Modeling Post-Disaster Urban Sprawl Trajectories Through ANN-Based Land Use/Land Cover Change Analysis and Scenario Projection

doi:10.21203/rs.3.rs-6550160/v1

Download PDF

Research Article

Modeling Post-Disaster Urban Sprawl Trajectories Through ANN-Based Land Use/Land Cover Change Analysis and Scenario Projection

https://doi.org/10.21203/rs.3.rs-6550160/v1

This work is licensed under a CC BY 4.0 License

Journal Publication

published 09 Dec, 2025

Read the published version in Applied Geomatics →

You are reading this latest preprint version

Urban expansion in the aftermath of natural disasters presents critical challenges to sustainable land use planning and environmental resilience. This study models post-disaster urban growth trajectories by analysing land use and land cover (LULC) changes from 2017 to 2025 and simulating future development scenarios up to 2040 using an Artificial Neural Network (ANN) integrated within the QGIS MOLUSCE module. Sentinel-2 satellite imagery and digital elevation models were employed to classify six LULC categories: built-up areas, croplands, rangelands, bare land, forested areas, and water bodies.

The methodology was applied to the Central District of Elazığ, Türkiye a region significantly affected by the 2020 earthquake. Results reveal a substantial 60.89% increase in built-up areas, primarily driven by rapid post-disaster reconstruction. This expansion has coincided with notable reductions in cropland and rangeland coverage, while forest and water body areas have increased due to afforestation projects and water-related infrastructure investments.

Scenario-based projections indicate that, if current urbanisation trends persist, pressure on ecologically sensitive and agriculturally valuable lands will likely intensify by 2040. The ANN model demonstrated high predictive accuracy, with an overall correctness of 97.52% and a Kappa coefficient of 0.96. Based on these findings, the study recommends integrated planning strategies that: (i) prevent development on fertile agricultural plains, (ii) incorporate ecological thresholds in urban site selection, (iii) avoid construction near seismic fault lines and water bodies, and (iv) promote green infrastructure solutions including ecological corridors, urban forests, and sustainable stormwater systems within post-disaster urban development frameworks.

Urban sprawl

LULC Change

Rural Encroachment

Artificial Neural Network

Post-Earthquake Urbanization

The conversion of natural or agricultural landscapes into urban areas constitutes a pressing concern for many countries and cities worldwide(Dadashpoor & Salarian, 2020; Nuissl et al., 2009). One of the most prominent consequences of development under rapid urbanisation and economic expansion has been the substantial transformation of rural LULC (Dumreicher, 2008; Kiss, 2000; Ma et al., 2018; Tian et al., 2012; Yang et al., 2015). Intensifying land-use competition has emerged as a key driver of the widespread and irreversible loss of natural areas (Lambin & Meyfroidt, 2011). A substantial body of research has demonstrated the negative impacts of urban sprawl on sustainable development. Environmentally, urban sprawl contributes to the degradation of water quality, loss of biodiversity and natural habitats, reduction of agricultural and environmentally sensitive lands, and the destruction of natural landscapes. It also leads to the increased fragmentation of ecosystems, changes in energy consumption patterns, the uncontrolled expansion of built-up areas, and spatial imbalances that significantly alter the structure and functionality of urban landscapes (Araya & Cabral, 2010; Bihamta et al., 2015; Johnson, 2001; Wright & Boorse, 2015). Furthermore, urban sprawl has significant implications for quality of life, including reduced levels of physical activity, increased car ownership, longer commuting distances, higher rates of motorway fatalities, and elevated health risks. Additional severe consequences include the destruction of ecologically valuable and unique natural areas, stratospheric ozone depletion, and the exacerbation of climate change. Urban sprawl also contributes to the decline of agricultural productivity by encroaching on farmland and discouraging cultivation. The term "sprawl" is used to describe the largely unplanned and continuous expansion of urban peripheries into rural areas, often without clear direction or defined boundaries, resulting in fragmented and inefficient urban growth (Festus et al., 2020). This perspective frequently highlights individual preferences for larger homes, private gardens, and quieter residential environments, suggesting that urban sprawl is primarily a manifestation of consumer-driven demand (Zhang, 2016).

