Land Use/Land Cover Changes Detection in Lagos City of Nigeria Using Remote Sensing and GIS

Katabarwa Murenzi Gilbert, Yishao Shi^*

College of Surveying and Geo-Informatics, Tongji University, Shanghai, China.

DOI: 10.4236/ars.2023.124008                

Abstract

The rapid urbanization and population growth of Lagos City, Nigeria, have led to a significant change in land use and cover over the past two decades. The primary objective of this research was to assess the changes in land use and cover and forecast future trends in Lagos for the sustainable development of urbanization. The study utilized remote sensing and GIS technologies to monitor and identify the land use and cover of Lagos from 2000 to 2020. The CA Markov artificial neural network technique for cellular automata was employed to predict changes in land use and cover from 2020 to 2030. In addition, the post-classification comparison method was used to detect changes in classified classes in land use and cover. The study classified satellite images for 2000, 2010, and 2020 to develop land use and cover maps using ERDAS Imagine. The classification was based on six categories, namely 1) water bodies, 2) built-up, 3) bare land, 4) forest, 5) vegetation, and 6) wetlands. The results showed that: 1) the vegetation cover, wetlands, built-up areas, forests, and bare land have undergone significant changes over the past two decades. Built-up areas, wetlands, and forests have increased by 33.57%, 1.01%, and 21.37%, respectively, while vegetation, bare land, and water have decreased by 21.77%, 5.14%, and 17.13%, respectively. 2) Moreover, during 2020-2030, it is projected that 19.18% of forests and 16% of vegetation will decline, while 5.27% of barren land, 0.82% of wetlands, and 15.83% of water will increase. The urban area will be expanded by 42.44%. 3) The simulated results showed that the correction percentage was 82.43%, and the global kappa value was 0.85. The study found that the expansion of urban built-up areas due to population growth was the primary driver of the changes in land use and cover in Lagos. This research provides crucial insights that contribute to sustainable planning and management and helps us better understand the changes in land use and cover in Lagos.

Keywords

Urbanization, LU/LC Change, Remote Sensing, CA Markov, Sustainable Development

1. Introduction

A process of detecting land use/land cover (LULC) alteration involves identifying changes to the features or phenomenon over time [1] , and it is key to controlling environmental change [2] . Global anthropogenic activities increase considerably and lead to large-scale modifications to the earth’s surface, affecting the effectiveness of global systems. Consequently, the swift changes in LULC, specifically in low-income countries, have reduced important resources, such as water, soil, and vegetation [3] . Due to their magnitude, they have become global critical implications, and it is alarming that those changing steps are increasing locally, regionally, nationally, and worldwide, and this may significantly impact the environment on a different level [4] [5] . Satellite images are the most basic data for detecting, quantifying, and mapping LULC changes because of their repetitive acquisition, and their digital format is suitable for computer processing with a precise geo-reference procedure [6] . For the LULC, change detection and monitoring by ERDAS imagine involves using numerous datasets of images to assess the alterations occurring in LULC between the different acquisition dates of images due to several environmental conditions and human action [7] . The technique requires an adequate understanding of landscape features, imaging systems, and methodology involved [8] . Lagos has experienced significant urban growth and has become one of Africa’s continent largest and most rapidly growing cities. In recent decades, there has been an unmatched level of urban expansion in Lagos, making it a unique case in West Africa [9] . Lagos is the economic center of Nigeria and the West African sub-region. As such, it has attracted a high volume of domestic and international migrants, resulting in an intense settlement in the region [10] . However, the deficiency of updated and accurate data on the place, the spatial extent, the rate, and triggering factors of city development has always been a major obstacle to implementing adequate and effective urban planning and governance policies in major cities in developing countries like Lagos [11] . Because urban development involves a dynamic spatial-temporal variation process, modeling, simulation, and prediction can be useful planning tools for understanding the interaction between the natural and anthropogenic environment and problems resulting from rapid urban growth. Paul et al. [12] pointed out that changing detection has become essential in RS for examining urban development and LULC changes. Various methods and remote sensing data have been used for monitoring LULC [13] . Among these methods, the Post Classification Comparison (PCC) and different complex images are frequently used, particularly for planning LULC change over time [14] . The PCC approaches analyze land cover changes by comparing satellite images produced in different years [15] . It proves the nature of LULC change and helps to minimize the issues associated with satellite image variations. Therefore, the current study utilized the PCC method for examining the LULC change in Lagos from 2000-2020 using various Landsat imagery, remote sensing, and Geographic Information Systems. This study focuses on forecasting land use/land cover changes in Lagos, Nigeria, using the CA Markov artificial neural network technique and multiple Landsat imagery datasets. The study compares the urbanization of Lagos and Shanghai, two cities known for high population density. As a developed city, Shanghai has avoided slums, while Lagos is still advancing in infrastructure and economy. The findings of this study provide valuable insights into sustainable urban development strategies in Lagos. Moreover, the study’s results can serve as a guide for other low-income countries facing similar challenges. By offering a comprehensive analysis of Lagos’s urbanization process, the study fills the data gap crucial to effective urban planning and governance policies in burgeoning cities like Lagos.

