Land Cover Change Research Articles

Land use land cover change detection in Baghdad city for the years 2000 and 2024 using random forest algorithm

Land use land cover change detection in Baghdad city for the years 2000 and 2024 using random forest algorithm

Prediction and Simulation for Land Use and Land Cover Change of Paddy Field Influence by Salinization in Coastal Demak Regency

The extent of coastal rice paddy agricultural land is vulnerable to land use and land cover (LULC) changes to non-agricultural uses due to land degradation, one of which is caused by salinity. This study aims to detect and project LULC changes up to 2031, particularly in coastal rice paddy areas affected by salinity, by comparing LULC in 2017, 2019, and 2021. Sentinel-2 Imagery is used for LULC classification, with recordings selected during the generative phase of rice growth to obtain the most optimal rice paddy area. There are six LULC classifications: water, wetland, low-medium-high vegetation cover, and built-up area. To understand the impact of salinity on crops, several vegetation indices (VIs) such as NDVI, SAVI, EVI, and ARVI are used. The LULC changes classified according to VIs are compared with the MOLUSCE plugin based on artificial neural networkmultilayer perceptron (ANN-MLP) and Cellular Automata (CA). The comparison of VIs results shows that NDVI is better at describing LULC changes due to the influence of salinity, with a kappa value of 0.63 and a Correctness of 72.565. The LULC projection using CA in all VIs indicates that wetland areas are more likely to convert into water bodies, suggesting that high salinity land tends to be unproductive for rice paddies, making it prone to conversion.

Productive conservation at the landslide prone area under the threat of rapid land cover changes

Abstract Landslides often occur in the study area as a continuation of the erosion process on very thick soil from a series of volcanic ash deposition during the Tertiary and Quaternary periods. Rapid land cover changes from agricultural land into settlement increase runoff significantly causing accelerated soil erosion. Soil conservation approaches using parameters to reduce surface runoff and soil loss are less acceptable in agricultural society. Soil conservation methods aimed at reducing runoff and soil loss are not widely embraced in agricultural communities, efforts in soil conservation must be economically beneficial. Vegetative-based erosion control is the most suitable option for the agricultural communities. However, there needs to be improvements in terms of plant arrangement that is adapted to the spatial arrangement of slopes and is focused on zones along rills and gullies. Selection of tree species planted for erosion control that have the value of increasing economic income is the key to the success of planned soil and water conservation efforts.

Remote Sensing Mapping and Analysis of Spatiotemporal Patterns of Land Use and Cover Change in the Helong Region of the Loess Plateau Region (1986–2020)

Land use and cover change (LUCC) is directly linked to the sustainability of ecosystems and the long-term well-being of human society. The Helong Region in the Loess Plateau has become one of the areas most severely affected by soil and water erosion in China due to its unique geographical location and ecological environment. The long-term construction of terraces and orchards is one of the important measures for this region to combat soil erosion. Despite the important role that terraces and orchards play in this region, current studies on their extraction and understanding remain limited. For this reason, this study designed a land use classification system, including terraces and orchards, to reveal the patterns of LUCC and the effectiveness of ecological restoration projects in the area. Based on this system, this study utilized the Random Forest classification algorithm to create an annual land use and cover (LUC) dataset for the Helong Region that covers eight periods from 1986 to 2020, with a spatial resolution of 30 m. The validation results showed that the maps achieved an average overall accuracy of 87.54% and an average Kappa coefficient of 76.94%. This demonstrates the feasibility of the proposed design and land coverage mapping method in the study area. This study found that, from 1986 to 2020, there was a continuous increase in forest and grassland areas, a significant reduction in cropland and bare land areas, and a notable rise in impervious surface areas. We emphasized that the continuous growth of terraces and orchards was an important LUCC trend in the region. This growth was primarily attributed to the conversion of grasslands, croplands, and forests. This transformation not only reduced soil erosion but also enhanced economic efficiency. The products and insights provided in this study help us better understand the complexities of ecological recovery and land management.