This pattern of expansion has also exerted significant adverse effects on terrestrial biodiversity (Newbold et al., 2015) and the provision of ecosystem services (Costanza et al., 2014). Notably, deforestation has emerged as a major contributor to global greenhouse gas emissions (Tubiello et al., 2015; van Vliet, 2019). In addition, the expansion of agricultural land has been identified as a key driver of natural area loss, leading to widespread environmental degradation (Curtis et al., 2018; Helmut & Lambin, 2002). Urban sprawl has a direct impact on natural habitats by converting them into urban land uses (Güneralp et al., 2020; Ren et al., 2022). Additionally, it exerts indirect effects through various disturbances associated with expanding urban environments, including increased levels of noise, air, and water pollution (McDonald et al., 2019). At the European Union level, policy documents such as the European Landscape Convention (CEC, 2001, 2004, 2005; CoE, 2000), the European Spatial Development Plan (1999), and the guidelines associated with common structural and agricultural policy funding frameworks emphasize the need to limit land consumption and promote more sustainable land use practices (Nuissl et al., 2009). The impacts of urban expansion on natural habitats have been examined extensively in global-scale studies. For instance, it has been estimated that between 1985 and 2015, approximately 12% of urban growth occurred at the expense of grasslands, while 9% resulted in the loss of forested areas (Liu et al., 2020; Ren et al., 2022). The initial settlement of Elazığ, which constitutes the focus of this study, was established in Harput. Over time, settlements functionally linked to Harput gradually shifted towards the El-Aziz city center, which offered greater accessibility and transportation advantages. The Harput garrison town was originally founded on an area of 1.47 km². During the 19th century, as the settlement expanded from Harput towards the lower hamlets, approximately 3.22 km² of land was incrementally urbanised. This process reflects a form of rural encroachment, whereby previously undeveloped rural areas were absorbed into the growing urban fabric (Akdemir, 2014). The villages of the 19th century and the initial neighbourhoods that constituted the nuclei of Elazığ underwent a circular expansion process driven by population growth. During the period of spatial dispersion-referred to as agglomeration-the city expanded predominantly along the north-south axis. This expansion transformed the central business and commercial district into a focal "crucible" for urban activity, thereby accelerating population movements between the city centre and its periphery (Akdemir, 2013; Kaya & Akdemir, 2021). The expansion of Elazığ, largely shaped by the unplanned urban development of the past century, has led to the reduction—and in some cases, complete destruction of surrounding agricultural lands through improper land use. A total of 8,222.5 hectares of agricultural land in the Uluova and Elazığ Plains has been occupied by urban structures, industrial facilities, the airport, and the Keban Dam. Considering the region’s predominantly mountainous morphology and the scarcity of flat land suitable for agriculture, the extent of this occupation and degradation is particularly concerning (Karadoğan & Yaman, 2012). As a consequence of rapid urban development, the number of neighbourhoods in Elazığ has increased significantly over time. The number of neighbourhoods, which stood at 9 in 1950, rose to 14 by 1965, 28 by 1985, and reached 32 by 2007 (Karakaş, 2010). As of 2024, this number has grown to 69. In the same year, the city’s population reached 458,747 (URL 1, 2024). This study investigates the extent to which urban expansion contributed to the loss of natural areas both directly and indirectly between 2017 and 2024. To assess the impact of newly established settlements, particularly those developed following the 24 January 2020 earthquake, recent years were selected for analysis. Subsequently, a scenario analysis for the year 2040 was conducted using the QGIS MOLUSCE module and incorporated into the study.

2.1. Study Area

The Central District of Elazığ Province, which was significantly affected by the 24 January 2020 earthquake resulting in the loss of 41 lives and injuries to 1,607 individuals (Caglar et al., 2023) was selected as the study area (Fig. 1).

A common feature of the residential units constructed shortly after the earthquake is their location on the urban periphery. While both Karşıyaka Neighbourhood, located in the southeast, and Yemişlik Neighbourhood, situated to the south of the city, share this characteristic, they also exhibit notable differences. Karşıyaka Neighbourhood was heavily damaged during the earthquake and subsequently underwent complete demolition and reconstruction. In contrast, Yemişlik Neighbourhood was newly established in an undeveloped area south of the new ring road. Due to the availability of ample land and their distance from the city centre, construction activities in both neighbourhoods progressed rapidly (Ökde & Ekinci, 2022). This development contributed to the emergence of new residential areas and further accelerated urban sprawl (Fig. 2).

2.2. Obtaining the Data Used in the Analyses

The data used and their sources are detailed in Table 1.

Table 1

The types of data used in the study and their sources
Data Type	Data Used	Reference
LULC Data	Sentinel-2 Land Cover Explorer	(Esri, 2024)
Slope, Aspect, Elevation	Digital Elevation Model	(ASF, 2024)
Transportation Network Data	Open Street Map	(OSM, 2024)
Hydrology Data	Digital Elevation Model, Hydrology Tool	(ASF, 2024, ArcGIS 10.7)
2040 Scenario Analysis	MOLUSCE Tool	(QGIS, 2025)

2.3. Determination of Land Use Change Scenarios with QGIS MOLUSCE Method

In this study, the QGIS MOLUSCE plug-in, which has been widely adopted by researchers for modeling land use/land cover (LULC) changes and projecting future scenarios, was employed to analyze current trends and simulate potential future land use Dynamics (Alshari & Gawali, 2022; Amgoth et al., 2023; Baghel et al., 2024; Bathe & Patil, 2024; Gündüz, 2025; Iskandar et al., 2024; Kamaraj & Rangarajan, 2022; Muhammad et al., 2022).

The application of the QGIS MOLUSCE plug-in for detecting land use/land cover (LULC) changes comprises four fundamental steps (Farda, 2017; Isnain & Said, 2019; Schultz et al., 2017). In the first step, essential spatial data such as satellite imagery, land cover maps, and other relevant geographic information are collected and subjected to pre-processing. In this study, slope, aspect, elevation classes, distance to rivers, and distance to roads were selected as explanatory variables. The second step involves the analysis of spatial changes between two time points, T1 and T2, to identify LULC transformations over the observed period (Gündüz, 2025). To assess land use changes in the Elazığ city center and conduct comparative analyses across the two periods, remote sensing techniques were combined with visual interpretation methods.

Sentinel-2 satellite imagery was utilized for land use classification, and the digitization process was conducted using ArcGIS 10.7 Geographic Information Systems (GIS) software. In the third stage, land use change was modeled using Artificial Neural Network (ANN) methods. In the final stage, the simulated LULC maps were compared with reference LULC maps to assess the accuracy of the simulation outcomes. During this evaluation, several performance metrics were employed, including overall accuracy, Kappa (overall) \(\:{K}_{o}\);, Kappa (histogram) \(\:{K}_{h}\), Kappa (location) \(\:{K}_{l}\), and accuracy percentage (Baghel et al., 2024; Bathe & Patil, 2024; Gündüz, 2025; Kafy et al., 2021). The variables required for the modeling process were identified based on previous studies (Alrubkhi, 2017; Aneesha Satya et al., 2020; Bolat & Doğan, 2022; Guidigan et al., 2019; Rahman et al., 2017). In addition to commonly used factors such as elevation, slope, aspect, distance to rivers, and distance to roads, other spatial variables including distance to railways, distance to fault lines, and distance to the reservoir were also incorporated into the analysis.