2. Material and Methods

2.1. Study Area

Positioned in the southwest portion of Nigerian Federation Figure 1, Lagos is the most urbanized metropolis in Nigeria, the most populated nation in Africa,

Figure 1. The location of Lagos city on Africa map.

and one of the cities experiencing the most rapid expansion on a global scale in terms of its urban population. It stretches 180 km across the Guinea shoreline of the Gulf of Benin on the Atlantic Sea. Moreover, it is roughly located on latitudes and longitudes of (6˚22' to 6˚42') N and (2˚45' to 4˚20') E, in the order mentioned, and situated at a height of 645 meters relative to sea level [16] . Its geographic scope and political authority extend to Lagos, with four administrative regions of Ikeja, Ikorodu, Epe, and Badagry, also known as IBILE, is a region in Nigeria that covers 3577 km², or 0.4% of the country’s total land area (923,773 km²).

According to the United Nations, globally, Lagos is classified as the urban region’s most densely inhabited and rapidly developing region [17] . Moreover, it has many administrative, commercial, and industrial activities in Nigeria. As an urban conglomerate, Lagos extends towards the interior, creating an urban corridor connecting Lagos with other hinterland cities, such as Ibadan. The city is believed to have around 22 million inhabitants, and many live in urban regions.

2.2. Data Source

Landsat images were utilized to determine LULC distribution and alterations over time. To complete the objective, the task required acquiring three sets of image datasets with a resolution of 30 meters. These datasets were obtained from the USGS Earth Explorer and correspond to the years 2000, 2010, and 2020. Specifically, Landsat 5, 7, and 8 were used to collect the respective datasets for each of these years. The software packages ERDAS Imagine 2022, ArcGIS Pro 3, Excel, and Google Earth Pro were actively used in different analysis phases. Table 1 describes distinct categories of LULC.

Table 1. Classification of LULC of Lagos.

2.3. Data Processing and Data Analysis

The overall methodology used in this research is schematically represented in Figure 2.

2.4. Supervised Classification

Classifying images in a supervised manner is one of the best approaches with highly precise. An operator identifies sample areas (training areas). It requires familiarity with the area of interest using Google Earth with high spatial resolution. ERDAS IMAGINE 2022 is software used for Landsat image processing. Precisely, training samples for the specified LULC types have been chosen by demarcating polygons around indicative sites, with pixels surrounded by these polygons and spectral signatures for the corresponding land cover types collected by satellite images [2] . Incorporated the spectral signature into the classification procedure once it was tried satisfactorily. As one of the familiar parametric classifiers applied for supervised classification, the maximum likelihood technique as a classification method was chosen. According to Mugiraneza et al. [18] , the process of calculating the likelihood D or weighted distance of the unknown measurement vector X falls into a specific category known as M_c, and it serves as a fundamental component of the Bayesian equation.

$D=\ln \left(a_c\right)-0.5\ln \left(\left|co{v}_c\right|\right)-0.5\left(X-M_c\right)T\left(co{v}_c-1\right)\left(X-M_c\right)$ (1)

The MLC has the advantage of considering variance and covariance within the ranges as a parameterization classifier, and it works better than other recognized parametric classifiers for normal distribution data [9] . However, if the data provided has a non-normal distribution, it may be necessary to enhance the accuracy

Figure 2. Flow chart.

of the results [19] . The post-classification threshold was set using a thematic layer and distance files output from supervised classification, and three initial LULC maps were created.

2.5. Accuracy Assessment

This study tested the accuracy of the LULC map and the change detection results by comparing them with surface reality by randomly choosing ground truth points as references. It has been performed for all results. However, an error matrix and simple descriptive statistics were used to determine approval and disapproval of all images regarding classification. An error matrix is a grid of numerical values arranged in both rows and columns that displays a count of sample elements, such as pixels, that are allocated to a specific group compared with those assigned according to a referenced dataset [20] . The Kappa coefficient was also computed to measure how accurate the results are. It is a commonly used metric for evaluating accuracy and is a method for analyzing discrete multivariate data [21] . More generally, the Kappa coefficient is the percentage of agreement minus what we would expect by chance [22] [23] [24] . The calculation of Kappa, as outlined by Jensen and Cowen, in addition, is determined using the next equation:

$K=\frac{N{\displaystyle {\sum }_{i=1}^r{x}_{ii}}-{\displaystyle {\sum }_{i=1}^r\left(x_{i+}\times x_{+i}\right)}}{N^2-{\displaystyle {\sum }_{i=1}^r\left(x_i\times x_{+i}\right)}}$ (2)

Let N represent the overall count of sites within the matrix, r denotes the number of rows present in the matrix, x_ii signify the value found at the intersection of row i and column i. x_+i indicates the sum of values within row i, while x_i+ represents the sum of values within column i [24] . The LULC map result has a Kappa statistic estimated to be greater than 0.85. The Kappa coefficient expresses the proportionate reduction of a classification process’s errors compared to a random classification error [25] . A Kappa value of one implies true agreement, whereas a value greater than 0.85 shows that the resulting LULC map avoided more than 85% of errors. Remote sensing professionals and GIS practitioners widely acknowledged the accuracy of the LULC map of the research area [26] .