Detecting Land-Use Changes in Greater Kandy Development Area

As urban growth became a threat to Kandy city, the Urban Development Authority (UDA) has introduced a new concept called the “Greater Kandy Development Area (GKDA)” to control and manage the rapid urban growth, as well as to minimize its’ impacts towards the environment. This study examines the land use/ land cover changes in GKDA, in selected time periods using GIS and Remote Sensing techniques. Findings demonstrate that dynamic patterns of urban expansion cause progressive growth in built-ups and lowering in non-built-ups. In 2005, there were only 16.9 percent of built-up areas in GKDA but, it has increased up to 40 percent in 2020. 81.7 percent of non-built-up areas in 2005, has reduced up to 58.8 percent. As population growth happened inside the city limits, land use changes also happened within. These changes create clustered as well as sprawl development patterns.

Fusion of spectral and topographic features for land use mapping using a machine learning framework for a regional scale application.

This study investigated the dynamics of land use and land cover (LULC) modelling, mapping, and assessment in the Kegalle District ofSri Lanka, where policy decision-making is crucial in agricultural development where LULC temporal datasets are not readily available.Employing remotely sensed datasets and machine learning algorithms, the work presented here aims to compare the accuracy of three classification approaches in mapping LULC categories across the time in the study area primarily using the Google Earth Engine (GEE). Three classifiers namely random forest (RF), support vector machines (SVM), and classification and regression trees (CART) were used in LULC modelling, mapping, and change analysis. Different combinations of input features were investigated to improve classification performance. Developed models were optimised using the grid search cross-validation (CV) hyperparameter optimisation approach. It was revealed that the RF classifier constantly outstrips SVM and CART in terms of accuracy measures, highlighting its reliability in classifying the LULC. Land cover changes were examined for two periods, from 2001 to 2013 and 2013 to 2022, implying major alterations such as the conversion of rubber and coconut areas to built-up areas and barren lands. For suitable classification with higher accuracy, the study suggests utilising high spatial resolution satellite data, advanced feature selection approaches, and a combination of several spatial and spatial-temporal data sources. The study demonstrated practical applications of derived temporal LULC datasets for land management practices in agricultural development activities in developing nations.

Land Cover Simulation and Carbon Storage Assessment in Daqing City based on FLUS-InVEST Model

Considering Daqing City as the research area, the impact of land cover change on carbon storage in the future was discussed, and the hot spots of carbon sequestration capacity were identified. The future land use simulation （FLUS） model was used to simulate the land cover pattern of a natural succession scenario, ecological protection scenario, urban development scenario, and comprehensive development scenario in 2030, and the integrated valuation of ecosystem services and trade-offs （InVEST） model was combined to estimate carbon storage in 2010, 2020, and 2030. Finally, the hot spot analysis tool was used to identify the cold hot spots of carbon sequestration capacity. The results showed the following： ① From 2010 to 2020, the area of cultivated land, water, and artificial surface increased, whereas the area of other land cover types decreased, and the total carbon storage decreased by 8.6×105 t. ② The land cover change of the natural succession scenario and urban development scenario in 2030 was similar to that of 2010-2020, with carbon storage decreasing by 1.16×106 t and 1.20×106 t, respectively. The carbon storage of the comprehensive development scenario decreased by 1.00×106 t compared with that in 2020, and carbon storage of the ecological protection scenario was 5.677 7×108 t, which increased by 2.53×106 t compared with that in 2020. ③ The conversion of grassland and wetland to cultivated land was the main cause of carbon storage loss, and the main contributor of carbon storage in the ecological protection scenarios was wetland. ④ The hot spots of carbon sequestration capacity were mainly located in the wetland area, and the cold spots were mainly distributed in the central part of Daqing City. The carbon sequestration capacity of cultivated land was not significant. According to the research results, to realize the urban transformation of Daqing City, we should insist on returning farmland to forest and grass, increase the intensity of returning moisture, improve the utilization rate of urban land, and increase green infrastructure in the main urban area.