3.1. LULC in 2017

An examination of land use in Elazığ province in 2017 reveals that rangeland constituted the largest land use category (Fig. 3).

Based on the 2017 LULC datas for Elazığ province, 20,360.90 ha (9.17%) of the area was classified as water bodies, 241.14 ha (0.11%) as forest areas (trees), 85,872.61 ha (38.68%) as crops, 12,029.17 ha (5.42%) as built areas, 3,907.75 ha (1.76%) as bare land, and 99,618.94 ha (44.87%) as rangeland (Table 2).

Table 2

2017 Elazığ province LULC datas
Land Use	Area (Ha)	Percent
Bare	3905.83	1.76
Built	12029.66	5.42
Crops	85875.36	38.68
Range	99617.03	44.87
Trees	241.10	0.11
Water	20361.53	9.17
Total	222030.51	100

3.2. LULC in 2025

An analysis of the 2025 land use in Elazığ province indicates that, similar to 2017, rangelands remain the dominant land use category (Fig. 4).

According to the 2025 land use data for Elazığ province, 22,845.21 ha (10.29%) of the area is classified as water bodies, 571.90 ha (0.26%) as forest areas (trees), 85,348.75 ha (38.44%) as crops, 19,353.54 ha (8.72%) as built areas, 790.21 ha (0.36%) as bare land, and 93,120.61 ha (41.94%) as rangeland (Table 3).

Table 3

2025 Elazığ province LULC datas
Land Use	Area	Percent
Bare	790.05	0.36
Built	19349.66	8.71
Crops	85348.91	38.44
Range	93126.7	41.94
Trees	571.58	0.26
Water	22843.61	10.29
Total	222030,51	100

3.3. 2017–2025 LULC Change

An analysis of land use changes between 2017 and 2025 in the city centre of Elazığ reveals a 3.30% increase in built-up areas, expanding from 12,029.66 ha to 19,349.66 ha. This growth is primarily attributed to the development of new residential zones following the earthquake, driven by the need for safer housing options. Additionally, within the framework of the Murat River Basin Rehabilitation Project, which was completed in 2023, afforestation efforts within the central district led to an increase in forested (tree-covered) areas by 0.15%, rising from 241.10 ha to 571.58 ha. In contrast, bare lands experienced a notable decrease of 1.40%, shrinking from 3,905.83 ha to 790.05 ha (Table 4).

Table 4

LULC change between 2017–2025
	Area (2017)	Area (2025)	∆	2017%	2024%	∆ %
Bare	3905.83 ha	790.05 ha	-3115.78 ha	1.76	0.36	-1.40
Built	12029.66 ha	19349.66 ha	7320.00 ha	5.42	8.71	3.30
Crops	85875.36 ha	85348.91 ha	-526.45 ha	38.68	38.44	-0.24
Range	99617.03 ha	93126.70 ha	-6490.33 ha	44.87	41.94	-2.92
Trees	241.10 ha	571.58 ha	330.48 ha	0.11	0.26	0.15
Water	20361.53 ha	22843.61 ha	2482.08 ha	9.17	10.29	1.12

With regard to other land use classes, agricultural land (crops) decreased by 0.24%, from 85,875.36 ha to 85,348.91 ha, while rangelands declined by 2.92%, from 99,617.03 ha to 93,126.70 ha. In contrast, water bodies increased by 1.12%, rising from 20,361.53 ha to 22,843.61 ha (Fig. 5). This increase is likely associated with the construction of irrigation and livestock watering ponds within the central district, implemented as part of the Murat River Basin Rehabilitation Project (Fig. 5).

How land use has changed is detailed in Fig. 6.

3.4. 2040 LULC Scenario

In determining the 2040 LULC scenario, several spatial variables were considered, including slope, aspect, distance to fault lines, distance to rivers, distance to railways, distance to roads, and distance to reservoirs and water bodies. To assess the relationships among these variables, Pearson's correlation method was employed. The correlation matrix summarizing the strength and direction of these relationships is presented in Table 5.

Table 5

Pearson correlation results
	Slope	Distance to Faults	Distance to Rivers	Distance to Railways	Distance to Roads	Distance to Waterbodies
Aspect	0.0815	0.0128	0.0646	-0.0050	-0.1067	0.1351
Slope		-0.0596	0.0470	-0.0121	0.1894	0.1139
Distance to Faults			0.2997	0.8824	0.2491	0.1660
Distance to Rivers				0.3174	-0.0002	0.2979
Distance to Railways					0.2882	0.1501
Distance to Roads						-0.1396

Pearson correlation analysis was conducted to examine the relationships between the morphometric and spatial variables evaluated in the study. The resulting symmetrical correlation matrix offers valuable insights into the direction and strength of linear associations among the variables.

The analysis revealed a very strong positive correlation between the variables "Distance to Faults" and "Distance to Rivers" (r = 0.882), suggesting that fault lines and river systems within the study area are either spatially distant from one another or follow a parallel distribution pattern. Furthermore, a perfect correlation was observed between "Distance to Rivers" and "Distance to Railways" (r = 1.000), indicating a significant spatial overlap between these two features.