2.6. Change Detection

Change detection analysis determines the nature, magnitude, and level of land cover changes over spatial-temporal variations [13] . Land managers may use the results delivered by LULC change detection by linking different variables such as urban sprawl, water resource management, deforestation, and land degradation [27] [28] . Change detection is performed by deducting images from two different periods of the same location [29] [30] .

The distinction between images for two or more dates indicates an increase or decrease in specific LULC categories and variation in their spatial distribution. Many indices have been well-known and used to detect changes in various environmental states worldwide. The normalized difference water index (NDWI) and the normalized difference vegetation index (NDVI) are extensively used time series indices. Different satellite images are routinely used to identify and monitor water and vegetation cover changes across time [30] . The following equation has been modified to calculate changes in land cover.

$K_{gain}=S_b-S_a$ (3)

$K_0=S_{bi}=S_{ai}$ (4)

$K_{loss}=S_a-K_0$ (5)

where S_a and S_b mean land cover types at the starting and end year (time) in an expected period (10 years), respectively. S_ai and S_bi represent land cover types.

The intersection tool in ArcGIS Pro, which is a spatial analysis tool that overlays two or more layers to create a new layer with only the features that overlap, was used to detect LULC change for 20 years (2000, 2010, and 2020). Areas where changes have occurred were identified by overlaying the LULC data for each period. In vector data format, the resulting output from the intersection tool allows for further analysis and visualization of the changes over time. It is extensively utilized in diverse domains such as urban planning, natural resource management, and environmental monitoring.

2.7. Driving Factors for LULC Change

In the context of (LULC) change, elevation has been identified as a major factor influencing the transformation of undeveloped land to developed land. This is possible because places at higher altitudes are better suited for settlement. After all, Lagos is located on low-lying land susceptible to flooding. Distance from the water bodies is a vital spatial factor that influences urban development. In addition, proximity to the town center plays a significant role in LULC change; areas nearer the urban center are more likely to be developed into built-up areas. It is because the city infrastructure, employment opportunities, and other socioeconomic resources are concentrated in the downtown area, making them more accessible to people living close to the town center. In contrast, the slope is not observed to impact urban growth in Lagos significantly. However, it could be attributed to the flat topography of Lagos, where slope-related constraints are less pronounced than in mountainous regions. As a result of Lagos’ rapid population growth, there has been pressure on various types of land use, which has led to the conversion and modification of land LULC in the city. LULC changes and population growth are significantly related during the observed period. LULC in the Lagos city region changed rapidly from 2000 to 2010. Urbanization is primarily caused by the migration of rural residents to urban areas. Furthermore, more reliable population data is needed to make land use policy for planning and implementation easier. This is one of the primary issues that has rendered successive governments’ execution of land use plans to handle population growth in an orderly and planned manner a failure. The expanding population’s demand for shelter and other facilities resulted in unprecedented urban expansion (spatial). The influx of people to Lagos led to the formation of shanty towns and villages, which deteriorated into slums in modern Lagos.

3. Results

3.1. LULC Distribution in 2000, 2010, and 2020

In order to test the validity of satellite image classification results, we wanted to compare them with reference data or ground truth. An error matrix is commonly used to assess classification accuracy for remote sensing applications [31] . LULC maps resulting from visual interpretation and classification were evaluated using an error matrix. The following are classified image maps, their accuracy assessment reports, and the area and percentages for each class. Figure 3 indicates the LULC maps of Lagos in 2000, 2010, and 2020, and Table 2 shows the area with the corresponding percentage of each LULC type. Figure 3 shows that between 2000 and 2020, there were considerable changes in the LULC in Lagos, Nigeria. The most notable change was the increase in the build-up area, which grew from 598.426 km² in 2000 to 1271.286 km² in 2020, as shown in Table 2.

Figure 3. Lagos LULC change of different period.

Table 2. Overall LULC distribution (2000-2020) in the study area.

This represents a 112.2% rise in built-up, indicating that Lagos has experienced rapid urbanization over the past two decades. The increase in the built-up area was accompanied by a decline in vegetation, which decreased by 376.3 km² during the same period. Thus, vegetation reduction has been considered a triggering factor for several environmental-related issues, including soil erosion, decreased air quality, and reduced biodiversity.

