Land Use And Land Cover Types Research Articles

Change in Bhutan’s Land Use and Land Cover from 1930 - 2020

The land is a fundamental component of Bhutan's geographical makeup, characterized by natural features and human activities. Bhutan's land can be divided into land use and land cover (LULC), where human activities contribute to land use, and natural elements define land cover. This paper analyzes Bhutan's LULC patterns, emphasizing the evolving trends in major LULC types, strengths and challenges of sustainable land use management, and envisioning its future trajectory. In recent years, Bhutan's land-use pattern has displayed a predominant forest cover, encompassing a significant portion of the total land area. Similarly, the built-up area in Bhutan is gradually increasing, reflecting the country's ongoing urbanization and development activities. A long-term analysis reveals dynamic shifts in agricultural land in Bhutan. While there has been a historical expansion of agricultural areas, recent trends may suggest a potential slowdown or decline, influenced by factors such as urban growth and changing economic landscapes. Like community forestry practices in Bhutan, successful conservation efforts may also influence land-use changes. In the eastern Himalayas, Bhutan faces challenges related to snow/glacial cover impacted by climate change. Increasing temperatures in the region contribute to alterations in snow/glacial patterns, necessitating a focus on environmental conservation and sustainable practices to preserve these vital resources. The land tenure system and land use policies in Bhutan have evolved and been shaped by socioeconomic and political dynamics. Bhutan needs to adapt and formulate effective policies to address contemporary challenges and promote sustainable LULC management. Implementing specific LULC zones, as outlined in Bhutan's land use policies, is crucial for ensuring sustainable land management practices.

Identifying land use land cover dynamics using machine learning method and GIS approach in Karaivetti, Tamil Nadu

<p>An important analytical tool for tracking, mapping, and quantifying changes in land use and land cover (LULC) across time serves as the use of machine learning techniques. The environment and human activities both have the potential to change how land is used and covered. Classifying LULC types at different spatial scales has been effectively achieved by models like classification and regression trees (CART), support vector machines (SVM), extreme gradient boosting (XGBoost), and random forests (RF). To prepare images from Landsat before sending and analysis for an aspect of our research, we employed the Google Earth Engine. High-resolution imagery from Google Earth images were used to assess each kind of method and field data collection. Utilizing Geographic Information System (GIS) techniques, LULC fluctuations between 2015 and 2020 were assessed. According to our results, XGBoost, SVM, and CART models proved superior by the RF model regarding categorization precision. Considering the data, we collected between 2015 and 2020, from 11.57 hectares (1.74%) in 2015 to 184.19 hectares (27.65%) in 2020, the barren land experienced the greatest variation, that made an immense effect. Utilizing the support of satellite imagery from the Karaivetti Wetland, our work combines novel GIS techniques and machine learning strategies to LULC monitoring. The created land cover maps provide a vital benchmark that will be useful to authorities in formulating policies, managing for sustainability, and keeping track of degradation.</p>

Sustainable flood hazard mapping with GLOF: A Google Earth Engine approach

This study aims to evaluate the efficacy of Google Earth Engine (GEE) in mapping floods and their aftermath, focusing on the recent event caused by cloud burst rainfall and glacial lake outburst flood (GLOF) of Lhonak glacier lake in the Teesta River basin, North Sikkim. The objective is to utilize GEE, coupled with Sentinel-1 Synthetic Aperture Radar (SAR) data and Landsat 9 imagery, for precise remote sensing analysis, flood mapping, and Land Use and Land Cover (LULC) classification. The study employs a comprehensive methodology within the GEE platform, involving the acquisition and preprocessing of Sentinel-1 SAR data to create pre- and post-flood images. The difference between these images is calculated to generate flood maps at five-day intervals, providing a temporal evolution of the flood extent. Additionally, LULC mapping is conducted using Landsat 9 data, contributing to an understanding of pre-flood landscape characteristics. The results and discussion reveal significant impacts on various LULC types, with barren rocks, dense and medium forests, settlements, and agricultural lands experiencing notable effects. This research not only enhances our understanding of GLOFs but also serves as a critical tool for informing disaster management strategies, emphasizing the importance of accurate hazard assessment and the need for holistic approaches to mitigate the cascading effects of such events.

