into a built-up area, barren land, vegetation, and water area. This study has been conducted to assess the spatio-temporal analysis of Land Use/Land Cover (LULC) with driving factors from 1980–2020 in the Cholistan Desert, Punjab, Pakistan, and the relationship between different normalized satellite indices with LULC. Post-classification change detection methods were then used to assess the variation over the study period. The built-up area has increased by 6.25% from 1980–2020. The Kappa coefficient was estimated at 0.83, 0.82, 0.83, 0.85, and 0.88 in 1980, 1990, 2000, 2010, and 2020, respectively. At the annual scale (the years 2000 and 2020), a significant positive relationship was observed among LULC, NDVI, and MNDWI for the regions located in the western part of the Cholistan region, while negative trends in the year 1980 to the 2010 year.

Land-cover changes and deforestation drivers in the forest landscape of Banmauk township in the Sagaing Region of upper Myanmar

ABSTRACT This study focused on the extent of land-cover changes and prediction of probable factors in deforestation based on changes observed from 2000 to 2021 in the forest landscape of Banmauk Township in Myanmar’s Sagaing Region. Landsat 7 ETM+ and Landsat 8 OLI satellite imagery were used to identify seven land-cover classes via supervised random tree classification, and binary logistic regression analysis was used to predict the potential for biophysical and locational factors to affect deforestation. A stratified random sampling method was used to assess the accuracy of the classified maps and to estimate the areas. The study revealed that dense forest coverage decreased from 45.65% in 2000 to 29.01% in 2021, while open forest areas increased from 49.33% to 54.51%. Mining areas exhibited a considerable increase from 0.37% to 5.35%, while settlement and barren/scrub land areas increased from 0.16% to 0.51% and 1.71% to 7.70%, respectively. Agricultural areas slightly increased from 2.11% to 2.33%, while water areas remained almost the same at around 0.60%. Post-classification change detection analysis showed that deforestation occurred mainly through converting forest land to mining and barren/scrub land. The study indicated that lower altitudes and road accessibility are significantly associated with the potential for deforestation.

Remote-Sensing-Based Change Detection Using Change Vector Analysis in Posterior Probability Space: A Context-Sensitive Bayesian Network Approach

Change vector analysis (CVA) and post-classification change detection (PCC) have been the most widely used change-detection methods. However, CVA requires sound radiometric correction to achieve optimal performance, and PCC is susceptible to accumulated classification errors. Although change vector analysis in the posterior probability space (CVAPS) was developed to resolve the limitations of PCC and CVA, the uncertainty of remote sensing imagery limits the performance of CVAPS owing to three major problems: 1) mixed pixels, 2) identical ground cover type with different spectra, and 3) different ground cover types with the same spectrum. To address this problem, this study proposes the FCM-CSBN-CVAPS approach under the CVAPS framework. The proposed approach decomposes the mixed pixels into multiple signal classes using the fuzzy C means (FCM) algorithm. Although the mixed pixel problem is less severe in the high-resolution image, the change detection performance is still enhanced because, as a soft clustering algorithm, FCM is less susceptible to cumulative clustering error. Then, a context-sensitive Bayesian network (CSBN) is constructed to establish multiple-to-multiple stochastic linkages between signal pairs and ground cover types by incorporating spatial information to resolve problems 2 and 3 discussed above. Finally, change detection is performed using CVAPS in the posterior probability space. The effectiveness of the proposed approach is evaluated on three bi-temporal remote sensing datasets with different spatial sizes and resolutions. The experimental results confirm the effectiveness of FCM-CSBN-CVAPS in addressing the uncertainty problems of change detection and its superiority over other relevant change-detection techniques.

Monitoring Shoreline and Land Use/Land Cover Changes in Sandbanks Provincial Park Using Remote Sensing and Climate Data

Climate change-driven forces and anthropogenic interventions have led to considerable changes in coastal zones and shoreline positions, resulting in coastal erosion or sedimentation. Shoreline change detection through cost-effective methods and easy-access data plays a key role in coastal management, where other effective parameters such as land-use/land-cover (LULC) change should be considered. This paper presents a remotely sensed shoreline monitoring in Sandbanks Provincial Park, Ontario, Canada, from 1984 to 2021. The CoastSat toolkit for Python and a multilayer perceptron (MLP) neural network classifier were used for shoreline detection, and an unsupervised change detection framework followed by a postclassification change detection method was implemented for LULC classification and change detection. The study assessed the recent coastal erosion and accretion trends in the region in association with spatiotemporal changes in the total area of the West and East Lakes, the transition between LULC classes, extreme climate events, population growth, and future climate projection scenarios. The results of the study illustrate that the accretion trend apparently can be seen in most parts of the study area since 1984 and is affected by several factors, including lake water-level changes, total annual precipitations, sand movements, and other hydrologic/climatic parameters. Furthermore, the observed LULC changes could be in line with climate change-driven forces and population growth to accelerate the detected accretion trend in the East and West Lakes. In total, the synergistic interaction of the investigated parameters would result in a greater accretion trend along with a lower groundwater table amid even a low carbon scenario. The discussed findings could be beneficial to regional/provincial authorities, policymakers, and environmental advocates for the sustainable development of coastal communities.