Another significant change observed in Lagos was the decline in bare land, which decreased by 436.739 km² between 2000 and 2020 (Table 2). This change was due to the alteration of bare land into built-up. However, this decline in bare land may also have negative implications for the region’s hydrology, as bare land is important for groundwater recharge and infiltration. On the other hand, the wetlands showed a minor increase of 2.772 km² from 2000 to 2020, as shown in Table 2. This increase is attributed to the government’s efforts to preserve wetlands for flood mitigation purposes. Previous studies have highlighted the challenges of urbanization in Lagos, with a growing population and rapid expansion leading to various environmental, social, and economic problems. One of the most significant challenges is flooding, which has become a recurrent problem in the region. This study provides valuable information for flood mitigation efforts. The development in built-up areas may contribute to the flooding problem, as it can reduce the permeability of the soil, resulting in increased surface runoff. Therefore, sustainable land use planning is a need in Lagos to balance the needs of urban development with the conservation of natural resources and the protection of vulnerable ecosystems [32] .

3.2. LULC Accuracy Determination

Assessing the accuracy of the classification result is a vital requirement for analyzing LULC changes. Classification results presented that the total accuracy was 95%, 92%, and 93% for 2000, 2010, and 2020, respectively, and the kappa coefficient values were 94%, 90%, and 91% for 2000, 2010, and 2020, respectively (Table 3). Further, the classification accuracy exceeded the acceptable threshold, indicating it could meet the LULC classification requirements.

Table 3. Overall LULC accuracy distribution and kappa coefficient (%).

3.3. LULC Change Detection

The LULC change detection results have briefly been presented in Tables 4-6 for the past two decades (2000-2010, 2010-2020, and 2000-2020). Meanwhile, Figure 4 indicates the spatial distribution of LULC classes. In this study, the changes matrix was determined by applying the cross-tabulation technique to compare two maps of the different periods. Teferi et al. [33] net change refers to the disparity between the amount gained and the amount lost. The alterations in LULC throughout the research were assessed by comparing data from 2000, 2010, and 2020. The results, primarily displayed in Table 7 as well as Figures 5-7, highlight the gains and losses.

From Table 7, the outcomes showed that the LULC in Lagos has undergone significant changes in the selected period. The built-up has augmented by 672.860 km², with a net increase of 485.228 (81.08%) km² between 2000 and 2010 and 187.632 (17.25%) km² between 2010 and 2020. On the other hand, the bare land has decreased by 436.739 km², with a net decrease of 286.103 km² between 2000 and 2010 and 150.636 km² between 2010 and 2020. Similarly, the forest area has increased by 235.609 km², with a net increase of 119.261 km² between 2000 and 2010 and 116.349 km² between 2010 and 2020. The vegetation area has shown a significant net decrease of 376.300 km² between 2000 and 2020, with a net decrease of 313.615 km² between 2000 and 2010 and 62.685 km² between 2010 and 2020. The water area has also decreased by 98.202 km² between 2000 and 2020, with a net increase of 23.436 km² between 2000 and 2010 and a net decrease of 121.638 km² between 2010 and 2020. The wetland area has slightly increased by 2.772 km² between 2000 and 2020, with a net decrease of 28.207 km² between 2000 and 2010 and a net increase of 30.979 km² between 2010 and 2020. In the next 10 years, it is predicted that the LULC will keep changing. A prediction map from 2020-2030 revealed a significant decreasing trend in (the forest, vegetation, bare land, wetlands, and water by 19.18%,

Figure 4. Lagos LULC change detection from 2000 to 2020.

Table 4. LULC changes matrix as detected from 2000 to 2010.

Figure 5. Predicted statistics of LULC in 2030.

Table 5. LULC changes matrix as detected from 2010 to 2020.

Figure 6. Lagos prediction LULC in 2030.

Table 6. LULC changes matrix as detected from 2000 to 2020.

Table 7. Summary of LULC changes in each period.

Figure 7. Lagos population growth.

16.46%, 5.27%, 0.82%, and 15.83%, respectively, and increasing trends in built-up developed by 42.44%. There will be a dramatic build-up increase from 33.57% in 2020 to 42.44% in 2030, and those significant changes will be derived from the ongoing population growth as predicted by the UN [33] [34] . It has an annual growth rate of 2.91% [35] [36] . Lagos City is expected to increase from 26 million people in 2020 to 33.6 million in 2030, which will impact existing LULU. According to the 2030 predicted model, 42.44% of the whole area will be built-up. Figure 8 indicates the trends of Lagos city population growth from 2000 to 2010, 2010 to 2020, and 2020 to 20230, with a percent increase of 69.61%, 41.04%, and 36.79%, respectively. In addition, the overall percentage of increase from 2000 to 2030 is estimated to be 227.25%. In conclusion, Lagos city experienced tremendous urban expansion over 30 years.

