Land Cover Characteristics Research Articles

Zoonotic implications of white-footed mice habitat selection and territoriality in fragmented landscapes.

White-footed mouse (Peromyscus leucopus) populations can thrive in fragmented suburban and urban parks and residential spaces and play a pivotal role in the spread and prevalence of tick-borne diseases. We collected spatial data on 58 individual mice living at the intersection of county park land and residential land in suburban Howard County, MD, U.S.A. We analyzed mouse density, home-range size and overlap, and a Bayesian mixed-effects model to identify the habitats where they were found relative to where they were caught, as well as a resource selection function for general habitat use. We found that as mouse density increased, home-range size decreased. The overlap indices and the resource selection function supported territoriality coupled with site-specific space use in these suburban mouse populations. While mice occurred in open areas, forest edge, and forest, they showed a strong preference for forested areas. Interestingly, mice captured only 30 to 40 m into the forest rarely used the nearby private yards or human structures and this has direct implications for the placement of rodent-targeted tick control treatments. Our study supports the need for zoonotic disease management frameworks that are based on site-specific land cover characteristics as well as specific management objectives.

An Assessment of Landscape and Land Use/Cover Change and Its Implications for Sustainable Landscape Management in the Chittagong Hill Tracts, Bangladesh

Human-caused environmental change has profoundly impacted resource management and land use patterns in Bangladesh’s Chittagong Hill Tracts. This study used multi-temporal Landsat images from 1998, 2008, and 2018 to analyze land use and land cover changes, particularly those associated with forest cover changes, in Bangladesh’s Chittagong Hill Tracts. Using object-based image classification, Landsat images from 1998, 2008, and 2018 were separated into four categories based on their dominant land use and land cover features: forest, grassland, water bodies, and bare land. Post-classification comparison was used to assess the degree and frequency of change, and this method was further developed to evaluate the balance, fluctuation, and adaptation of forests. In addition, the spatial structure of land cover and temporal trajectories related to changes in forest cover were studied. The CA–Markov chain model was also used to anticipate the 2048 LULC map. The image classification of the years 1998, 2008, and 2018 showed that the overall accuracy was 89.65%, 84.44%, and 86.26%; producer accuracy was 90.00%, 68.75%, and 72.22%; and the Kappa coefficient was 85.68, 82.84, and 76.36, respectively. The results showed that between 1998 and 2018, forest cover increased by 58.03%, transforming grassland to forest; grassland increased by 29.50%, converting bare land to grassland; and forest conversion to grassland was 13.34%. In addition, the result of the landscape metric revealed that during the whole study period, class level indicated a fragmentation of forest, bare land, grassland, and water in the CHT, and landscape level indicated by Shannon’s Diversity Index and Shannon’s Evenness Index showed a slight decrease in the land. Based on the CA–Markov model, forest area is predicted to expand to 9129 Km2 in 2048; however, other land uses (bare land and grassland) continue to decrease. This substantial increase in forest cover results from effective forest management based on community forestry practices and the successful execution of Bangladesh’s national forest strategy. However, as Bangladesh’s population rises, so does the country’s need for lumber/timber. Bangladesh’s government should revise its forest policy to meet the local community’s needs without endangering the forest, and policymakers must take climate change seriously. Our strategy for evaluating the critical indicators of changes in forest cover and pathways of change will aid in connecting these patterns to the dynamics of change, such as deforestation and reforestation. It would therefore serve as a framework for developing effective conservation and management plans for the Chittagong Hill regions in Bangladesh.

WATER AND VEGETATION COVER CHANGE DETECTION USING MULTISPECTRAL SATELLITE IMAGERY: A CASE STUDY ON JHENAIDAH DISTRICT OF BANGLADESH