Land cover and burn severity dynamics of the Ogan Komering Ilir peatlands from 2015 to 2023 using sar and optical datasets

Land cover changes and wildfires have had an increasing impact on the Ogan Komering Ilir Peatland ecosystems in South Sumatra, Indonesia. This study aims to understand the peatland land cover and burn severity dynamics from 2015 to 2023. The random forest method was applied to classify land cover, while the differenced Normalized Burn Ratio (dNBR) was used for mapping fire severity. We combined various satellite data to classify land cover, consisting of Landsat-8, Sentinel-1, and Sentinel-2. Landsat-8 or Sentinel-2 images were also used for the dNBR calculation. We revealed complex climate, human, and restoration interactions in land cover and burn severity fluctuations over 273,799 hectares of the study area from 2015 to 2023. The 2015 El Niño-induced drought led to 21,754 fire hotspots and 2.01% of the area in high-severity burns. In 2016, it reduced tree cover by 10.18% and increased bare/sparse vegetation by 6.11%. The 2019 El Niño event led to 7,893 fire hotspots, lessening unburned areas and worsening burns. Due to the extreme effects of the 2015 drought, restoration efforts between 2016 and 2020 significantly decreased fire hotspots in 2016. Tree cover stabilized, reaching 48.46% by 2020, whereas unburned areas rose to 69.46% in 2018, showing good recovery and lower fire severity. In 2021-2023, fire hotspots were modest relative to El Niño years but increased in 2023. After 2020, tree cover decreased, but other land cover classes fluctuated. Therefore, continual monitoring and adaptive management are critical for reducing negative consequences and increasing ecosystem resilience.

Changing windstorm characteristics over the US Northeast in a single model large ensemble

Abstract Extreme windstorms pose a significant hazard to infrastructure and public safety, particularly in the highly populated US Northeast (NE). However, the influence climate change and changing land use will have on these events remains unclear. A large ensemble generated using the Max-Planck Institute (MPI) Earth system model is used to generate projections of NE windstorms under different shared socioeconomic pathways (SSPs) and to attribute changes to projected land use land cover (LULC) change, externally forced changes and internal climate variability. To reduce the influence of coarse grid cell resolution and uncertainties in surface roughness lengths, windstorms are identified using simultaneous widespread exceedance of local 99th percentile 10 m wind speeds (U99). Projected declines in forest cover in the NE and the resulting reductions in surface roughness length under SSP3-7.0 lead to projections of large increases in U99 and derived windstorm intensity and scale. However, these projected changes in regional LULC under SSP3-7.0 are unprecedented in a historical context and may not be realistic. After corrections are applied to remove the influence of LULC on wind speeds, regionally averaged U99 exhibit declines for most of the single model initial-condition large ensemble (SMILE) members which are broadly proportional to the radiative forcing and global air temperature increase in the SSPs, with a median value of −0.15 ms−1 °C−1. While weak cyclones are projected to decline in frequency in the NE, intense cyclones and the resulting windstorms and indices of socioeconomic loss do not. Where present, significant trends in these loss indices are positive, and some MPI SMILE members generate future windstorms that are unprecedented in the historical period.

High-Precision Heterogeneous Satellite Image Manipulation Localization: Feature Point Rules and Semantic Similarity Measurement

Misusing image tampering software makes it easier to manipulate satellite images, leading to a crisis of trust and security concerns in society. This study compares the inconsistencies between heterogeneous images to locate tampered areas and proposes a high-precision heterogeneous satellite image manipulation localization (HSIML) framework to distinguish tampered from real landcover changes, such as artificial constructions, and pseudo-changes, such as seasonal variations. The model operates at the patch level and comprises three modules: The heterogeneous image preprocessing module aligns heterogeneous images and filters noisy data. The feature point constraint module mitigates the effects of lighting and seasonal variations in the images by performing feature point matching, applying filtering rules to conduct an initial screening to identify candidate tampered patches. The semantic similarity measurement module designs a classification network to assess RS image feature saliency. It determines image consistency based on the similarity of semantic features and implements IML using predefined classification rules. Additionally, a dataset for IML is constructed based on satellite images. Extensive experiments compared with existing SOTA models demonstrate that our method achieved the highest F1 score in both localization accuracy and robustness tests and demonstrates the capability for handling large-scale areas.

How the characteristics of land cover changes affect vegetation greenness in Guangdong, a rapid urbanization region of China during 2001-2022.