Among the moderate positive correlations, notable relationships were identified between "Slope" and "Distance to Roads" (r = 0.189), and between "Distance to Faults" and "Distance to Railways" (r = 0.249). These findings imply that topographic slope and proximity to fault lines may indirectly influence the spatial alignment of transportation networks such as roads and railways.

Negative correlations were generally weak. For instance, the slight negative correlation between "Aspect" and "Distance to Roads" (r = -0.106) may reflect subtle location preferences of transportation infrastructure in relation to terrain orientation. However, due to the low magnitude of this correlation, its statistical significance and interpretive value remain limited (Fig. 7).

An analysis of the learning curve of the artificial neural network (ANN) model during the training process reveals a marked decrease in the loss values for both the training and validation datasets in the initial stages. The rapid decline in loss, particularly within the first 20 epochs, indicates that the model effectively adapts to the learning process. Following approximately the 50th epoch, both loss curves reach minimal values and stabilize, suggesting that the model successfully converges by the end of the training phase. Moreover, the close alignment between training and validation loss values demonstrates the model’s strong generalization ability and indicates a low risk of overfitting. These findings collectively suggest that the ANN model exhibits stable and robust performance across both training and validation datasets (Fig. 8).

The accuracy and Kappa coefficient values obtained from the classification analysis indicate that the model yields highly reliable and consistent results. According to the analysis, the overall accuracy was calculated as 97.52%, demonstrating that a substantial proportion of the classified samples were correctly identified, and the classification process was largely successful.

The evaluation of Kappa coefficients further underscores the robustness of the classification, independent of chance agreement. The \(\:{K}_{o}\) coefficient of 0.96227 corresponds to an “almost perfect agreement,” suggesting that the model performs significantly better than random classification. Similarly, the \(\:{K}_{h}\) value (0.96315) confirms that the classification is consistently accurate across all land use classes. Notably, the \(\:{K}_{l}\) coefficient of 0.99909 reflects an exceptionally high level of spatial accuracy, indicating that the model performs extremely well in predicting the correct locations of land use types.

Collectively, these performance metrics highlight the high contextual and spatial reliability of the classification method and affirm the scientific robustness of the results (Basheer et al., 2022; Cohen, 1960; Sajan et al., 2022; Zhang, 2016). The projected land use changes under the 2040 urban sprawl scenario for Elazığ are presented in Table 6.

Table 6

2040 Elazığ province LULC datas
Land Use	Area	Percent
Bare	781.21	0.35
Built	19336.31	8.71
Crops	85362.58	38.45
Range	93138.45	41.95
Trees	567.57	0.26
Water	22844.40	10.29
Total	222030.51	100

In the development of the 2040 land use scenario, a correlation analysis was conducted to evaluate the relationships among key spatial variables, including slope, aspect, distance to fault lines, distance to rivers, and distance to railways. The detailed correlation matrix, which illustrates the associations between these variables and their potential influence on land use change, is presented in Fig. 9.

An examination of land use data for the period 2017–2025 in the Elazığ Central District reveals that spatial transformation in the region has primarily occurred along the axes of urban sprawl, loss of natural areas, and the conversion of agricultural lands. The most prominent change during this period is a 60.89% increase in built-up areas. This substantial growth indicates a pattern of urban expansion from the city center toward peripheral zones and reflects zoning policies that appear to favor construction activities. Moreover, this trend aligns with existing literature, which highlights that post-disaster housing policies in developing countries often promote settlement expansion into rural areas (Araya & Cabral, 2010; Seto et al., 2012). Critics contend that urban sprawl results in inefficient land use, escalates infrastructure development costs, and fosters automobile dependency, all of which collectively undermine the sustainability and vitality of urban centres (Palmieri & Serre, 2019). Similar patterns of urban expansion have been observed in many developing cities across Turkey (Güneş, 2021; Hayrullahoğlu et al., 2021).

The expansion of settlement areas has occurred in inverse proportion to the decline in natural land cover classes. Notably, bare lands experienced a substantial reduction of 79.97%, indicating that urban development has predominantly taken place on previously unused or vacant land. However, the decrease of 6.52% in rangelands and 0.61% in croplands highlights that urban growth is not confined to idle spaces but is also encroaching upon productive rural areas. This trend raises concerns regarding its potential long-term impacts on food security, rural development, and biodiversity conservation (Seto et al., 2012).

On the other hand, tree covered areas exhibited the highest proportional increase, rising by 137.17%. This significant change may be attributed to afforestation efforts undertaken within the city, the implementation of landscaping projects, or improvements in the accuracy of classification methods. However, the sustainability of such increases warrants further evaluation based on criteria such as the species of trees planted, the spatial extent of the afforested areas, and the continuity and ecological functionality of these landscapes (Barredo & Demicheli, 2003).

Similarly, the 12.21% increase observed in water bodies suggests that the hydrological infrastructure in Elazığ such as dams, ponds, and flood control systems has undergone notable changes in parallel with urban development. Elazığ, particularly recognized for its proximity to the Keban Dam, exhibits a spatial utilization of water resources that differs from the national average in Turkey.

According to the 2040 scenario maps generated through Artificial Neural Network (ANN) supported MOLUSCE modeling, it is projected that construction pressure on natural areas will intensify if current development trends persist. The model demonstrates a high level of predictive reliability, with an overall accuracy of 97.52% and an \(\:{K}_{o}\) coefficient of 0.96, underscoring the robustness of its estimations (Basheer et al., 2022; Sajan et al., 2022).