Water and vegetation are the two most important land cover features of any natural setting. The Jhenaidah District of Bangladesh is known for its remarkable physical geography, featuring diversified vegetation cover and numerous oxbow lakes. Due to several anthropogenic causes, this majestic land cover is degrading rapidly. This study examines the study area's spatiotemporal water and vegetation cover change from 1990 to 2020. Freeware Satellite imageries from the USGS data archive were used as the main secondary data source, ensuring consistency by collecting dry season images. In addition, open discussions with the residents provided valuable insights into the situation. Remote sensing (RS) based Soil Adjusted Vegetation Index (SAVI) was used to detect the water and vegetation cover from the preprocessed satellite imageries. Furthermore, the water and vegetation cover were classified based on a scheme developed by field observation and discussion with the residents. The analysis reveals an overall 84.47% decline in dense vegetation, 63.01% decline in deep water cover, 185.69% increase in shallow water cover, and 16.08% increase in agricultural lands within the mentioned time frame. Almost all the upazila of Jhenauidah district experience the criticality of the land cover change. Among the upazila, Shailkupa faced an unprecedented decline in deep water (95.29%), and Kaliganj faced a heavy decrease in forested vegetation (92.40%). In contrast, shallow water expanded significantly in Sadar Upazila (251.37%), and agricultural land experienced the most increasing trend (32.70%) in Shailakupa Upazila.

Using social media data and machine learning to map recreational ecosystem services

Crowdsourced geotagged social media data and machine learning approaches have emerged as promising tools for mapping ecosystem services, especially cultural ecosystem services that are difficult to assess. Here, we use recreation to show how social media data, machine learning, and spatial analysis techniques can improve our understanding of human-nature interactions and the mapping of recreational ecosystem services. We extracted 80,500 photographs taken in non-urban areas of the Tahoe Central Sierra Initiative project area in California between 2005 and 2019 that were posted to the photo sharing application Flickr and used these as a proxy for recreational visits to the area. Automated image content analysis was used to identify the objects and concepts in the photographs and uncover the types of nature experiences that are important to visitors. Additionally, variable importance, a Random Forest machine learning technique, was used to examine the environmental and landscape variables that drive recreation in the area and to create a classification model that predicts the recreation potential of the entire area based on important variables. The automated image content analysis identified 1,239 unique labels linked to recreation, with mountains, hills, and rocks being the most prominent features (22%). Our Random Forest model indicates that vegetation cover, land cover, elevation, smoke days, and landscape features are major drivers of recreation in the area and are of interest to visitors in the area. The model predicted that 25.9% of the area has the potential to support recreational visits. Most of these recreation potential areas are in protected areas (77.8%), predominantly in conifer forests (66%) and within national forest boundaries, especially the Tahoe National Forest area (37.6%). These results show that recreational ecosystem services vary across landscapes and illustrate the need for improved mapping approaches to determine the provision of ecosystem services in different places. The analysis provides novel insights into the various ways social media data and machine learning techniques can be powerful components of ecosystem service research and how they hold great potential for monitoring and informing management interventions on ecosystem service provision, especially in places with limited traditional onsite visitation data.

Spatiotemporal and Driving Factors of Land-Cover Change in the Heilongjiang (Amur) River Basin

Monitoring land-use and land-cover change (LUCC) is extremely important in the sustainable development and management of terrestrial ecosystems. Taking the Heilongjiang (Amur) River Basin as the study area, this study aimed to identify the spatiotemporal characteristics of land cover at the entire basin and at the country levels of the three countries using the land-use change index, frequency statistics and land-cover change degree. The results showed that: (1) The LULC types were mainly forest land and grassland (accounting for nearly 83% in total) from 2001 to 2019. The main land-cover types in China, Russia and Mongolia were forest land, forest land and grassland, respectively. (2) The area of urban land, cropland and wetland increased significantly from 2001 to 2019, while the area of forest land and bare land decreased during this time. In general, the ecological environment has greatly improved over the last 19 years, although the relevant ecological restoration still needs to be further implemented. The findings can provide a scientific basis for ecological protection and sustainable development in the Heilongjiang (Amur) River Basin. The approaches here are also applicable to land-cover change research in other similar regions.