4. Discussion

4.1. The Impact of Urbanization on Environmental Aspects

LULC changes have significant environmental consequences at local and global levels. These changes have extreme consequences at the regional and global level, such as damage to biodiversity, distress of hydrological cycles, rise in soil displacement, and sediment deposition [35] . In addition to environmental aspects such as water quality, air pollution, and the temperature of land, urbanization significantly impacts slums (Table 8).

Generally, African urbanization is occasionally defined as “parasitic urbanism,” “urbanization of poverty,” or “premature urbanism” [41] . Mainly, African urbanization often differs from Western cities [42] . Moreover, this resulted in the high slum creation and made slums the primary residential land use type [41] .

4.2. The Leading Indicator of Built-Up Expansion

The data provided illustrates a strong correlation between population growth and the increase of built-up areas in Lagos. The substantial population increases experienced by Lagos City over two consecutive decades, as depicted in Figure 7 and Figure 8, have had significant implications on LULC patterns within the region.

Figure 8. Lagos built-up expansion.

Table 8. Comparing the impact of urbanization between Lagos and Shanghai city based on different factors.

As the population of Lagos has grown remarkably, the demand for residential, commercial, and industrial spaces has increased. This population surge has necessitated converting previously undeveloped or vegetated areas into built-up areas to accommodate housing, infrastructure, and economic activities. Consequently, the expansion of built-up areas has resulted in a reduction of vegetation cover. The relationship between population growth and the increase of built-up areas becomes even more apparent when examining specific years.

As the population has grown remarkably, the demand for residential, commercial, and industrial spaces has increased. This population surge has necessitated converting previously undeveloped or vegetated areas into built-up areas to accommodate housing, infrastructure, and economic activities. Consequently, the expansion of built-up areas has resulted in a reduction of vegetation cover. The relationship between population growth and the increase of built-up areas becomes even more apparent when examining specific years. For example, from 2000 to 2010, the population of Lagos experienced a remarkable increase of 69.61%. As a result, the built-up areas expanded to cover approximately 81.04% of the total land area in 2000. Similarly, between 2010 and 2020, there was a significant rise in population by 41.04%, leading to a 17.25% expansion of the built-up areas. As the population grows, there is a greater demand for housing, infrastructure, and economic activities.

4.3. Limitations

• The foremost limitation is the quality of images that are available on Google Earth Pro, where some satellite images were blurred or cloud-covered in some study areas, and they were used as references while performing accuracy assessment.

• Some images have a low level of haze due to atmospheric conditions, which may affect the image classification accuracy.

• Temporal resolution: the images are corrected at different times, and changes in the landscape between short periods were not detected because the interval set for this change may be long.

5. Conclusion and Recommendation

In conclusion, the findings of this study show a significant change in the LULC of Lagos City from 2000 to 2020. The analysis revealed the substantial reduction in vegetation, bare land and wetlands, and the development in the built-up area. This shift in LULC is attributed to swift urbanization, population expansion, and economic growth. Utilizing GIS and remote sensing methods has proved to be valuable in monitoring and mapping these changes, particularly in mitigating the potential risks associated with such changes, such as flooding. Policymakers and urban planners must consider the environmental and ecosystem impacts of LULC changes and establish sustainable development plans. Based on the results of this research, several recommendations may be suggested to mitigate the negative effects of urbanization and promote sustainable development in Lagos. First, politicians and urban planners must emphasize the conservation of vegetation cover, which has decreased significantly throughout the study’s period. This can be accomplished by creating protected areas, replanting projects, and enforcing environmental restrictions to avoid further destruction of natural habitats. Second, efforts should be made to promote more sustainable urban development patterns, such as compact and mixed-use urban forms, which reduce the need for major land use alteration. This could include encouraging high-density development near existing urban centers and providing efficient public transportation systems to reduce reliance on private cars. Third, the study highlights the need for more accurate and updated spatial data on urban growth and land use/cover change to inform evidence-based policy and decision-making. Therefore, there should be continued investment in using remote sensing and GIS technologies to monitor LULC changes in Lagos and other urban areas in Nigeria. Finally, the study’s findings have significant suggestions for policymakers and urban planners in Lagos and other cities in Nigeria. It is feasible to mitigate the negative influence of urbanization on the environment and create a more livable and resilient future by taking a more comprehensive and sustainable approach to urban development.

Acknowledgements

The research authors would like to extend their heartfelt appreciation to the referenced authors and data owners for their valuable contribution to the study. Moreover, the authors acknowledge the editor and anonymous reviewers for their constructive feedback, which played a pivotal role in enhancing the quality of the final manuscript. It is also worth mentioning that the USGS provided the data for this research, which was instrumental in achieving the study’s objectives.