To evaluate the quantitative impacts of land cover change on vegetation greenness in the significantly human-impacted subtropical region, the characteristics of land cover change were explored by land use dynamic degree, transition matrix and normalized entropy. Various methods including Standardized coefficient, LMG (Lindeman-Merenda-Gold), GEN (Genizi measure) and CAR (Correlation-Adjusted Marginal Correlation) were employed to estimate the contributions of land cover changes on vegetation greenness using MODIS data during 2001-2022 in Guangdong. The conclusions revealed that land cover changes exhibited obvious temporal characteristics in Guangdong with a significantly increasing trend of normalized entropy indicating a more balanced distribution of land cover types under human intervention. NDVI (Normalized Difference Vegetation Index) tended to increase likely due to the large-scale increase in evergreen forest. With regard to the contributions of impact factors on vegetation greenness, the contributions evaluated by LMG, GEN and CAR showed that the natural variation of NDVI accounted for the major contribution (> 33%), while the changes of evergreen forest and grassland had the highest contribution (> 37%) according to Standardized coefficient. These differences were mainly due to the characteristics of land cover changes in Guangdong, the correlations among impact factors and the inherent attributions of the methods. Moreover, the expansions of evergreen forest and urban at the expense of the reductions of grassland and cropland also had significant impacts on NDVI (> 10%) according to LMG, GEN and CAR indicating that human-induced land cover changes had remarkable influences on NDVI.

Habitat quality outweighs the human footprint in driving spatial patterns of Cetartiodactyla in the Kunlun-Pamir Plateau

The Human Footprint (HFP) and Habitat Quality (HQ) are critical factors influencing the species' distribution, yet their relation to biodiversity, particularly in mountainous regions, still remains inadequately understood. This study aims to identify the primary factor that affects the biodiversity by comparing the impact of the HFP and HQ on the species’ richness of Cetartiodactyla in the Kunlun-Pamir Plateau and four protected areas: The Pamir Plateau Wetland Nature Reserve, Taxkorgan Wildlife Nature Reserve, Middle Kunlun Nature Reserve and Arjinshan Nature Reserve through multi-source satellite remote sensing product data. By integrating satellite data with the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST)HQ model and utilizing residual and linear regression analysis, we found that: (1) The Wildness Area (WA) predominantly underwent a transition to a Highly Modified Area (HMA) and Intact Area (IA), with a notable 12.02% rise in stable regions, while 58.51% rather experienced a negligible decrease. (2) From 1985 to 2020, the Kunlun-Pamir Plateau has seen increases in the forestland, water, cropland and shrubland, alongside declines in bare land and grassland, denoting considerable land cover changes. (3) The HQ degradation was significant, with 79.81% of the area showing degradation compared to a 10.65% improvement, varying across the nature reserves. (4) The species richness of Cetartiodactyla was better explained by HQ than by HFP on the Kunlun-Pamir Plateau (52.99% vs. 47.01%), as well as in the Arjinshan Nature Reserve (81.57%) and Middle Kunlun Nature Reserve (56.41%). In contrast, HFP was more explanatory in the Pamir Plateau Wetland Nature Reserve (88.89%) and the Taxkorgan Wildlife Nature Reserve (54.55%). Prioritizing the restoration of degraded habitats areas of the Kunlun Pamir Plateau could enhance Cetartiodactyla species richness. These findings provide valuable insights for the biodiversity management and conservation strategies in the mountainous regions.

Hybrid Naïve Bayes Gaussian mixture models and SAR polarimetry based automatic flooded vegetation studies using PALSAR-2 data

Flood mapping using Synthetic Aperture Radar (SAR) data impose limitations in fully distinguishing flood under vegetation due to false double bounce returns from inundated tree trunks along with seasonal heterogeneities devised from changing land cover settings. In addition, rapid mapping of flooded vegetation is challenging during near real time applications. In this paper a fully automatic novel supervised classification approach called polarimetric Naïve Bayes is proposed that combines polarimetric information with series of Gaussian mixture models in Naïve Bayes framework to detect various flooded vegetation classes. It also allows the user to choose class configuration and eliminates creation of Region of Interest (ROI) for supervised training. The proposed approach uses scattering information from pre monsoon PolSAR dataset in training step to create ROIs for buildings and other features. In the next step series of Gaussian Mixtures are used for density estimation for different features in Bayesian multiclass problem. The newly developed classifier applied on 2016 Assam flood event resulted in precise mapping of at least three different vegetation classes under flood such as submerged vegetation, wetlands and floating vegetation. Under optimal class configuration, the approach showed better performance compared to other supervised techniques applied on the same data set such as MLE, Mahalanobis, Minimum Euclidean distance, and SVM classifications in delineating flood, submerged vegetation, wetlands and floating vegetation with Producer’s Accuracy of 98.6%, 81.1%, 94% and 51.5% respectively and combined Overall accuracy of 95.5% for flooded vegetation class. This method also detected multiple vegetation classes with better accuracy compared to similar methods.