Modeling the impact of urban land cover features and changes on the land surface temperature (LST): The case of Jordan

Higher land surface temperature (LST) in cities than their surrounding areas presents a major sustainability challenge for cities. Decision-makers and planners use the LST measurements to monitor the urban environment to reduce the urban climate’s main challenges. Therefore, there is an urgent need to examine the impacts of urban features and changes on the LST. This study focused on the relationship between LST and urban land changes and the impact of these changes on LST during different periods. Although a set of studies explored the relationship between landscape features and urban LST, several aspects still need further discussion. Here, the study aims to explore the influence of landscape features and land cover patterns on land surface temperature LST in two cities (Amman and Zarqa) in Jordan, and identify which of these features (vegetation cover, built-up and population density) has the most effective and influence on LST values. Therefore, this paper is the first study about land surface temperature LST and its relations with these aspects in Jordan. This study used a mixed method approach using quantitative method (GIS) and qualitative method (comparative case studies). This study revealed that the most important features affecting the LST values were: (1) Population density; (2) Built-up; and (3) Vegetation, and in descending order from the strongest to the least effective. It is also concluded that in the city in which the population density is high, the effect of built-up areas on the values of LST is as high as possible and positive more than the cities with medium and low population density. As for the city in which the population density is medium to low, the effect of vegetation cover on the values of LST is greater, and this can be more positive than in cities with a high population density. Therefore, the study contributes to improving the planners' and policymakers’ suitable future decisions for making sustainable cities.

Investigation of the Microenvironment, Land Cover Characteristics, and Social Vulnerability of Heat-Vulnerable Bus Stops in Knoxville, Tennessee

The urban heat island is a climate, public health, and environmental justice issue. Sustainable urban infrastructure needs improvements in public transport to protect citizens’ health from the urban heat island. This case study investigates the local microenvironment and social vulnerability of heat-vulnerable bus stops in Knoxville, Tennessee, using publicly available data from a variety of sources. These included ground and satellite measurements of heat and humidity from the Knoxville Heat Mapping Campaign, characteristics of land surface from the National Land Cover Dataset 2019 of the United States Geological Survey, and the 2018 Social Vulnerability Index from the U.S. Centers for Disease Control and Prevention. A geographic information system and a principal component analysis were used to identify social vulnerability in areas where the bus stops are located. The results show that most heat-vulnerable bus stops are poor microenvironments without trees and shelters. The hottest bus stops are concentrated in the highly developed and densely populated areas of West Knoxville and downtown Knoxville and in South, North, Northeast, and Northwest Knoxville, which are relatively high vulnerability clustered and have poor public infrastructure. The findings provide the foundation for mitigation strategies to better prepare local communities for climate change by identifying public transportation areas negatively impacted by the urban heat island.

High Resolution Forest Masking for Seasonal Monitoring with a Regionalized and Colourimetrically Assisted Chorologic Typology

Comparisons of recent global forest products at higher resolutions that are only available annually have shown major disagreements among forested areas in highly fragmented landscapes. A holistic reductionist framework and colourimetry were applied to create a chorologic typology of environmental indicators to map forest extent with an emphasis on large-scale performance, interpretability/communication, and spatial–temporal scalability. Interpretation keys were created to identify forest and non-forest features, and a set of candidate tree cover indices were developed and compared with a decision matrix of prescribed criteria. The candidate indices were intentionally limited to those applying only the visible and NIR bands to obtain the highest possible resolution and be compatible with commonly available multispectral satellites and higher resolution sensors, including aerial and potentially UAV/drone sensors. A new High-Resolution Tree Cover Index (HRTCI) in combination with the Green band was selected as the best index based on scores from the decision matrix. To further improve the performance of the indices, the chorologic typology included two insolation indices, a water index and a NIR surface saturation index, to exclude any remaining spectrally similar but unrelated land cover features such as agriculture, water, and built-up features using a process of elimination. The approach was applied to the four seasons across a wide range of ecosystems in south-eastern Australia, with and without regionalisation, to identify which season produces the most accurate results for each ecoregion and to assess the potential for mitigating the spatial–temporal scaling effects of the Modifiable Spatio-Temporal Unit Problem. Autumn was found to be the most effective season, yielding overall accuracies of 94.19% for the full extent, 95.79% for the temperate zone, and 95.71% for the arid zone. It produced the greatest spatial agreement between two recognised global products, the GEDI forest heights extent and the ESA WorldCover Tree cover class. The performance, transparency, and scalability of the approach should provide the basis for a framework for globally relatable forest monitoring.