Hydraulic Modeling and Remote Sensing Monitoring of Floodhazard in Arid Environments—A Case Study of Laayoune City in Saquia El Hamra Watershed Southern Morocco

Morocco often faces significant intense rainfall periods that can generate flash floods and raging torrents, causing serious damage in a very short period of time. This study aims to monitor wetland areas after a flash-flood event in an arid region, Saquia El hamra Saharan of Morocco, using a technique that combines hydraulic modeling and remote sensing technology, namely satellite images. The hydrological parameters of the watershed were determined by the WMS software. Flood flow was modeled and simulated using HEC HMS and HEC-RAS software. To map the flooded areas, two satellite images (Sentinel-2 optical images) taken before and after the event were used. Three classifications were carried out using two powerful classifiers: support vector machines and decision tree. The first classifier was applied on both dates’ images, and the resulting maps were used as input for a constructed decision tree model as a post-classification change detection process.

The South African land cover change detection derived from 2013_2014 and 2017_2018 land cover products

The appetite for up-to-date information about the earth’s surface is ever increasing, as such information provides a basis for a large number of applications. These include the earth’s resource detection and evaluation, land cover and land use change monitoring together with other vast environmental studies such as climate change assessment. Due to the advantages of repetitive data acquisition, the synoptic view, together with the varied spatial resolution it provides, and its available historically achieved dataset, remote sensing earth observation has become the major preferred data source for various earth studies. This study assesses land cover change detection of the land cover products (2013_2014 and 2017_2018) derived from earth observation.There are vast number of change detection methodologies and techniques with some still emerging. This study embarked on post classification change detection methodology which entailed morphological and spectral filtering techniques. The 10 land cover classes that were assessed for change detection are: natural wooded land, shrubland, grassland, waterbodies, wetlands, barren lands, cultivated, built-up, planted forest together with mines and quarries. The change detection accuracy result was 74.97%. Through the likelihood analysis, the likelihood for change to occur (e.g. cultivated to grassland) and unlikelihood of change to occur (e.g. built-up to planted forest), resulted in 72.2% areas of potential realistic change.The change detection results, further depend on the quality, compatibility and accuracy of the input land cover datasets. The application of different ancillary data together with different modelling techniques for land cover classification also affect the true reflectance of land cover change detection. Therefore extra caution should be exercised when analysing change detection so as to provide true and reliable changes.

The influence of urban expansion on landslide evolution. A case study in Cluj-Napoca Municipality.

In the case of Cluj-Napoca Municipality, the analysis of the landslides is a frequently discussed topic due to its complex geology and urban expansion tendency. In this study, we chose the Gruia Neighbourhood in order to map the landslide evolution and land-use/land-cover (LULC) changes which occured between 2003 and 2021. In order to use the post-classification Change Detection method, we applied the supervised classification technique on three satellite imageries (2003, 2009, 2021), which were validated by high Kappa coefficient values, as it follows: 0,892, 0,879 and 0,931. Comparing the three classified imageries, we could conclude that a transition between agricultural land to urban areas is visible, with a total decrease of the agricultural land by 40,69% and a total increase of the urban area by 24,47%. In the evaluation process of the influence of the LULC change on the landslide evolution, we could observe that the increase of the urban areas led to the increase of the surface of the landslides, moreover, the slided territories on urban areas have increased by 200%.

Dynamics and Prediction of Land Use and Land Cover Changes Using Geospatial Techniques in Abelti Watershed, Omo Gibe River Basin, Ethiopia

Ethiopia is a growing country which is in need of scientific ground for land use planning and agricultural-based economy. Evaluation of land use/land cover (LULC) changes helps for proper scheduling and use of natural resources with safe administration in accordance with time and dynamic population growth of the country, specifically in the study area. One of the detailed and useful ways to develop land use evaluation and classification maps is the use of geospatial techniques such as remote sensing and geographic information systems (GIS). The main focus of this study is to evaluate the dynamics of land use and land cover (LULC) changes in the Abelti Watershed, Omo-Gibe River basin, Ethiopia. Maximum likelihood algorithm approach supervised classification method was used for identifying the LULC changes using satellite data to know LULC changes in the watershed. Quantifications of spatial and temporal dynamics of land use/cover changes were accomplished by using three satellite images of 2000, 2010, and 2017 and classifying them via a supervised classification algorithm by using Earth Resources and Development System (ERDAS) software and finally applying the postclassification change detection technique was performed by using ArcGIS 10.3. From the LULC analysis, the increase was observed in the agricultural area and settlement area from 2000 to 2017. On the other hand, shrub land followed a declining trend during the study period. However, forest and bare land followed variable trends during the study period in which forest declined from 2000 to 2010 but increased from 2010 to 2017 and bare land increased from 2000 to 2010 and declined from 2010 to 2017. Generally, the driving force behind this change was population growth, rapid urbanization, and deforestation which resulted in a wide range of environmental impacts, including degraded habitat quality in the watershed.