Land use change and ecosystem service tradeoffs on California agricultural land

Abstract Introduction 
The need to transition to sustainable agricultural practices while maintaining high food yield and strengthening resilience to climate change cannot be overstated. California farmers have received incentive funding from federal and state agencies to use land management practices that are less impactful to the land and in line with California’s sustainability goals. However, there are no regional monitoring measures to determine whether farming is becoming more sustainable. 

Methods 
In this study, we used land cover change analysis and ecosystem services modeling to understand how farming practices influence environmental benefits on California farmland from 2010 to 2020. We analyzed the tradeoffs between soil erosion control, soil carbon storage, and production of California’s top agricultural commodities, and we compared these changes to changes in land cover in five agricultural regions statewide. 

Results and Conclusion 
We found that the trade-offs in ecosystem services and food production differ depending on the regional context, and that major expansion in almond production and land use changes have had different impacts throughout California. Statewide, soil organic carbon storage increased, soil erosion control increased slightly, and food production boomed for most commodities. Incentive programs that influence farming practices may need to operate at a regional level rather than a statewide level to achieve sustainable outcomes specific to each region.

Impacts of Land Use and Land Cover Changes on Biomass and Carbon Sequestration in Coastal Kinondoni, Tanzania

Impacts of Land Use and Land Cover Changes on Biomass and Carbon Sequestration in Coastal Kinondoni, Tanzania

Effects of urbanization on river morphology in a Mediterranean coastal city (Genova, Italy)

From the geomorphological point of view, urbanization changes fluvial systems more drastically than any other single human activity. Its impact on rivers is of interest as it results in serious issues concerning geomorphic instability, ecosystem service reduction, and geo-hydrological risk increase. The present study provides a quantitative and qualitative assessment of landscape changes driven by urbanization, which occurred from the mid-19th century to the present day along the lower reaches of the Bisagno and Polcevera rivers and their tributaries in the Mediterranean coastal city of Genova (NW Italy). The bankfull channel morphological adjustments, the minor hydrographic network disappearance, the land use and land cover changes, and the current physical accessibility of river margins were investigated. This work is based on collection and review of historical data, photograph interpretation, GIS analysis, and field surveys. Urbanization essentially occurred between the mid-19th century and the late 1930s. The bankfull channel of the Bisagno and Polcevera rivers experienced large narrowing associated with widespread establishment of channelization structures. The minor hydrographic network essentially disappeared underground. After the 1930s, further minor anthropogenic interventions were implemented to accommodate urban expansion and consolidate channelization works; however, the overall geomorphological setting remained unchanged. The geomorphological evolution of the Bisagno and Polcevera rivers followed three different phases associated with the urban expansion process. Nowadays, the study area is completely urbanized, the fluvial stems flowing through the valley floor are totally disconnected from their adjacent areas, the main rivers show a relevant geomorphological stability induced by anthropogenic pressures, and the accessibility of river margins for people is rather limited. The outcomes from this study represent an essential knowledge base for technicians and policymakers to plan urban development and inform effective and sustainable management measures. Moreover, they provide insights into the medium- and short-term morphological evolution of urban rivers.

Narrowing down the drivers of flood risk in medium-sized sub-Saharan African cities: insights from the Greater Kumasi Metropolitan Area, Ghana

ABSTRACT Literature on the drivers of flooding in sub-Saharan Africa is mostly focused on large and megacities, despite the majority of cities in the region being medium- and small-sized. We conducted a systematic review using 27 peer-reviewed scientific papers selected following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocols using the Greater Kumasi Metropolitan Area (GKMA), Ghana, as a case study, and validated the results in a workshop attended by 51 stakeholders. We found that the reported drivers of flood risk in GKMA are land cover changes (61.5%) (e.g. wetlands degradation); governance challenges (16.2%); challenges with drainage (13%); extreme rainfall (6.5%); and apathy towards nature (3.2%). We conclude that floods in GKMA are overwhelmingly human induced through unsustainable urbanization processes that are so rapid that city authorities are unable to properly control them. Also, a holistic understanding of flood risk is missing since majority of the included papers rather used qualitative methodologies.