Author Contributions

Katabarwa Murenzi Gilbert and Yishao Shi planned the study and selected the data; Katabarwa Murenzi Gilbert processed and analyzed the data; results interpreted and discussed by Yishao Shi and Katabarwa Murenzi Gilbert; and Yishao Shi reviewed the paper.

Funding

This study was funded by Shenzhen Planning and Land Development Research Center. “Case Analysis of Urban Planning and Construction of Global Cities” (2021FY0001-2588).

Data Availability Statement

Apart from the spatial data available on the USGS website, additional data and materials can be provided via email upon request by the authors.

Conflicts of Interest

The authors declare no conflict of interest.

References

[1]	Salem, M., Tsurusaki, N. and Divigalpitiya, P. (2020) Land Use/Land Cover Change Detection and Urban Sprawl in the Peri-Urban Area of Greater Cairo since the Egyptian Revolution of 2011. Journal of Land Use Science, 15, 592-606. https://doi.org/10.1080/1747423X.2020.1765425
[2]	Rwanyiziri, G., Kayitesi, C., Mugabowindekwe, M., Byizigiro, R.V., Muyombano, E., Kagabika, M.B. and Bimenyimana, T. (2020) Spatio-Temporal Analysis of Urban Growth and Its Effects on Wetlands in Rwanda: The Case of Rwampara Wetland in the City of Kigali. Journal of Applied Sciences and Environmental Management, 24, 1495-1501. https://doi.org/10.4314/jasem.v24i9.2
[3]	Ayeni, A.O. and Odume, J.I. (2020) Analysis of Algae Concentration in the Lagos Lagoon Using Eye on Water and Algae Estimator Mobile App. FUTY Journal of the Environment, 14, 105-115. https://www.ajol.info/index.php/fje/article/view/201424
[4]	Gudo, A.J.A., Deng, J. and Qureshi, A.S. (2022) Analysis of Spatiotemporal Dynamics of Land Use/Cover Changes in Jubek State, South Sudan. Sustainability, 14, Article No. 10753. https://doi.org/10.3390/su141710753
[5]	Islam, I., Cui, S., Xu, L., Prodhan, F.A., Ahmed, S., Rahman, M.A. and Hasan, J. (2022) Monitoring Changes in Land Use Land Cover and Ecosystem Service Values of Dynamic Saltwater and Freshwater Systems in Coastal Bangladesh by Geospatial Techniques. Water, 14, Article No. 2293. https://doi.org/10.3390/w14152293
[6]	Iwuji, M., Ibe, C., Njoku, J., Anyanwu, S., Amangabara, G., Ac-Chukwuocha, N. and Ukaegbu, K. (2017) Analysis of Land Use and Land Cover Dynamics in Orlu, Nigeria. Asian Journal of Environment & Ecology, 4, 1-10. https://doi.org/10.9734/AJEE/2017/34143
[7]	Arif, M., Sengupta, S., Mohinuddin, S.K. and Gupta, K. (2023) Dynamics of Land Use and Land Cover Change in Peri-Urban Area of Burdwan City, India: A Remote Sensing and GIS-Based Approach. GeoJournal, 88, 4189-4213. https://doi.org/10.1007/s10708-023-10860-3
[8]	Adepoju, M.O., Millington, A.C. and Tansey, K.T. (2006) Land Use/Land Cover Change Detection in Metropolitan Lagos (Nigeria): 1984-2002. ASPRS 2006 Annual Conference, Reno, 1-5 May 2006, 1-7. https://www.asprs.org/a/publications/proceedings/reno2006/0002.pdf
[9]	Onilude, O.O. and Vaz, E. (2020) Data Analysis of Land Use Change and Urban and Rural Impacts in Lagos State, Nigeria. Data, 5, Article No. 72. https://doi.org/10.3390/data5030072
[10]	Idowu, T.E., Waswa, R.M., Lasisi, K., Nyadawa, M. and Okumu, V. (2020) Object-Based Land Use/Land Cover Change Detection of a Coastal City Using Multi-Source Imagery: A Case Study of Lagos, Nigeria. South African Journal of Geomatics, 9, 136-148. https://doi.org/10.4314/sajg.v9i2.10
[11]	Onilude, O.O. and Vaz, E. (2021) Urban Sprawl and Growth Prediction for Lagos Using GlobeLand30 Data and Cellular Automata Model. Sci, 3, Article No. 23. https://doi.org/10.3390/sci3020023
[12]	Nkundabose, J.P. (2021) Employing Remote Sensing Tools for Assessment of Land Use/Land Cover (LULC) Changes in Eastern Province, Rwanda. American Journal of Remote Sensing, 9, 23-32. https://doi.org/10.11648/j.ajrs.20210901.13