The 2040 scenario further suggests that if existing planning policies remain unchanged, the spatial development of Elazığ will continue in a manner inconsistent with the principles of sustainability. In this context, it becomes evident that to manage future urbanization trends, the establishment of ecological corridors, strict protection of agricultural lands, and the imposition of limits on construction pressure are essential measures (Lambin & Meyfroidt, 2011; Palmieri & Serre, 2019).

In light of these findings, it can be concluded that urban sprawl in Elazığ Central District has occurred in a low-density yet spatially impactful manner, producing observable effects on ecological systems, rural landscapes, and socio-economic structures. Comparable spatial dynamics have been reported in other rapidly developing cities across Turkey (Ewing & Hamidi, 2015). This pattern of urbanization highlights the urgent need for integrated green infrastructure strategies, a balanced rural–urban interface, and the adoption of sustainable land use policies in future planning initiatives.

This study analyzes land use changes in the Elazığ Central District between 2017 and 2025 and presents a spatial projection of urban sprawl for the year 2040. The results, derived from satellite imagery, geographic information systems (GIS), and artificial neural network-based MOLUSCE modeling, demonstrate a significant expansion of urban boundaries in recent years—particularly following the 2020 Elazığ earthquake.

The findings are consistent with existing literature indicating that urban sprawl poses a serious threat to sustainable urban development and underscore the urgent need for integrated policy responses. A notable increase of over 60% in built-up areas between 2017 and 2025 was identified, suggesting that much of the expansion has occurred on previously vacant or natural land. Moreover, observed reductions in agricultural and rangeland areas, such as croplands and pastures, indicate that urban growth also encroaches upon productive rural landscapes. Conversely, increases in tree-covered and water areas—linked to afforestation and irrigation projects—suggest that environmental rehabilitation efforts have yielded some positive outcomes.

Despite these insights, the study has certain limitations. The analysis is confined to regional characteristics, and future comparative research in regions with differing geographic and socioeconomic conditions could offer a broader understanding of the phenomenon. It is also crucial that forthcoming studies investigate the long-term impacts of urban sprawl and assess the feasibility of implementing targeted, solution-oriented strategies.

Overall, the results reveal that spatial expansion in developing cities such as Elazığ is driven not only by factors like population growth and post-disaster resettlement but also by deficiencies in planning and land management practices. To mitigate the environmental, economic, and social consequences of unplanned urban sprawl, it is imperative to strengthen legal and administrative frameworks for the protection of agricultural land, define urban growth boundaries to contain expansion, and incorporate ecological corridors and green infrastructure into planning processes. Furthermore, post-disaster housing policies should align with the principles of spatial sustainability, and long-term urban development strategies should be informed by AI-supported spatial modeling tools.

In conclusion, this study not only demonstrates the tangible spatial impacts of urban sprawl but also contributes to the development of scientifically grounded future projections. The findings may serve as a valuable reference not only for Elazığ but also for other medium-sized cities exhibiting similar structural characteristics.

Funding

The author received no financial support for the research

Conflict of Interest

The author declare no conflict of interest.

All authors have read, understood, and have complied as applicable with the statement on “Ethical responsibilities of Authors” as found in the Instructions for Authors.