Transfer-Ensemble Learning: A Novel Approach for Mapping Urban Land Use/Cover of the Indian Metropolitans

Land use and land cover (LULC) classification plays a significant role in the analysis of climate change, evidence-based policies, and urban and regional planning. For example, updated and detailed information on land use in urban areas is highly needed to monitor and evaluate urban development plans. Machine learning (ML) algorithms, and particularly ensemble ML models support transferability and efficiency in mapping land uses. Generalization, model consistency, and efficiency are essential requirements for implementing such algorithms. The transfer-ensemble learning approach is increasingly used due to its efficiency. However, it is rarely investigated for mapping complex urban LULC in Global South cities, such as India. The main objective of this study is to assess the performance of machine and ensemble-transfer learning algorithms to map the LULC of two metropolitan cities of India using Landsat 5 TM, 2011, and DMSP-OLS nightlight, 2013. This study used classical ML algorithms, such as Support Vector Machine-Radial Basis Function (SVM-RBF), SVM-Linear, and Random Forest (RF). A total of 480 samples were collected to classify six LULC types. The samples were split into training and validation sets with a 65:35 ratio for the training, parameter tuning, and validation of the ML algorithms. The result shows that RF has the highest accuracy (94.43%) of individual models, as compared to SVM-RBF (85.07%) and SVM-Linear (91.99%). Overall, the ensemble model-4 produces the highest accuracy (94.84%) compared to other ensemble models for the Kolkata metropolitan area. In transfer learning, the pre-trained ensemble model-4 achieved the highest accuracy (80.75%) compared to other pre-trained ensemble models for Delhi. This study provides innovative guidelines for selecting a robust ML algorithm to map urban LULC at the metropolitan scale to support urban sustainability.

Temporal and spatial variations of carbon storage and carbon sink improvement strategy at the district and county level based on PLUS-InVEST model: Taking Yanqing District as an example

Under the background of the carbon peaking and carbon neutrality goals, the evolution of the spatiotemporal pattern of carbon storage has recently emerged as a research hotspot. The change in land use and land cover (LULC) is the primary driver of carbon storage changes. Understanding the spatiotemporal variations of LULC and carbon storage at the small scale of district and county level and proposing strategies to improve carbon sink, will contribute to the ecological conservation, restoration and sustainable development of districts or counties. With Yanqing District in Beijing as an example, we calculated carbon storage from 1990 to 2020 based on the InVEST model and used the PLUS model to predict LULC type changes under three scenarios (natural growth, ecological conservation and economic development) from 2020 to 2050. We further predicted the carbon storage and proposed mea-sures to improve carbon sink. The results showed that the key LULC change in Yanqing between 1990 and 2020 were the conversion of 88.9% of grassland to forest, 50.1% of farmland to forest, and 39.5% of cropland to impervious surface. The total carbon storage showed an upward trend, with an increase of 3.34×106 Mg. The spatial distribution of carbon storage presented "high in the northeast, low in the southwest, and high in the mountainous areas, low in the riverine areas." The increase in forest and the decrease in grassland were the main reasons for the increase and decrease in carbon storage, respectively. Between 2020 and 2050, the ecological restoration efforts under the ecological protection scenario increased, and the probability of other LULCs transforming into forest increased, resulting in a 5.8% increase in carbon storage, which had the highest increase and carbon storage under the three scenarios. High-value carbon storage areas were concentrated in the northeast, northwest, and south of Yanqing District, basically corresponding to the mountainous regions of Yanqing with high forest coverage, and the low-value areas generally corresponded to the plains with high development intensity and low forest coverage. We could implement comprehensive ecological protection and restoration measures, including forest and grassland ecosystem protection, water environment ecological restoration, farmland ecological restoration, to promote sustainable development in Yanqing District and to achieve the "dual carbon" goal.