Local Climate Zone Classification Using Daytime Zhuhai-1 Hyperspectral Imagery and Nighttime Light Data

The tremendous advancement of cities has caused changes to the urban subsurface. Urban climate problems have become increasingly prominent, especially with regard to the intensification of the urban heat island (UHI) effect. The local climate zone (LCZ) is a new quantitative method for analyzing urban climate that is based on the kind of urban surface and can effectively deal with the problem of the hazy distinction between urban and rural areas in UHI effect research. LCZs are widely used in regional climate modeling, urban planning, and thermal comfort surveys. Existing large-scale LCZ classification methods usually use visual features of optical images, such as spectral and textural features. There are many problems with hyperspectral LCZ extraction over large areas. LCZ is an integrated concept that includes features of the geography, society, and economy. Consequently, it makes sense to consider the characteristics of human activity and the visual features of the images to interpret them accurately. ALOS_DEM data can depict the city’s physical characteristics; however, images of nighttime lights are crucial indicators of human activity. These three datasets can be used in combination to portray the urban environment. Therefore, this study proposes a method for fusing daytime and nighttime data for LCZ mapping, i.e., fusing daytime Zhuhai-1 hyperspectral images and their derived feature indices, ALOS_DEM data, and nighttime light data from Luojia-1. By combining daytime and nighttime information, the proposed approach captures the temporal dynamics of urban areas, providing a more complete representation of their characteristics. The integration of the data allows for a more refined identification and characterization of urban land cover. It comprehensively integrates daytime and nighttime data, exploits synergistic information from multiple sources, and provides higher accuracy and resolution for LCZ mapping. First, we extracted various features, namely spectral, red-edge, and textural features, from the Zhuhai-1 images, ALOS_DEM data, and nighttime light data from Luojia-1. Random forest (RF) and XGBoost classifiers were used, and the average impurity reduction method was employed to assess the significance of the variables. All the input variables were optimized to select the best combination of variables. The results from a study of the 5th ring road area of Beijing, China, revealed that the technique achieved LCZ mapping with good precision, with a total accuracy of 87.34%. In addition, to examine and contrast the effects of various feature indices on the LCZ classification accuracy, feature combination methods were used. The results of the study showed that the accuracies of LCZ classification in terms of spectral and textural were improved by 2.33% and 2.19% using the RF classifier, respectively. The radiation brightness value (RBV) (GI value = 0.0212) attained the classification’s highest variable importance value; the DEM also produced a high GI value (0.0159), indicating that night lighting and landform features strongly influence LCZ classification.

One size does not fit all: The complex relationship between biodiversity and psychological well-being

Conserving urban biodiversity is often promoted as a ‘win-win’ nature-based solution that can help align public health and biodiversity conservation agendas. Yet, research on the relationship between biodiversity and psychological well-being reveals inconsistent and complex results. This body of research is also restricted to a few socio-cultural and environmental contexts and tends to ignore differences in individual characteristics, such as nature relatedness (i.e., emotional affinity to nature) and ecological knowledge, that can influence people’s experience of biodiversity. The aim of this interdisciplinary research is to explore the relationships between biodiversity and psychological well-being, and test the moderating effect of nature relatedness and ecological knowledge on these relationships. An ecological survey was conducted in 24 small urban gardens in Israel to measure the richness and abundance of birds, butterflies and plants, as well as land cover characteristics. In parallel, a social survey (close-ended questionnaires) was conducted in-situ to measure psychological well-being, nature relatedness, ecological knowledge, perceived species richness and socio-demographic variables. Psychological well-being measures were mostly associated with the cover of woody species, perceived species richness, and to a lesser extent, with actual species richness and abundance, for all taxa. Nature relatedness moderated these relationships. Respondents with high nature relatedness demonstrated positive well-being-richness relationships, while those with intermediate, or low nature relatedness showed no, or even negative relationships, respectively. Opposite relationships were recorded for bird abundance. Overall, individuals demonstrated poor ecological knowledge and this variable moderated only few relations between well-being measures, perceived butterfly richness and bird abundance. Our results demonstrate that one-size-does-not-fit-all when considering the relationship between psychological well-being and biodiversity, and that affinity to nature is a key moderator for this relationship. Designing urban green spaces that provide inclusive and meaningful nature experiences and foster emotional affinity to nature, is therefore key to aligning ecological and social objectives for sustainable urban planning.