Akdemir, I. O. (2013). Elazığ’ın kentleşme sürecinin coğrafi analizi. Geçmişten Geleceğe Harput Sempozyumu, 1033–1054.
Akdemir, I. O. (2014). Periferik kentleşme süresinin etkenleri: Elazığ modeli. Fırat Üniversitesi Harput Araştırmaları Dergisi, 1(2), 131–150.
Alrubkhi, A. (2017). Land use change analysis and modeling using open source ( QGIS ) case study: Boasher Willayat. Sultan Qaboos University College Of Arts and Social Science.
Alshari, E. A., & Gawali, B. W. (2022). Modeling land use change in Sana’a City of Yemen with MOLUSCE. Journal of Sensors, 2022, 1–15. https://doi.org/10.1155/2022/7419031
Amgoth, A., Rani, H. P., & Jayakumar, K. V. (2023). Exploring LULC changes in Pakhal Lake area, Telangana, India using QGIS MOLUSCE plugin. Spatial Information Research, 31(4), 429–438. https://doi.org/10.1007/s41324-023-00509-1
Aneesha Satya, B., Shashi, M., & Deva, P. (2020). Future land use land cover scenario simulation using open source GIS for the city of Warangal, Telangana, India. Applied Geomatics, 12(3), 281–290. https://doi.org/10.1007/s12518-020-00298-4
Araya, Y. H., & Cabral, P. (2010). Analysis and modeling of urban land cover change in Setúbal and Sesimbra, Portugal. Remote Sensing, 2(6), 1549–1563. https://doi.org/10.3390/rs2061549
ASF. (2024). ALOS PALSAR. Https://Search.Asf.Alaska.Edu/#/?Zoom=9.322&center=39.889,38.093&dataset=ALOS&polygon=POLYGON((38.5125%2038.0636,40.0474%2038.0636,40.047
4%2039.1546,38.5125%2039.1546,38.5125%2038.0636))&resultsLoaded=true&granule=ALPSRS106522850-L1.5.
Baghel, S., Kothari, M. K., Tripathi, M. P., Singh, P. K., Bhakar, S. R., Dave, V., & Jain, S. K. (2024). Spatiotemporal LULC change detection and future prediction for the Mand catchment using MOLUSCE tool. Environmental Earth Sciences, 83(2), 66. https://doi.org/10.1007/s12665-023-11381-5
Barredo, J. I., & Demicheli, L. (2003). Urban sustainability in developing countries’ megacities: modelling and predicting future urban growth in Lagos. Cities, 20(5), 297–310. https://doi.org/10.1016/S0264-2751(03)00047-7
Basheer, S., Wang, X., Farooque, A. A., Nawaz, R. A., Liu, K., Adekanmbi, T., & Liu, S. (2022). Comparison of land use land cover classifiers using different satellite imagery and machine learning techniques. Remote Sensing, 14(19), 4978. https://doi.org/10.3390/rs14194978
Bathe, K. D., & Patil, N. S. (2024). Assessment of land use-land cover dynamics and its future projection through Google Earth Engine, machine learning and QGIS-MOLUSCE: A case study in Jagatsinghpur district, Odisha, India. Journal of Earth System Science, 133(2), 111. https://doi.org/10.1007/s12040-024-02305-3
Bihamta, N., Soffianian, A., Fakheran, S., & Gholamalifard, M. (2015). Using the SLEUTH Urban Growth Model to Simulate Future Urban Expansion of the Isfahan Metropolitan Area, Iran. Journal of the Indian Society of Remote Sensing, 43(2), 407–414. https://doi.org/10.1007/s12524-014-0402-8
Bolat, S., & Doğan, M. (2022). Uzun dönemli (1984-2020) arazi kullanımı değişiminin tespiti ve modellemesi (2035): Gölcük İlçesi’nin analizi. Coğrafya Dergisi, 2022(44), 169–181. https://doi.org/10.26650/JGEOG2022-997334
Caglar, N., Vural, I., Kirtel, O., Saribiyik, A., & Sumer, Y. (2023). Structural damages observed in buildings after the January 24, 2020 Elazığ-Sivrice earthquake in Türkiye. Case Studies in Construction Materials, 18, e01886. https://doi.org/10.1016/j.cscm.2023.e01886
CEC. (2001). A sustainable Europe for a better world: A European Union strategy for sustainable development.
CEC. (2004). Commission’s communication ‘Towards a thematic strategy in the urban environment.’
CEC. (2005). Impact assessment guidelines.
CoE. (2000). European landscape convention.
Costanza, R., de Groot, R., Sutton, P., van der Ploeg, S., Anderson, S. J., Kubiszewski, I., Farber, S., & Turner, R. K. (2014). Changes in the global value of ecosystem services. Global Environmental Change, 26, 152–158. https://doi.org/10.1016/j.gloenvcha.2014.04.002
Curtis, P. G., Slay, C. M., Harris, N. L., Tyukavina, A., & Hansen, M. C. (2018). Classifying drivers of global forest loss. Science, 361(6407), 1108–1111. https://doi.org/10.1126/science.aau3445
Dadashpoor, H., & Salarian, F. (2020). Urban sprawl on natural lands: analyzing and predicting the trend of land use changes and sprawl in Mazandaran city region, Iran. Environment, Development and Sustainability, 22(2), 593–614. https://doi.org/10.1007/s10668-018-0211-2
Dumreicher, H. (2008). Chinese villages and their sustainable future: the European Union-China-Research Project “SUCCESS.” J. Environ. Manag., 87(2008), 204–215.
Esri. (2024). Sentinel-2 land cover explorer. Https://Livingatlas.Arcgis.Com/Landcoverexplorer/#mapCenter=-154.87343%2C19.47701%2C11&mode=step&timeExtent=2017%2C2023&year=2023.
Ewing, R., & Hamidi, S. (2015). Measuring urban sprawl and validating sprawl measures.
Farda, N. M. (2017). Multi-temporal land use mapping of coastal wetlands area using machine learning in Google Earth Engine. IOP Conference Series: Earth and Environmental Science, 98, 012042. https://doi.org/10.1088/1755-1315/98/1/012042