Palm oil plantation transportation management improving using economic information systems and Qm-Windows

Limited information, mainly based on real economy as a tool for determining transportation infrastructure location, is one of the obstacles faced by oil palm plantation companies. This study aims to develop a management information system for transporting the Transportation of Fresh Fruit Bunches (FFB) in oil palm plantations with considering the economic analysis by combination of GIS and Qm-Windows. This research uses the descriptive method. The study was conducted at one of the oil palm plantations in Central Kalimantan. Data were analyzed using the post-classification change detection (PCCD) method and estimated costs using the transportation method with the Qm-Windows program’s help. The results showed that the GIS with Arcgis 10.1 application could compile an inventory information system for oil palm plantation transportation. Cost estimation based on the Qm-Windows application can be used to determine the priority of transportation selection estimation with minimum cost. These applications can be applied as reference considerations for policymaking in managing oil palm FFB transportation management.

Effects of Monocropping on Land Cover Transitions in the Wet Evergreen Agro-Ecological Zone of Ghana

The wet evergreen forest ecological zone of Ghana is undergoing notable structural changes, although most maps erroneously depict the area to be an intact forest. Several hectares of plantation agriculture such as rubber, oil palm, and cocoa are replacing the natural vegetation and habitats, thereby threatening indigenous biodiversity. This study aimed to assess the effects of tree monocrop proliferation on landscape transitions between 1986 and 2020 in the Wassa East District of Ghana. The ISODATA clustering technique was used to produce land cover category maps from Landsat images of 1986, 2002, and 2020. A post-classification change detection technique resulted in transition matrices which were used for the computation of land cover transition intensities over 34 years. The results showed that the landscape was dominated by forests in 1986. Still, the forest continuously declined by 34% (1% annually) in 2020 while all other land cover types increased in both periods with cocoa covering 23% oil palm covering 14%, and rubber covering 2% of the land area. These conversions in the land area are important, especially since the closed forests usually transition to monocrops through the intermediate process: food crop farming. This information is essential for decision making on land development and biodiversity conservation.

Change detection and future change prediction in Habra I and II block using remote sensing and GIS – A case study

Mapping, analysis, and monitoring of landuse and landcover in micro region is necessary for sustainable land development, planning and management. The present study is, therefore, aimed to identify the spatio-temporal change of LULC in two central administrative C.D. blocks of North 24 Parganas in West Bengal, India during period 1987-2020. To figure out the essence of the transition, the supervised classification along with post-classification change detection using the 'From'-'To' approach was employed. Furthermore, hotspot analysis has been utilized to identify all of the areas that are the most variable in terms of change potentiality. Besides, cellular automata were also introduced to find out the character of urban growth and future trend of LULC change. The results show that between 1987 and 2020, agricultural area and vegetation with settlement decreased by -11.60 % and -4.34 %, respectively, while dense set-tlement increased by +15.69 % due to significant population growth and overcrowding from neighboring countries. The prediction model also supports this argument. So, the very high and uncontrolled growth of urban settlement in the study area, may become a big challenge for the district authority to control the unplanned urban expansion.

Land Use/Land Cover change detection in the wetlands. A case study: Al-Aba Oasis, west of Ras Tanura, Kingdom of Saudi Arabia

In addition to unthinking anthropogenic meddling with the subtle ecological balance, the territories of Al-Aba Oasis are witnessing various Land Use and Land Cover (LULC) changes. Comprehending LULC is a central facet of upholding a sustainable, friendly, and fit environment. This paper presents a spatiotemporal study of land use and land cover trends in the wetlands of Al-Aba Oasis, an ecologically sensitive area in the west of Ras Tanura in the east of the Kingdom of Saudi Arabia. The study area faces several environmental problems, including the rise in groundwater levels, expansion of agricultural land, urban expansion, and anthropogenic interference with the ecological balance. In this paper, a verified representation of the changes in each LULC class has been made using satellite images. Remote sensing imagery is helpful for studying temporal changes in LULC and providing environmental monitoring data. We analysed Landsat-5 and Sentinel-2 imagery for 1985, 2000, and 2021. The overall precision besides the kappa coefficient for precision assessment indicates the relevance of the LULC classification. LULC map products were overlaid and interpreted based on post-classification change detection methods. The LULC aspects were classified into six classes: water body, waterlogged area, sabkha soil, sandy area, cultivated area, and built- up area. The results prove that from 2001 to 2021, the extension of the built-up area (2.6%) and agricultural land (6.85%) is directly proportional to the population growth (36.5% between 1992 and 2004) and the sabkhas are subject to constant metamorphosis under the joint influence of urban and agricultural land expansion. 100 samples were collected for the years 1986, 2001, and 2021 to assess the accuracy. We reviewed the outcomes of this study by evaluating the accuracy (77, 81, and 84% for 1986, 2001, and 2021 respectively) and comparing the field truth using a GPS (Global Positioning System) sensor. The results of this study are useful in the development of environmental policies during the development of sustainable territorial development programmes of the oasis.