Temporal Analysis of Riparian Buffer Zones and Demographic Trends in the Coastal Districts of Kastamonu

Aim of study: This study investigates the temporal changes of forest areas within and outside the Riparian Buffer Zones (RBZs) and examines their correlation with demographic trends in the coastal districts of Kastamonu from 1987, 2000, and 2016 to assess how population dynamics influence forest cover. Area of study: The study was conducted in four coastal districts in northern Kastamonu province, Türkiye, covering approximately 1000 square kilometers and focusing on 153 forest villages. Material and methods: Geographic Information Systems and remote sensing data delineated and analyzed land cover and population changes. The study used Landsat imagery and population data to explore spatial and temporal dynamics within the RBZs Main results: The study found a significant increase in forest area from 1987 to 2000 and a subsequent decrease from 2000 to 2016, with these changes showing a weak but significant negative correlation with the declining local population. Research highlihts: The findings suggest that declining rural populations may reduce anthropogenic pressures on forests and pose challenges to effective forest management and conservation. The research highlights the need for sustainable strategies integrating demographic change with forest conservation efforts to maintain ecosystem services and biodiversity.

Assessment of the spatial-temporal impact of the Longhai Railway transportation corridor on land cover changes and landscape patterns

IntroductionTransportation corridors, as special economic corridors, have a greater impact on land cover and landscape pattern changes.MethodsTherefore, 10 buffer zones were established at 1 km intervals on both sides of the Longhai Railway as the centerline to trace the impact of the railroad corridor on the land use change and regional landscape pattern change of the cities along the line from 1985 to 2020.ResultThe results show that: (1) The land cover changes along the railroad corridor during the 35 years are mainly characterized by the conversion between cropland, grassland, and construction land. Compared with 1985, in 2020, the construction land increased by 161.96%, the grassland area decreased by 11.83%, and the cropland area decreased by 15.83%. (2) The fragmentation of land patches and vegetation coverage is negatively and positively correlated with the buffer zone distance, respectively. In the same year, the comprehensive land-use dynamic degree is smaller as it is further away from the railway. The nighttime light index in the buffer zone is significantly correlated with the land aggregation index and average patch area, and the closer to the railroad, the higher the land aggregation index of construction land. (3) In terms of zoning, the intensity of land cover and landscape pattern changes in the eastern section is higher than that in the western section, with a higher degree of land fragmentation and more agglomeration of construction land, and the transportation corridor has a greater impact on the change of integrated land use motives in this region. The results of the study can provide a scientific basis for optimising the spatial pattern of land and improving the ecological environment in the construction of cross-regional transport corridors.

Analysis of short- and long-term controls on the variability of event-based runoff coefficient

Study regionThis study focuses on the Ohio Region, which spans 11 states in the eastern United States. Study focusRunoff coefficients are crucial in hydrology, indicating the relationship between rainfall and runoff. Understanding their controls and variability is essential for water resource assessment, management strategies, and land use planning. This research examines factors influencing runoff coefficients and their trends in the Ohio region using data from the North American Land Data Assimilation System phase-2 (NLDAS-2) Mosaic Land Surface Model, covering 2000–2020. The analysis considers short-term controls, such as climatic features (rainfall intensity, amount, and duration), hydrological factors (antecedent soil moisture, drainage density, and curve number), topographic factors (drainage area, land use, slope, elevation), and watershed shape. Additionally, the study investigates trends in runoff coefficients and their long-term controls, including climatic factors and land use changes. New hydrological insights for the regionThe findings indicate that runoff coefficients increase with antecedent soil moisture and rainfall intensity. Higher elevations show lower runoff coefficients due to forested land use. Larger watersheds have lower runoff coefficients at low rainfall intensity but higher ones when intensity is high. Long-term trends reveal soil moisture as the primary control, with land cover changes as a secondary factor. This research deepens understanding of runoff coefficient dynamics and controls in the Ohio region. Future studies could explore the impacts of urbanization, reservoirs, evapotranspiration, and snowmelt on runoff coefficients.