Festus, I. A., Omoboye, I. F., & Andrew, O. B. (2020). Urban sprawl: Environmental consequence of rapid urban expansion. Malaysian Journal of Social Sciences and Humanities (MJSSH), 5(6), 110–118. https://doi.org/10.47405/mjssh.v5i6.411
Guidigan, M. L. G., Sanou, C. L., Ragatoa, D. S., Fafa, C. O., & Mishra, V. N. (2019). Assessing land use/land cover dynamic and its impact in Benin Republic using land change model and CCI-LC products. Earth Systems and Environment, 3(1), 127–137. https://doi.org/10.1007/s41748-018-0083-5
Gündüz, H. I. (2025). Land-use land-cover dynamics and future projections using GEE, ML, and QGIS-MOLUSCE: A case study in Manisa. Sustainability, 17(4), 1363. https://doi.org/10.3390/su17041363
Güneralp, B., Reba, M., Hales, B. U., Wentz, E. A., & Seto, K. C. (2020). Trends in urban land expansion, density, and land transitions from 1970 to 2010: a global synthesis. Environmental Research Letters, 15(4), 044015. https://doi.org/10.1088/1748-9326/ab6669
Güneş, P. (2021). Kentsel büyüme, yayılma ve kentsel saçaklanma ile gayrimenkul piyasası ilişkilerinin değerlendirilmesi: Ankara ili Alacaatlı, Bağlıca ve Dodurga mahalle örnekleri [Yüksek Lisans]. Fen Bilimleri Enstitüsü.
Hayrullahoğlu, G., Tanrıvermiş, Y. A., & Tanrıvermiş, H. (2021). Kentsel yayılma alanları ve bu alanlardaki konut talebi üzerine nitel bir araştırma. İdealkent, 12(34), 1413–1439.
Helmut, J. G., & Lambin, E. F. (2002). Proximate causes and underlying driving forces of tropical deforestation: Tropical forests are disappearing as the result of many pressures, both local and regional, acting in various combinations in different geographical locations. BioScience, 52(2), 143–150.
Iskandar, B., Kurnia, A. A., Jauhari, A., & Zannah, F. (2024). Modeling land cover change using MOLUSCE in Kahayan Tengah forest management unit, Kalimantan Tengah. Jurnal Sylva Lestari, 12(2), 242–257.
Isnain, Z., & Said, S. J. (2019). Using the geographical information system (GIS) methods in determination of landuse changes at Batu Sapi, Sandakan, Sabah, Malaysia. Journal of Physics: Conference Series, 1358(1), 012069. https://doi.org/10.1088/1742-6596/1358/1/012069
Johnson, M. P. (2001). Environmental impacts of urban sprawl: A survey of the literature and proposed research agenda. Environment and Planning A: Economy and Space, 33(4), 717–735. https://doi.org/10.1068/a3327
Kafy, A. A., Faisal, A. A., Shuvo, R. M., Naim, Md. N. H., Sikdar, Md. S., Chowdhury, R. R., Islam, Md. A., Sarker, Md. H. S., Khan, Md. H. H., & Kona, M. A. (2021). Remote sensing approach to simulate the land use/land cover and seasonal land surface temperature change using machine learning algorithms in a fastest-growing megacity of Bangladesh. Remote Sensing Applications: Society and Environment, 21, 100463. https://doi.org/10.1016/j.rsase.2020.100463
Kamaraj, M., & Rangarajan, S. (2022). Predicting the future land use and land cover changes for Bhavani basin, Tamil Nadu, India, using QGIS MOLUSCE plugin. Environmental Science and Pollution Research, 29(57), 86337–86348. https://doi.org/10.1007/s11356-021-17904-6
Karadoğan, S., & Yaman, A. (2012). Geri gelmemek üzere kaybolup giden tarım topraklarımız (Elazığ Ovası ve Uluova örneği). 7. Karaburun Bilim Kongresi, 1–9.
Karakaş, E. (2010). Şehir nüfus dağılımında sosyal ve ekonomik faktörlerin etkisi, Elazığ örneği. Nature Sciences, 5(3), 240–254.
Kaya, A. Y., & Akdemir, I. O. (2021). Kentsel değişim-kent imgesi korelasyonu: Elazığ örneği. Fırat Üniversitesi Sosyal Bilimler Dergisi, 31(1), 1–23.
Kiss, E. (2000). Rural restructuring in Hungary in the period of socio-economic transition. GeoJournal, 51(3), 221–233. https://doi.org/10.1023/A:1017507328301
Lambin, E. F., & Meyfroidt, P. (2011). Global land use change, economic globalization, and the looming land scarcity. Proceedings of the National Academy of Sciences, 108(9), 3465–3472. https://doi.org/10.1073/pnas.1100480108
Liu, X., Huang, Y., Xu, X., Li, X., Li, X., Ciais, P., Lin, P., Gong, K., Ziegler, A. D., Chen, A., Gong, P., Chen, J., Hu, G., Chen, Y., Wang, S., Wu, Q., Huang, K., Estes, L., & Zeng, Z. (2020). High-spatiotemporal-resolution mapping of global urban change from 1985 to 2015. Nature Sustainability, 3(7), 564–570. https://doi.org/10.1038/s41893-020-0521-x
Ma, W., Jiang, G., Li, W., & Zhou, T. (2018). How do population decline, urban sprawl and industrial transformation impact land use change in rural residential areas? A comparative regional analysis at the peri-urban interface. Journal of Cleaner Production, 205, 76–85. https://doi.org/10.1016/j.jclepro.2018.08.323
McDonald, R. I., Mansur, A. V., Ascensão, F., Colbert, M., Crossman, K., Elmqvist, T., Gonzalez, A., Güneralp, B., Haase, D., Hamann, M., Hillel, O., Huang, K., Kahnt, B., Maddox, D., Pacheco, A., Pereira, H. M., Seto, K. C., Simkin, R., Walsh, B., … Ziter, C. (2019). Research gaps in knowledge of the impact of urban growth on biodiversity. Nature Sustainability, 3(1), 16–24. https://doi.org/10.1038/s41893-019-0436-6
Muhammad, R., Zhang, W., Abbas, Z., Guo, F., & Gwiazdzinski, L. (2022). Spatiotemporal change analysis and prediction of future land use and land cover changes using QGIS MOLUSCE plugin and remote sensing big data: A case study of Linyi, China. Land, 11(3), 419. https://doi.org/10.3390/land11030419