[13]	Solanki, S., Chandran, C., Garg, J.K. and Bhattacharya, P. (2019) Analysis of Long-Term Spatio-Temporal Trends in Land Use/Land Cover in Devikulam Taluk, Kerala Using Geospatial Techniques. International Journal of Environment, 8, 34-52. https://doi.org/10.3126/ije.v8i3.26616
[14]	Romano, B., Fiorini, L., Marucci, A. and Zullo, F. (2020) The Urbanization Run-Up in Italy: From a Qualitative Goal in the Boom Decades to the Present and Future Unsustainability. Land, 9, Article No. 301. https://doi.org/10.3390/land9090301
[15]	Elekwachi, W., Hart, L. and Ifeanyi, C.E. (2021) Spatio-Temporal Changes of Land Use/Land Cover Classes in the Urban Wetland Area of Yenagoa Local Government Area of Bayelsa State, Nigeria. Journal of Geography, Environment, and Earth Science International, 25, 194-207. https://doi.org/10.9734/jgeesi/2021/v25i1030325
[16]	Faisal Koko, A., Yue, W., Abdullahi Abubakar, G., Hamed, R. and Noman Alabsi, A.A. (2021) Analyzing Urban Growth and Land Cover Change Scenario in Lagos, Nigeria Using Multi-Temporal Remote Sensing Data and GIS to Mitigate Flooding. Geomatics, Natural Hazards and Risk, 12, 631-652. https://doi.org/10.1080/19475705.2021.1887940
[17]	Wilmoth, M.J., Menozzi, M.C. and Bassarsky, M.L. (2022) Why Population Growth Matters for Sustainable Development. 1-4. https://www.un.org/development/desa/pd/sites/www.un.org.development.desa.pd/files/undesa_pd_2022_policy_brief_population_growth.pdf
[18]	Mugiraneza, T., Nascetti, A. and Ban, Y. (2020) Continuous Monitoring of Urban Land Cover Change Trajectories with Landsat Time Series and Landtrendr-Google Earth Engine Cloud Computing. Remote Sensing, 12, Article No. 2883. https://doi.org/10.3390/rs12182883
[19]	Azareh, A., Sardooi, E.R., Gholami, H., Mosavi, A., Shahdadi, A. and Barkhori, S. (2021) Detection and Prediction of Lake Degradation Using Landscape Metrics and Remote Sensing Dataset. Environmental Science and Pollution Research, 28, 27283-27298. https://doi.org/10.1007/s11356-021-12522-8
[20]	Baig, M.F., Mustafa, M.R.U., Baig, I., Takaijudin, H.B. and Zeshan, M.T. (2022) Assessment of Land Use Land Cover Changes and Future Predictions Using CA-ANN Simulation for Selangor, Malaysia. Water, 14, Article No. 402. https://doi.org/10.3390/w14030402
[21]	Mathewos, M., Lencha, S.M. and Tsegaye, M. (2022) Land Use and Land Cover Change Assessment and Future Predictions in the Matenchose Watershed, Rift Valley Basin, Using CA-Markov Simulation. Land, 11, Article No. 1632. https://doi.org/10.3390/land11101632
[22]	Hamud, A.M., Prince, H.M. and Shafri, H.Z. (2019) Land Use/Land Cover Mapping and Monitoring Using Remote Sensing and GIS with Environmental Integration. IOP Conference Series: Earth and Environmental Science, 357, Article ID: 012038. https://doi.org/10.1088/1755-1315/357/1/012038
[23]	Piao, Y., Xiao, Y., Ma, F., Park, S., Lee, D., Mo, Y. and Kim, Y. (2023) Monitoring Land Use/Land Cover and Landscape Pattern Changes at a Local Scale: A Case Study of Pyongyang, North Korea. Remote Sensing, 15, Article No. 1592. https://doi.org/10.3390/rs15061592
[24]	Xie, G. and Niculescu, S. (2021) Mapping and Monitoring of Land Cover/Land Use (LCLU) Changes in the Crozon Peninsula (Brittany, France) from 2007 to 2018 by Machine Learning Algorithms (Support Vector Machine, Random Forest, and Convolutional Neural Network) and by Post-Classification Comparison (PCC). Remote Sensing, 13, Article No. 3899. https://doi.org/10.3390/rs13193899
[25]	Spruce, J., Bolten, J., Mohammed, I.N., Srinivasan, R. and Lakshmi, V. (2020) Mapping Land Use Land Cover Change in the Lower Mekong Basin from 1997 to 2010. Frontiers in Environmental Science, 8, Article No. 21. https://doi.org/10.3389/fenvs.2020.00021
[26]	Mainuri, Z.G. (2018) Impact of Human Settlement on Land Use/Land Cover Changes in the Middle River Njoro Sub Watershed in Kenya. European Journal of Multidisciplinary Studies, 3, 180-188. https://doi.org/10.26417/ejms.v3i4.p180-188