Impact of land use changes on the land surface thermal environment in Nanchang, Jiangxi province, China

Throughout human history, human activities have resulted in land use and land cover changes (LUCC) and can have a direct impact on the land surface thermal environment (LSTE). In the existing studies, the holistic nature of changes in land use and land cover (LULC) has been neglected in favor of focusing on the interactions between different LULC types and the land surface thermal environment. This study used ArcGIS Pro 3.0, ENVI 5.3, and SPSS software to construct a contribution index model and stepwise regression equation to investigate the relationship between LULC type, structure, and pattern changes and LSTE changes in Nanchang City, Jiangxi Province, China, from 1990 to 2020. The findings revealed that 1) rapid urbanization has led to a surge in the area of built-up land and a decrease in the area of arable land in Nanchang; between 1990 and 2020, the area of built-up land in Nanchang increased by 433.29 km2, while the area of arable land decreased by 291.99 km2; 2) The land surface temperature (LST) was divided into five classes according to the equal spacing method, and the areas with the highest and lowest temperature classes were the high temperature zone and the low temperature zone, respectively. Over the past 30 years, the LSTE in Nanchang has gradually deteriorated, with the area of the low temperature zone shrinking by 554.2 km2 and the area of other classes appearing to increase significantly; 3) the contribution index and stepwise regression equation demonstrate that the primary reasons for the worsening of the LSTE are an increase in the scale of cultivated land and construction land. It was found that rationalization of urban LULC type, structure, and pattern can effectively reduce land surface temperature.

GIS based method for mapping actual LULC by combining seasonal LULCs

One of the most significant applications of remote sensing data is to prepare land use and land cover (LULC) maps. LULC maps are always affected by seasonality and a single LULC map of a particular month is prepared to represent a year in most of the research, especially in change detection research. This does not represent the real view of the landscape because the seasonal variation of different LULC types is always overlooked. Considering the issue, the current method aims to solve the problem by incorporating seasonal LULC using the raster overlay method to remove the seasonality effect on LULC classification. To apply this method, a minimum of two seasonal LULC maps is required for a single study year. The map needs to overlay and then reclassify according to the stable and rotational LULC pattern of the study area. This method will replicate the actual LULC pattern of a study area from satellite images. Summary of the method is as follows:•LULC of each season was classified using image classification technique.•LULC of each seasons are coded and combined using overlay technique.•Combined map is reclassified to prepare the actual LULC map.

Evaluating the impact of land use and land cover changes on forest ecosystem service values using landsat dataset in the Atwima Nwabiagya North, Ghana

This study investigated land use and land cover (LULC) changes and its impact on forest ecosystem service values for 20 years in the Atwima Nwabaiagya North District using Landsat images of 2002, 2012 and 2022. Supervised classification with Maximum Likelihood Algorithm was used to classify the Landsat images. Five LULC types (high-dense forest, low-dense forest, water, bare-ground, and Built-up area) were successfully classified, with overall accuracies of 99.0 % and Kappa coefficients of 0.99. The result of the study showed a reduction of high-dense forest to 23.87 %, low-dense forest to 26.53 %, and water areas as 1.16 % whereas built-up (21.44 %) and bare-ground (27 %) experienced an expansion in their land areas. Related literatures and ecological assets value table with adjusted price value were used to evaluate ecosystem service values in response to LULC changes. The study discovered that ecosystem service value for high and low-dense forests have declined from USD 22.68 million and USD 8.75 million to USD 14.56 million and USD 5.2 million respectively. The overall total ecosystem service value declined by USD 33.73 million in 2002 to USD 21.91 million in 2022. It was revealed that the most notable feature to changes in forest ecosystem service values was the expansion of built-up and bare-grounds. There is a need to curb the current drivers of LULC changes in the Atwima Nwabiagya North to stop further forest degradation for optimum delivery of forest ecosystem service values in the district. For land use planners and decision makers who need site-specific information on the effects of LULC alterations on values of forest ecosystem services, the study's findings are essential. This will make it easier to track past environmental changes and obtain quick, accurate results for use in decision-making.

Land use and land cover changes and their impact on ecosystem service values in the north-eastern highlands of Ethiopia.