Using land cover, population, and night light data to assess urban expansion in Kimberley, South Africa

ABSTRACT Information on urban expansion is a significant input in forecasting upcoming land cover and land use changes in a city. This study combines Landsat 8, night-time lights, and population data to assess urban expansion in Kimberley, South Africa from 2013 to 2018. This study used a post-classification change detection approach to measure urban expansion. Urban and non-urban land use classes where the two classes mapped and evaluated for this analysis. Overall, urban expansion from 2013 to 2018 was 15% while the annual urban expansion rate experienced was 0.6%. Night-time lights, calculated from satellite imagery, are increasingly used by social scientists as a proxy for economic activity or economic development. During the period of 2013 to 2018, both the urban night-time lights and the urban population experienced high rates of growth. This study obtained a positive correlation for night-time light and population datasets of 0.51 for 2013 and 0.57 for 2018, to suggest a positive population and lighting increase in the study area. Municipal authorities and policymakers may use this knowledge as feedback during urban and environmental planning.

Dynamics of Land Surface Temperature in Response to Land Use Land Cover Change in Phewa watershed, Kaski, Nepal

Geospatial tools play an important role in monitoring Land Use Land Cover Change (LULCC) and Land Surface Temperature (LST). This study assessed the extent of LULCC during 1990, 2007 and 2020 using temporal satellite imageries, and estimates LST during the study periods in relation to LULCC and explores various adaptation practices adopted in response to LST change in Phewa watershed. Landsat imageries were used for LULC classification and LST estimation. Purposive household survey (N=150), key informant survey (N=4), focus group discussion (N=4) and direct field observations were carried out to explore various adaptation practices. LULC maps was generated by using supervised classification followed by post classification change detection technique for LULCC analysis. Agricultural land and urban areas were found to have increased by 6.6% and 0.32% respectively while forest area, barren land and water bodies were found to have decreased by 1.88%, 4.41% and 0.63%, respectively, between 1990 and 2007. Forest area, urban areas and barren land had increased by 5.54%, 1.32% and 1.48%, respectively, while agricultural land and water bodies were observed to have decreased by 8.2% and 0.13%, respectively, between 2007 and 2020. The mean LST were 22.59° C, 22.81° C and 24.56° C in March-April and 14.65° C, 14.97° C and 15.27° C in January-December, respectively. Urban areas and water bodies exhibit highest and lowest mean values of LST, respectively, during study periods. LULCC due to urban growth and infrastructural developments had contributed to increase in LST. The highest rank to adaptation practices were for changes in cropping patterns and species, followed by agroforestry, use of improved seeds, shift to other income generation activities, use of more fertilizers, irrigation practices and growing vegetables in poly house which were statistically significant. This study provides scientific insights for policy makers and urban planners in improving urban planning and management.

Change Detection for Heterogeneous Remote Sensing Images with Improved Training of Hierarchical Extreme Learning Machine (HELM)

To solve the problems of susceptibility to image noise, subjectivity of training sample selection, and inefficiency of state-of-the-art change detection methods with heterogeneous images, this study proposes a post-classification change detection method for heterogeneous images with improved training of hierarchical extreme learning machine (HELM). After smoothing the images to suppress noise, a sample selection method is defined to train the HELM for each image, in which the feature extraction is respectively implemented for heterogeneous images and the parameters need not be fine-tuned. Then, the multi-temporal feature maps extracted from the trained HELM are segmented to obtain classification maps and then compared to generate a change map with changed types. The proposed method is validated experimentally by using one set of synthetic aperture radar (SAR) images obtained from Sentinel-1, one set of optical images acquired from Google Earth, and two sets of heterogeneous SAR and optical images. The results show that compared to state-of-the-art change detection methods, the proposed method can improve the accuracy of change detection by more than 8% in terms of the kappa coefficient and greatly reduce run time regardless of the type of images used. Such enhancement reflects the robustness and superiority of the proposed method.