Newbold, T., Hudson, L. N., Hill, S. L. L., Contu, S., Lysenko, I., Senior, R. A., Börger, L., Bennett, D. J., Choimes, A., Collen, B., Day, J., De Palma, A., Díaz, S., Echeverria-Londoño, S., Edgar, M. J., Feldman, A., Garon, M., Harrison, M. L. K., Alhusseini, T., … Purvis, A. (2015). Global effects of land use on local terrestrial biodiversity. Nature, 520(7545), 45–50. https://doi.org/10.1038/nature14324
Nuissl, H., Haase, D., Lanzendorf, M., & Wittmer, H. (2009). Environmental impact assessment of urban land use transitions—A context-sensitive approach. Land Use Policy, 26(2), 414–424. https://doi.org/10.1016/j.landusepol.2008.05.006
Ökde, F., & Ekinci, E. (2022). Depremlerin kentsel dönüşüm uygulamalarına etkisi: 2020 Elazığ depremi örneği. Kent Akademisi, 15(3), 1223–1245. https://doi.org/10.35674/kent.1016589
OSM. (2024). Open Street Map. Https://Www.Openstreetmap.Org/Export#map=12/40.9153/40.4714.
Palmieri, T., & Serre, M. (2019). Experimenting intermediate lived spaces in residential subdivisions: Action, interaction and storytelling. SHS Web of Conferences, 64, 01002. https://doi.org/10.1051/shsconf/20196401002
QGIS. (2025). QGIS 3.40.4. qgis.org.
Rahman, M. T. U., Tabassum, F., Rasheduzzaman, M., Saba, H., Sarkar, L., Ferdous, J., Uddin, S. Z., & Zahedul Islam, A. Z. M. (2017). Temporal dynamics of land use/land cover change and its prediction using CA-ANN model for southwestern coastal Bangladesh. Environmental Monitoring and Assessment, 189(11), 565. https://doi.org/10.1007/s10661-017-6272-0
Ren, Q., He, C., Huang, Q., Shi, P., Zhang, D., & Güneralp, B. (2022). Impacts of urban expansion on natural habitats in global drylands. Nature Sustainability, 5(10), 869–878. https://doi.org/10.1038/s41893-022-00930-8
Sajan, B., Mishra, V. N., Kanga, S., Meraj, G., Singh, S. K., & Kumar, P. (2022). Cellular automata-based artificial neural network model for assessing past, present, and future land use/land cover dynamics. Agronomy, 12(11), 2772. https://doi.org/10.3390/agronomy12112772
Schultz, M., Voss, J., Auer, M., Carter, S., & Zipf, A. (2017). Open land cover from OpenStreetMap and remote sensing. International Journal of Applied Earth Observation and Geoinformation, 63, 206–213. https://doi.org/10.1016/j.jag.2017.07.014
Seto, K. C., Güneralp, B., & Hutyra, L. R. (2012). Global forecasts of urban expansion to 2030 and direct impacts on biodiversity and carbon pools. Proceedings of the National Academy of Sciences, 109(40), 16083–16088. https://doi.org/10.1073/pnas.1211658109
Tian, G., Qiao, Z., & Zhang, Y. (2012). The investigation of relationship between rural settlement density, size, spatial distribution and its geophysical parameters of China using Landsat TM images. Ecological Modelling, 231, 25–36. https://doi.org/10.1016/j.ecolmodel.2012.01.023
Tubiello, F. N., Salvatore, M., Ferrara, A. F., House, J., Federici, S., Rossi, S., Biancalani, R., Condor Golec, R. D., Jacobs, H., Flammini, A., Prosperi, P., Cardenas‐Galindo, P., Schmidhuber, J., Sanz Sanchez, M. J., Srivastava, N., & Smith, P. (2015). The contribution of agriculture, forestry and other land use activities to global warming, 1990–2012. Global Change Biology, 21(7), 2655–2660. https://doi.org/10.1111/gcb.12865
URL 1. (2024, November 25). Merkez mahalle ve köyleri, Elazığ. Https://Www.Nufusune.Com/Merkez-Mahalleleri-Koyleri-Elazig.
van Vliet, J. (2019). Direct and indirect loss of natural area from urban expansion. Nature Sustainability, 2(8), 755–763. https://doi.org/10.1038/s41893-019-0340-0
Wright, R., & Boorse, D. F. (2015). Environmental science: Towards a sustainable future. Pearson.
Yang, R., Liu, Y., Long, H., & Qiao, L. (2015). Spatio-temporal characteristics of rural settlements and land use in the Bohai Rim of China. Journal of Geographical Sciences, 25(5), 559–572. https://doi.org/10.1007/s11442-015-1187-6
Zhang, X. Q. (2016). The trends, promises and challenges of urbanisation in the world. Habitat International, 54, 241–252. https://doi.org/10.1016/j.habitatint.2015.11.018

No competing interests reported.

Download PDF

Journal Publication

published 09 Dec, 2025

Read the published version in Applied Geomatics →

Editorial decision: Revision requested
31 Jul, 2025
Reviews received at journal
29 Jul, 2025
Reviewers agreed at journal
03 Jul, 2025
Reviewers invited by journal
02 Jul, 2025
Editor assigned by journal
30 Apr, 2025
Submission checks completed at journal
30 Apr, 2025
First submitted to journal
28 Apr, 2025

You are reading this latest preprint version

Modeling Post-Disaster Urban Sprawl Trajectories Through ANN-Based Land Use/Land Cover Change Analysis and Scenario Projection

Status:

Journal Publication

Version 1

Abstract

Figures

1. INTRODUCTION

2. MATERIAL AND METHODS

2.1. Study Area

2.2. Obtaining the Data Used in the Analyses

2.3. Determination of Land Use Change Scenarios with QGIS MOLUSCE Method

3. RESULTS AND DISCUSSION

3.1. LULC in 2017

3.2. LULC in 2025

3.3. 2017–2025 LULC Change

3.4. 2040 LULC Scenario

4. CONCLUSION AND RECOMMENDATIONS

Declarations

References

Additional Declarations

Status:

Journal Publication

Version 1