The land use and land cover (LULC) changes driven by the growing demands of mankind have a considerable effect on ecosystem services and functions. The study was carried out in the north-eastern highlands of Ethiopia to (1) analyze the effect of LULC changes between 1984 and 2021 and (2) assess the spatiotemporal variations in ecosystem service values (ESVs) and elasticity in response to LULC changes. Using Landsat imageries from 1984 to 2021, the spatiotemporal changes in LULC were evaluated with supervised image classification using maximum likelihood algorithm in ArcGIS software. Six LULC types were subsequently categorized, with overall accuracy and Kappa coefficients above 87% and 0.87, respectively. The ESVs were then estimated based on the Benefit Value Transfer (BVT) approach employing modified conservative value coefficients. The findings revealed a significant increase in cultivated land (9759.1ha) and built-up area (10174.41ha) during the stipulated periods and a drop in other land use types. The forest loss gradually decreased from 4.1% in the second period (1991-2001) to 0.58% in the third (2001-2021), compared to the first of the 1.1% conversion rates. Similarly, the proportion of grassland and water bodies steadily reduced over the stipulated periods, by 1.15% and 2.3% per annum, respectively. The overall loss of ESVs in the study landscape was estimated to be 54.4 million US$ (67.3%), drastically decreasing from 80.3 million US$ in 1984 to 26.4 million US$ in 2021, driven by the declining area coverage of water bodies, grassland, and forestland. Regardless of the loss, the ecosystem functions of hydrological regulation (37.2, 35.0, 6.1, and 5.1 US$ ha-1yr-1), water supply (14.5, 13.6, 2.4, and 2 US$ ha-1yr-1), and food production (9.8, 10.0, 9.1, and 9.9 US$ ha-1yr-1) contributed the most to the total ESV of each year while disturbance regulation and cultural values were the least throughout the study periods. The coefficient of sensitivity (CS) analysis revealed that our estimates were relatively robust. The findings further showed that human-dominated land-uses at the expense of natural ecosystems are the primary drivers of LULC transitions and the ensuing loss of ecosystem services in the region. Thus, this calls for intensive work on more effective land use policies that encourage an integrated management approach, with a focus on safeguarding the sustainability of natural ecosystems.

Impact of land use and land cover change on land surface temperature over Lake Tana Basin

Isolation of climate and Land Use and Land Cover (LULC) changes and their compounded effect is complicated since the two influence each other through forcing-feedback cycles. This study investigates the changes in LULC and its contribution to the change in surface and air temperature in the Lake Tana Basin using data obtained from MODIS remote sensing satellites, ground observation and reanalysis model. Observation minus reanalysis (OMR) method and various analysis tools are used to estimate the impact of LULC changes on temperature. The analysis of LULC change indicates that an increase of Savanna and other type of forest cover by about 519 km2 from year 2001 to year 2020. Wetland increased by about 83.7 km2 during the said period. During the period 2001–2020, about 56.5% baren-land areas are being converted into wetland. The conversion of water bodies and baren land to wetland is likely due to the increase of water hyacinth on both the water body and nearby baren-land whereas the increase in Savanna is linked to an on-going eucalyptus tree plantation. The negative correlation between LST and NDVI (reaching a value of −0.60) is noticed over the Basin throughout the year on inter-annual time scale. An increase in vegetation cover such as Savanna and broad leaf forest coincides with the decreasing LST with an average rate of 0.08%/decade. Also, a reduction in temperature, derived from OMR, at an average cooling rate of about 0.87%/decade is observed in the study period. However, an increase in the LST change rate over built-up and grassland is about 0.03%/decade. Therefore, we conclude that the consistent associations of the increase in areal coverage of the some LULC types with lowest LSTs, 2m-temperature and temperature trend derived from NDVI-LST and LULC-LST associations as well as OMR temperature and LST are unambiguous signatures of the effect of LULC change on temperature over Lake Tana Basin, distinct from that arising due to climate change.

Impacts of Land Use and Land Cover Change on Vegetation Diversity of Tropical Highland in Ethiopia

Ethiopia has undergone a substantial shift in land use and land cover (LULC), which is home to the majority of the human and animal population. Land degradation has occurred in the Ethiopian highlands as a result of modifications in LULC caused by poor farming methods, high livestock population, and human pressures. Most researchers identified the many LULC drivers and their impact on floristic composition. All of these manifestations have the potential to have major consequences for land users and individuals whose livelihoods rely on the products of a healthy environment. This change in LULC type, combined with poor land management practices in Ethiopia, puts land in jeopardy of erosion, resulting in accelerated soil degradation. All LULC variables, such as the spread of various agricultural activities, the production of fuelwood and charcoal, cutting trees for construction resources, settlements, and revenue growth, are associated with population increase and resettlement. In Ethiopia, the lack of a relevant forest policy implementation on the ground is recognized as a cause pushing deforestation and other landscape changes. This review paper aimed to compile the effects of land use land cover changes on Ethiopian vegetation.