Machine Learning Classifier Evaluation for Different Input Combinations: A Case Study with Landsat 9 and Sentinel-2 Data

High-resolution multispectral remote sensing images offer valuable information about various land features, providing essential details and spatially accurate representations. In the complex urban environment, classification accuracy is not often adequate using the complete original multispectral bands for practical applications. To improve the classification accuracy of multispectral images, band reduction techniques are used, which can be categorized into feature extraction and feature selection techniques. The present study examined the use of multispectral satellite bands, spectral indices (including Normalized Difference Built-up Index, Normalized Difference Vegetation Index, and Normalized Difference Water Index) for feature extraction, and the principal component analysis technique for feature selection. These methods were analyzed both independently and in combination for the classification of multiple land use and land cover features. The classification was performed for Landsat 9 and Sentinel-2 satellite images in Delhi, India, using six machine learning techniques: Classification and Regression Tree, Minimum Distance, Naive Bayes, Random Forest, Gradient Tree Boosting, and Support Vector Machine on Google Earth Engine platform. The performance of the classifiers was evaluated quantitatively and qualitatively to analyze the classification results with whole image (comprehensive feature) and small subset (targeted feature). The RF and GTB classifiers were found to outperform all others in the quantitative analysis of all input combinations for both Landsat 9 and Sentinel-2 datasets. RF achieved a classification total accuracy of 96.19% for Landsat and 96.95% for Sentinel-2, whereas GTB achieved 91.62% for Landsat and 92.89% for Sentinel-2 in all band combinations. Furthermore, the RF classifier achieved the highest F1 score of 0.97 in both the Landsat and Sentinel datasets. The qualitative analysis revealed that the PCA bands were particularly useful to classifiers in distinguishing even the slightest differences among the feature class. The findings contribute to the understanding of feature extraction and selection techniques for land use and land cover classification, offering insights into their effectiveness in different scenarios.

Detecting and Predicting Archaeological Sites Using Remote Sensing and Machine Learning—Application to the Saruq Al-Hadid Site, Dubai, UAE

In this paper, the feasibility of satellite remote sensing in detecting and predicting locations of buried objects in the archaeological site of Saruq Al-Hadid, United Arab Emirates (UAE) was investigated. Satellite-borne synthetic aperture radar (SAR) is proposed as the main technology for this initial investigation. In fact, SAR is the only satellite-based technology able to detect buried artefacts from space, and it is expected that fine-resolution images of ALOS/PALSAR-2 (L-band SAR) would be able to detect large features (>1 m) that might be buried in the subsurface (<2 m) under optimum conditions, i.e., dry and bare soil. SAR data were complemented with very high-resolution Worldview-3 multispectral images (0.31 m panchromatic, 1.24 m VNIR) to obtain a visual assessment of the study area and its land cover features. An integrated approach, featuring the application of advanced image processing techniques and geospatial analysis using machine learning, was adopted to characterise the site while automating the process and investigating its applicability. Results from SAR feature extraction and geospatial analyses showed detection of the areas on the site that were already under excavation and predicted new, hitherto unexplored archaeological areas. The validation of these results was performed using previous archaeological works as well as geological and geomorphological field surveys. The modelling and prediction accuracies are expected to improve with the insertion of a neural network and backpropagation algorithms based on the performed cluster groups following more recent field surveys. The validated results can provide guidance for future on-site archaeological work. The pilot process developed in this work can therefore be applied to similar arid environments for the detection of archaeological features and guidance of on-site investigations.