[27]	Kayiranga, A., Kurban, A., Ndayisaba, F., Nahayo, L., Karamage, F., Ablekim, A. and Ilniyaz, O. (2016) Monitoring Forest Cover Change and Fragmentation Using Remote Sensing and Landscape Metrics in Nyungwe-Kibira Park. Journal of Geoscience and Environment Protection, 4, 13-33. https://doi.org/10.4236/gep.2016.411003
[28]	Wang, Y., Zhang, X. and Peng, P. (2021) Spatio-Temporal Changes of Land-Use/Land Cover Change and the Effects on Ecosystem Service Values in Derong County, China, from 1992-2018. Sustainability, 13, Article No. 827. https://doi.org/10.3390/su13020827
[29]	Bhattacharjee, S., Islam, M.T., Kabir, M.E. and Kabir, M.M. (2021) Land-Use and Land-Cover Change Detection in a Northeastern Wetland Ecosystem of Bangladesh Using Remote Sensing and GIS Techniques. Earth Systems and Environment, 5, 319-340. https://doi.org/10.1007/s41748-021-00228-3
[30]	Lin, L., Hao, Z., Post, C.J., Mikhailova, E.A., Yu, K., Yang, L. and Liu, J. (2020) Monitoring Land Cover Change on a Rapidly Urbanizing Island Using Google Earth Engine. Applied Sciences, 10, Article No. 7336. https://doi.org/10.3390/app10207336
[31]	Jimoh, R., Afonja, Y., Albert, C. and Amoo, N. (2018) Spatio-Temporal Urban Expansion Analysıs in a Growing City of Oyo Town, Oyo State, Nigeria Using Remote Sensing and Geographic Information System (GIS) Tools. International Journal of Environment and Geoinformatics, 5, 104-113. https://doi.org/10.30897/ijegeo.354627
[32]	United Nations Human Settlements Programme (2020) World Cities, Unpacking the Value of Sustainable Urbanization.
[33]	United Nations, Department of Economic and Social Affairs, Population Division (2022) World Population Prospects 2022, Data Sources. UN DESA/POP/2022/DC/NO. 9. https://population.un.org/wpp/Publications/Files/WPP2022_Data_Sources.pdf
[34]	Oyalowo, B. (2022) Implications of Urban Expansion: Land, Planning, and Housing in Lagos. Buildings and Cities, 3, 692-708. https://doi.org/10.5334/bc.243
[35]	Wang, H., Zhang, Y., Tsou, J.Y. and Li, Y. (2017) Surface Urban Heat Island Analysis of Shanghai (China) Based on the Change of Land Use and Land Cover. Sustainability, 9, Article No. 1538. https://doi.org/10.3390/su9091538
[36]	Demehin, M.O. (2022) Urbanization, Urban-Slum Settlements and Its Implications on Health: An Insight from Lagos State, Nigeria. International Journal of Social Sciences: Current and Future Research Trends, 13, 117-132. https://www.researchgate.net/publication/362067451_International_Journal_of_Social_Sciences_Current_and_Future_Research_Trends_IJSSCFRT_Urbanization_Urban-Slum_Settlements_and_its_Implications_on_Health_An_Insight_from_Lagos_State_Nigeria
[37]	Tomlinson, R. (2012) Does Shanghai Have Slums? International Development Planning Review, 34, 5-16. https://doi.org/10.3828/idpr.2012.14
[38]	Ohwo, O. and Abotutu, A. (2015) Environmental Impact of Urbanization in Nigeria. British Journal of Applied Science & Technology, 9, 212-221. https://doi.org/10.9734/BJAST/2015/18148
[39]	Cui, L. and Shi, J. (2012) Urbanization and Its Environmental Effects in Shanghai, China. Urban Climate, 2, 1-15. https://doi.org/10.1016/j.uclim.2012.10.008
[40]	Babalola, O.S. and Akinsanola, A.A. (2016) Change Detection in Land Surface Temperature and Land Use Land Cover over Lagos Metropolis, Nigeria. Journal of Remote Sensing & GIS, 5, Article No. 171. https://doi.org/10.4172/2469-4134.1000171
[41]	Badmos, O.S., Callo-Concha, D., Agbola, B., Rienow, A., Badmos, B., Greve, K. and Jürgens, C. (2020) Determinants of Residential Location Choices by Slum Dwellers in Lagos Megacity. Cities, 98, Article ID: 102589. https://doi.org/10.1016/j.cities.2019.102589
[42]	Dodman, D., Leck, H., Rusca, M. and Colenbrander, S. (2017) African Urbanization and Urbanism: Implications for Risk Accumulation and Reduction. International Journal of Disaster Risk Reduction, 26, 7-15. https://doi.org/10.1016/j.ijdrr.2017.06.029