Assessment and prediction of carbon storage based on land use/land cover dynamics in the coastal area of Shandong Province

Changes in land use and land cover (LULC) promote regional carbon storage capacity or trigger carbon depletion, which in turn exhibited significant impact on global climate change. Understanding the impacts of LULC on changes of carbon storage in coastal areas plays a critical role in the conservation of regional ecosystems and sustainable socio-economic development. The present study acted the coastal area of Shandong Province as an example to analyze the relationship between LULC and carbon storage combined with the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) and Patch-generating Land Use Simulation (PLUS) model. We further predicted the variation of carbon storage through the change of LULC types under three scenarios in 2030. Our results showed that cropland (which decreased by 9.41%) and built-up land (which increased by 7.66%) underwent the most significant changes over the past 20 years, while forest, grassland, wetland, water and bare land underwent less changes. As the dominant land type, cropland was also the most important carbon pool with medium carbon storage. Areas with high carbon storage were distributed in the mountains and hills, where the main land types were grassland and forest. In addition, wetland located in the Yellow River Delta also stores large amounts of carbon. Accordingly, areas with low carbon storage were widely distributed in built-up land of urban metropolitan regions. We pinpointed that the carbon storage in the coastal area of Shandong Province lost 47.96×106Mg due to the increasing of built-up land and the decreasing of cropland and forest, while ecological protection measures would effectively enhance regional carbon storage. Specifically, the regional carbon storage could be increased by 6.64×106Mg when the conversion of cropland, forest and grassland into built-up land was reduced by 20% and the conversion of wetland and water into built-up land was reduced by 30% (under the ecological priority scenario (EP)). We believe the present study could be a valid reference for administrators to develop policies in more reasonable planning of land use and urban development to achieve carbon peaking and carbon neutrality (“Dual Carbon” goals).

Drought-induced vulnerability and resilience of different land use types using time series of MODIS-based indices

Drought is a creeping and complex phenomenon that significantly impacts terrestrial ecosystem services by reducing the ecosystem's performance and upsetting the balance of the terrestrial carbon cycle. This study used Google Earth Engine (GEE) to quantify the effects of drought on the vulnerability and resilience of land use and land cover (LULC) types in the Karkheh basin, Iran's food basket and the third-largest basin in southwest Iran. Using MODIS data, we first extracted the vegetation health index (VHI) for drought monitoring during 2000–2020, and as a result, 2008 was designated as the drought year. Then, water use efficiency (WUE) was calculated for all LULC types during drought. In general, all LULC types experienced an increase in WUE, with the highest increase seen in the forest , which indicates the forest's high resistance to drought. To evaluate the ecosystems' resilience to drought, we computed the drought recovery period using the gross primary production (GPP). The results showed that recovery times varied among different LULC types, with the forest recovering in the shortest time, further indicating a higher resilience and greater importance for the absorption and stabilization of terrestrial carbon. Conversely, rainfed farming had the longest recovery time, indicating a higher vulnerability and, consequently, a greater need for the adoption of appropriate adaptive measures. The results of this study provide a better understanding of the response of different LULC types and their resilience to drought and can assist ecosystem conservation and LULC management.

Evaluation of predicted loss of different land use and land cover (LULC) due to coastal erosion in Bangladesh

Coastal erosion is one of the most significant environmental threats to coastal communities globally. In Bangladesh, coastal erosion is a regularly occurring and major destructive process, impacting both human and ecological systems at sea level. The Lower Meghna estuary, located in southern Bangladesh, is among the most vulnerable landscapes in the world to the impacts of coastal erosion. Erosion causes population displacement, loss of productive land area, loss of infrastructure and communication systems, and, most importantly, household livelihoods. With an aim to assess the impacts of historical and predicted shoreline change on different land use and land cover, this study estimated historical shoreline movement, predicted shoreline positions based on historical data, and quantified and assessed past land use and land cover change. Multi-temporal Landsat images from 1988–2021 were used to quantify historical shoreline movement and past land use and land cover. A time-series classification of historical land use and land cover (LULC) were produced to both quantify LULC change and to evaluate the utility of the future shoreline predictions for calculating amounts of lost or newly added land resources by LULC type. Our results suggest that the agricultural land is the most dominant land cover/use (76.04% of the total land loss) lost over the studied period. Our results concluded that the best performed model for predicting land loss was the 10-year time depth and 20-year time horizon model. The 10-year time depth and 20-year time horizon model was also most accurate for agricultural, forested, and inland waterbody land use/covers loss prediction. We strongly believe that our results will build a foundation for future research studying the dynamics of coastal and deltaic environments.