Species diversity, relative abundance, and distribution of avifauna in different habitats within Lewi Mountain, Awi zone, Ethiopia

Almost all habitats on the planet are home to birds, from the lowest deserts to the highest mountains. Birds have proved to be excellent indicators of biodiversity or productivity as they are easily observed and are relatively well known compared to other animals. Although bird species are distributed across the globe, habitat destruction, fragmentation, and loss have adversely affected their survival and distribution. Therefore, this study is an attempt to prepare a baseline data on avifaunal diversity with their relative abundance and species richness in different habitats within Lewi Mountain Awi zone, Ethiopia from December 2018 to October 2020, including both the wet and dry seasons. The sampling sites were stratified based on land cover features, and transect count techniques were employed. The data were summarized per season and habitat type in the excel spreadsheet throughout the study period. In this study, one-way ANOVA was used to determine the effect of habitat type on species diversity and abundance. T-tests are also use to analyze bird populations among seasons. A total of 1591 individuals, 56 bird species belonging to 29 families and 12 orders were identified during the two seasons. The Wetland habitat had the highest species diversity index (H’ = 3) with high evenness index (J = 0.88) during the dry season followed by the open shrubs habitat (H’ = 2.97) with the highest evenness index (J = 0.95). The settlement had the lowest species diversity (H' = 2.17) and the lowest evenness index (J = 0.8) in the same season. During the wet season, disturbed forests recorded the highest Shannon-Weiner diversity index (H’ = 3.2) with the highest evenness (J = 0.92) followed by Wetland habitat (H’ = 2.97) with high evenness index (J = 0.87). During dry and wet seasons, the abundance of birds' species in different habitat types did not differ significantly (F = 1.91, p = 0.193, dƒ = 3) and (F = 1.579, p = 0.199, dƒ = 3), respectively. From all studied habitats, the overall mean abundance of bird species between dry and wet seasons was significantly different (F = 3642, P ≤ 0.001, dƒ = 1). In conclusion, settlement had the lowest species diversity and the lowest evenness index in the research area for the entire season. The habitats are important to the conservation of birds, so good habitat management is required, such as minimizing agricultural expansion and overgrazing, demarcating the forest habitats for wild species only, and creating awareness among local communities.

Wind turbine power and land cover effects on cumulative bat deaths

Wind turbines (WT) cause bird and bat mortalities which depend on the WT and landscape features. The effects of WT features and environmental variables at different spatial scales associated to bat deaths in a mountainous and forested area in Thrace, NE Greece were investigated. Initially, we sought to quantify the most lethal WT characteristic between tower height, rotor diameter and power. The scale of interaction distance between bat deaths and the land cover characteristics surrounding the WTs was quantified. A statistical model was trained and validated against bat deaths and WT, land cover, and topography features. Variance partitioning between bat deaths and the explanatory covariates was conducted. The trained model was used to predict bat deaths attributed to existing and future wind farm development in the region. Results indicated that the optimal interaction distance between WT and surrounding land cover was 5 km, the larger distance than the ones examined. WT power, natural land cover type and distance from water explained 40 %, 15 % and 11 % respectively of the total variance in bat deaths by WTs. The model predicted that operating but not surveyed WTs comprise of 377.8 % and licensed but not operating yet will contribute to 210.2 % additional deaths than the ones recorded. Results indicate that among all WT features and land cover characteristics, wind turbine power is the most significant factor associated to bat deaths. In addition, WTs located within 5 km buffer comprised of natural land cover types have substantial higher deaths. More WT power will result in more deaths. Wind turbines should not be licensed in areas where natural land cover at a radius of 5 km exceeds 50 %. These results are discussed in the climate-land use-biodiversity-energy nexus.

Examining effect of super-resolution on AVIRIS-NG data: A precursor to generation of large-scale urban material and natural cover maps