Hydrological Responses to Land Use/Land Cover Changes in Koga Watershed, Upper Blue Nile, Ethiopia

Information on land use and land cover modification and their related problems for the streamflow and sediment yield are crucial for spatial planners and stakeholders to devise suitable catchment resources management plans and strategies. This research sought to assess the changes in land use and land cover (LULC) effects on the streamflow and sediment yield of the Koga watershed. Landsat-5 TM, Landsat-7 ETM+, and Landsat-8 OLI data were used to create the land use and land cover maps. The LULC type identification analysis was performed by using ERDAS Imagine 2015. After the supervised classification, the land use and land cover maps for three distinct years (1991, 2008, and 2018) were generated, and the accuracy of the maps was reviewed. The LULC change analysis results were pointed out, as there was an appreciable LULC change in the study watershed. Agricultural land increased by 14.21% over the research period, whereas grassland decreased by 22.91%. The other LULC classes (built-up area, forest area, water body, and wetland) increased by 0.39%, 6.36%, 4.30%, and 0.46%, respectively. Contrarily, bushland decreased by 2.80%. Human activities were decisive in the significant land use alterations within the catchment. The flow rate of the river basin increased over the rainy season in the years 1991–2008 and declined in the drier months. The watershed’s sediment yield increased from 1991 to 2008 as a result of the extension of its agricultural area. Thus, the findings of this investigation demonstrated that the flow and sediment yield characteristics are changed because of the modifications within the LULC in the catchment. Some downstream and upstream parts of the area are exposed to comparatively high erosion, and the maximum amount of sediment is generated during the rainy season.

Landscape Ecological Risk Assessment during 2000–2020 Based on Land Use and Land Cover Changes in Lanzhou City

A landscape ecological risk model was constructed to evaluate the landscape ecological risk pertaining to Lanzhou City based on the land use and land cover (LULC) changes obtained using remote sensing data for the years 2000, 2010, and 2020 covering the duration 2010–2020. Results show that during 2010–2020, the LULC types in Lanzhou City mainly comprised of cropland, grassland, and construction land. In terms of LULC changes in Lanzhou City the trend shows a decrease in cropland and increase in construction land with an increase in the fragmentation and separation of cropland, grassland, and shrubland, which is pronounced for cropland and shrubland. The spatial distribution pattern of ecological risk shows very high and very low levels of risk in the main urban area in the south and in the northwest of the city, respectively. From 2010 to 2020, the ecological risk level of the landscape shows a gradual increase with evidence for significant changes. The results of the study provide a scientific basis for the optimization of the landscape pattern, rational utilization and development of land resources in Lanzhou City, and lay a solid foundation for the formulation of ecological risk control measures.

Assessing the Inter-Relationship between Rural Population Migration and Environmental Change in the Dano Watershed, Burkina Faso

The study analyses the Land Use and Land Cover (LULC) dynamics as an important environmental factor and links it to migration trends towards the study area. The work uses data collected across two (2) villages, both located in the Dano watershed. Three sets of 30-m Landsat images were used to measure the changes in LULC types for the years 1986, 1999 and 2014. Cumulatively focus group discussion and household interview were employed for socio-economic data collection. Census data for the periods 1987, 1996 and 2006 were also collected from the national census reports. LULC analysis revealed that vegetation area was progressively converted into croplands with an annual rate of 0.92% during the period of study. Pearson correlation analysis between population and cropland on one hand and population and vegetation on the second hand revealed a high positive correlation between population size and cropland (r = 0.99), while there was a high negative correlation between population size and vegetation (r = 0.96). The survey of 180 farmers revealed a diversity of questions about environmental change on their livelihood. Most 78% of farmers believe that deforestation is the main driver of environmental change as a result of the decrease of rainfall and strong wind. Many strategies are used by local communities as a response to environmental changes and migration is seen by 31% of the respondents as a common strategy used by the affected communities. These results from the study showed that migration is one of the major local responses to environmental change.

Application of machine learning approaches for land cover monitoring in northern Cameroon

Machine learning (ML) models are a leading analytical technique used to monitor, map and quantify land use and land cover (LULC) and its change over time. Models such as k-nearest neighbour (kNN), support vector machines (SVM), artificial neural networks (ANN), and random forests (RF) have been used effectively to classify LULC types at a range of geographical scales. However, ML models have not been widely applied in African tropical regions due to methodological challenges that arise from relying on the coarse-resolution satellite images available for these areas. In this study, we compared the performance of four ML algorithms (kNN, SVM, ANN and RF) applied to LULC monitoring within the Mayo Rey department, North Province, Cameroon. We used satellite data from the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) combined with 8 Operational Land Imager (OLI) images of northern Cameroon for November 2000 and November 2020. Our results showed that all four classification algorithms produced relatively high accuracy (overall classification accuracy >80%), with the RF model (> 90% classification accuracy) outperforming the kNN, SVM, and ANN models. We found that approximately 7% of all forested areas (dense forest and woody savanna) were converted to other land cover types between 2000 and 2020; this forest loss is particularly associated with an expansion of both croplands and built-up areas. Our study represents a novel application and comparison of statistical and ML approaches to LULC monitoring using coarse-resolution satellite images in an African tropical forest and savanna setting. The resulting land cover maps serve as an important baseline that will be useful to the Cameroon government for policy development, conservation planning, urban planning, and deforestation and agricultural monitoring.

Land use and land cover changes influence the land surface temperature and vegetation in Penang Island, Peninsular Malaysia.

The ecological changes in vegetation and land of an area can be monitored and managed through the assessment of its past and present land use and land cover (LULC). In this study, we assessed the changes in the LULC of Penang Island between 2010 and 2021. We also determined the corresponding impacts on the land surface temperature (LST) and vegetation index in the form of normalized difference vegetation index (NDVI). Landsat-5 and Landsat-8 were selected for the study. The LULC types were classified using both supervised and unsupervised multivariate maximum likelihood techniques. The LULC change analysis revealed a considerable increase in the urbanized areas (45.71%), a slight increase in the forests (1.57%) and a sizeable reduction in the agricultural/herbaceous areas (- 33.49) of the city within the stipulated period. The urbanized areas were observed to have the highest LST in 2010 and 2021 (28.75-34.0°C) followed by the bare land (29.76-29°C). The increase in temperature could have been driven by the reduction in the greenness of the city coupled with the openness of vegetation cover. Similarly, strong positive correlations were observed between the LST and NDVI in the urbanized areas (R2 = 0.92), and bare lands (R2 = 0.86). We, therefore, hypothesize that urbanization is the main driver of the LULC changes on Penang Island.

Land use as an important indicator for water quality prediction in a region under rapid urbanization

Land use and land cover (LULC) have significant impacts on river water quality, particularly in regions subjected to rapid urbanization. However, it is unclear whether LULC (LULC type and pattern index) can be used as an effective indicator to predict water quality over the rapid urbanization regions. Here, we investigated the spatiotemporal changes of LULC and their impacts on the water quality of a river flowing through a rapidly developed area in China. Then, a cellular automata-Markov model was established to predict the LULC, which was used as a key indicator to predict future water quality by a multiple linear regression model. The results showed that construction land experienced rapid growth between 2000 and 2010 taking over arable land to a great extent, and the number of patch (NP) showed a significant downward trend during 2000–2010. The biochemical oxygen demand in five days (BOD5), total nitrogen (TN), and total phosphorus (TP) exhibited significantly positive correlations with construction land, while dissolved oxygen (DO) showed a significantly negative correlation with construction land. The DO exhibited a significantly positive correlation with the number of patch (NP), but TN and TP showed significantly negative correlations with NP. The water quality prediction model based on LULC performed well, especially TN prediction has a coefficient of determination of 0.691 and a mean relative error of 12.14%. The prediction of water quality in 2030 indicated that TN will not increase further, but TP will exhibit a remarkable increase in Zhenjiang city if the current development trend continues and no extra pollution control measures are taken.