The two-phase Airborne Visible InfraRed Imaging Spectrometer – Next Generation (AVIRIS-NG) campaign over India has generated datasets of numerous natural and artificial surroundings with high signal-to-noise ratios and higher spatial and spectral consistencies. However, the first phase AVIRIS-NG datasets of urban areas have 8.1 m spatial resolution, which is insufficient for producing level-4 urban material and natural cover maps required to model Earth’s processes at the micro-scale or constantly monitor urban processes. The current work addresses this drawback by demonstrating a part of the proposed proof-of-concept approach on the AVIRIS-NG dataset of Ahmedabad, India, wherein super-resolution (SR) is proposed to enhance the hyperspectral image’s spatial resolution and preserve its rich spectral content at the targeted spatial scale before utilizing it for producing detailed urban land cover maps. A step-wise account of the SR process has been provided herein to aid the reader in reproducing these experiments. Super-resolved products generated using four SR algorithms have been compared and validated using a composite framework based on processing time, qualitative visual investigation of selected image patches and spectral profiles, re-interpretation of Wald’s reduced resolution protocol and full-reference image quality metrics. Results suggest the AVIRIS-NG dataset’s successful spectral and spatial fidelity at a larger spatial scale, albeit varying in each super-resolved output. Sparse regression and natural prior (SRP), and anchored neighbourhood regression (ANR) produce the best and poorest super-resolved outputs among the tested SR algorithms. Although gradient profile prior (GPP) generated super-resolved product is the second best, it is also the most computationally expensive algorithm. An additional yardstick in the form of a spectral similarity analysis of randomly selected unknown spectral signatures on super-resolved output against a reference spectral library has been proposed to ascertain spectral content preservation further before utilizing the super-resolved product for urban information extraction. This exercise’s findings reveal the presence of the target urban land cover feature at the unknown pixels with matching scores of greater than 0.5 in both best and worst super-resolved products, thereby advocating the extension of the proposed proof-of-concept to recently launched spaceborne hyperspectral missions’ datasets.

Surabaya City Surface Temperature Distribution Based On Land Cover And Vegetation Density

According to the Central Bureau of Statistics, the atmospheric temperature of Surabaya City averagely from 2012-2017 was 28,1° per year. In 2017, land use was developed by 48% and undeveloped land by 52%. This study aimed to determine the characteristics of Surabaya City’s surface temperature distribution based on land cover characteristics and vegetation density in 2019. This study used a descriptive quantitative method with Overlay and Remote Sensing analysis techniques. The results of the analysis found that the dominant type of land cover in 2019 was undeveloped land (51%), and the vegetation density class was dominated by a very low density of green and a low density of green with a value of 0.4 − 0.25. In this case, the western part of Surabaya has a low surface temperature ranging from 23,2°C − 24°C, located in Pakal district. While the highest surface temperature (31°C − 41,1°C) is in the eastern part of Surabaya and the largest is in the Rungkut District. In conclusion, in the type of land cover and vegetation density class significantly affect the increase or decrease in surface temperature in Surabaya City.

Spatiotemporal Characterization Of Land Surface Temperature In Relation Landuse/Cover: A Spatial Autocorrelation Approach

Abstract The land use and land cover (LULC) characteristics of Ghaziabad have experienced dynamic changes because of the city’s ongoing industrialization and urbanisation processes. These shifts can be directly attributed to human actions. These shifts can be directly attributed to human actions. Thermal variation in the study area necessitates LULC analysis. Landsat and Sentinel satellite data for 2011 and 2021 were used to map LULC, estimate land surface temperature (LST) and analysis spatial autocorrelation among the variables using ArcGIS software and the Google Earth Engine (GEE) cloud platform. A sharp descent is observed in the cropland while built-up area has increased during the study period. With the increase in the built-up surface in the area, the ambient temperatures have also increased from 18.70 °C in 2011 to 21.81 °C in 2021 leading to urban heat island effect. At all spatial scales, spatial autocorrelation is a characteristic property of most ecological parameters. The spatial clustering of LST in an ecosystem can play a crucial role in determining the dynamics of LULC.The Moran’s, I show that there is a considerable level of spatial autocorrelation in the values of LST and highly clustered pattern for both the years. Monitoring and understanding the surface thermal environment is crucial to discerning the causes of climate change.

Performance of Deep Learning in Land Use Land Cover Classification of Indian Remote Sensing (IRS) LISS – III Multispectral Data

Identification of land use land cover is a very important task. However, methods existing for the above mention purpose are labor incentives, time-consuming, and costly. Remote sensing plays very important role in the mappings. classification of land cover features and offers very noteworthy and sensed information. The present study shows the semantic segmentation of Indian remote sensing (IRS) LISS-III multispectral image and the comparison of three algorithms U-Net, Deeplabv3+and Tiramisu. The deep neural network was used to perform the study. We present total 3 innovative datasets, built on these LISS-III images that has 4 different spectral bands (Band – 2 (Blue), Band-3 (Green), Band-4(Red), and Band-5 (Nearly Infrared), FCC (false color composite) images and the ground truth mask images. Dataset has 13500 labelled images. A fully-convolutional network (FCN) with skip connections is trained to take an input image of size 128 X 128 X 3 and outputs a matrix of shape 128 X 128 X 4 i.e., a one-hot encoded version of the mask. The experiment identifies 4 classes successfully (Water Bodies, Vegetation, Uncultivated Land, and Residential areas). The experiment showed that the U-Net algorithm has a very good capability for the classification of LISS -III images for land use land cover class detection then Tiramisu and Deeplabv3+. U-Net achieved accuracy 84%, Deelabv3+ achieved 29% whereas Tiramisu achieved accuracy 33%.

MFE-ResNet: A new extraction framework for land cover characterization in mining areas

Obtaining accurate information about land cover is a critical aspect of environmental monitoring in mining areas. However, the land cover in these areas is often complex and poses a challenge for analysis compared to other landscapes. This results in the difficulty of acquiring effective features and an unbalanced proportion of available training samples. We introduce a new approach to obtaining effective image features and enhancing the extraction of open-pit (OP) and waste-dump area (WDA) by using a mining feature-enhanced ResNet (MFE-ResNet). Our framework utilizes image objects as the basic units of high spatial resolution images (HSRIs) to better incorporate spatial and geometric information. The MFE-ResNet is an improvement of the ResNet18 architecture, forming a 26-layer network, and reducing the computational complexity by changing the convolutional kernel size. A squeeze-and-excitation (SE) module is also introduced to form an SE-residual structure to improve the network’s ability to perceive the detailed mining area features. To alleviate the sample imbalance problem, a switchable normalization (SN) layer is applied to optimize the internal network structure. In addition, focal loss is introduced in the training process. We build an evaluation system that considers both the number of objects and their area. Compared with other six deep learning methods, our MFE-ResNet achieves the best overall accuracy in both large and small study areas. Specifically, MFE-ResNet obtained F values (F) of 87.73% and 97.28%, and quality (Q) of 81.37% and 95.18% in OP extraction. The F of WDA extraction improved by 0.99% and 2.13%, and the Q improved by 0.98% and 9.56% compared to the second-ranked model. We show that our framework exhibits promising performance in monitoring mining areas.

Relict landslide detection using deep-learning architectures for image segmentation in rainforest areas: a new framework

ABSTRACT Landslides are destructive and recurrent natural disasters on steep slopes and represent a risk to lives and properties. Knowledge of relict landslides’ location is vital to understand their mechanisms, update inventory maps and improve risk assessment. However, relict landslide mapping is complex in tropical regions covered with rainforest vegetation. A new CNN framework is proposed for semi-automatic detection of relict landslides, which uses a dataset generated by a k-means clustering algorithm and has a pre-training step. The weights computed in the pre-training are used to fine-tune the CNN training process. A comparison between the proposed and the standard framework is performed using CBERS-04A WPM images. Three CNNs for semantic segmentation are used (Unet, FPN and Linknet) with two augmented datasets. A total of 42 combinations of CNNs are tested. Values of precision and recall were very similar between the combinations tested. Recall was higher than 75% for every combination, but precision values were usually smaller than 20%. False positives (FP) samples were addressed as the cause for these low precision values. Predictions of the proposed framework were more accurate and correctly detected more landslides. This work demonstrates that there are limitations for detecting relict landslides in areas covered with rainforest, mainly related to similarities between the spectral response of pastures and deforested areas with Gleichenella sp. ferns, commonly used as an indicator of landslide scars. Relict landslide detection has limitations in rainforest environments The proposed framework for CNN semantic segmentation proved to be useful for relict landslide detection Land cover features spectral characteristics, and input data technical specificities are crucial to the accuracy of CNN models No optimal combination of parameters has been identified No CNN proved to be superior