Geographic Information System Techniques Research Articles

Application of Geographic Information Systems (GIS) in the Study of Prostate Cancer Disparities: A Systematic Review.

Introduction: PCa is one of the cancers that exhibits the widest disparity gaps. Geographical place of residence has been shown to be associated with healthcare access/utilization and PCa outcomes. Geographical Information Systems (GIS) are widely being utilized for PCa disparities research, however, inconsistencies in their application exist. This systematic review will summarize GIS application within PCa disparities research, highlight gaps in the literature, and propose alternative approaches. Methods: This paper followed the methods of the Cochrane Collaboration and the criteria set of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Articles published in peer-reviewed journals were searched through the PubMed, Embase, and Web of Science databases until December 2022. The main inclusion criteria were employing a GIS approach and examining a relationship between geographical components and PCa disparities. The main exclusion criteria were studies conducted outside the US and those that were not published in English. Results: A total of 25 articles were included; 23 focused on PCa measures as outcomes: incidence, survival, and mortality, while only 2 examined PCa management. GIS application in PCa disparities research was grouped into three main categories: mapping, processing, and analysis. GIS mapping allowed for the visualization of quantitative, qualitative, and temporal trends of PCa factors. GIS processing was mainly used for geocoding and smoothing of PCa rates. GIS analysis mainly served to evaluate global spatial autocorrelation and distribution of PCa cases, while local cluster identification techniques were mainly employed to identify locations with poorer PCa outcomes, soliciting public health interventions. Discussion: Varied GIS applications and methodologies have been used in researching PCa disparities. Multiple geographical scales were adopted, leading to variations in associations and outcomes. Geocoding quality varied considerably, leading to less robust findings. Limitations in cluster-detection approaches were identified, especially when variations were captured using the Spatial Scan Statistic. GIS approaches utilized in other diseases might be applied within PCa disparities research for more accurate inferences. A novel approach for GIS research in PCa disparities could be focusing more on geospatial disparities in procedure utilization especially when it comes to PCa screening techniques. Conclusions: This systematic review summarized and described the current state and trend of GIS application in PCa disparities research. Although GIS is of crucial importance when it comes to PCa disparities research, future studies should rely on more robust GIS techniques, carefully select the geographical scale studied, and partner with GIS scientists for more accurate inferences. Such interdisciplinary approaches have the potential to bridge the gaps between GIS and cancer prevention and control to further advance cancer equity.

Mapping of the Seasonal Migration Routes of Cattle Pastoralists of the Deccan Plateau Region of India Using Ethnographic Geographic Information System Technique

Mapping of the Seasonal Migration Routes of Cattle Pastoralists of the Deccan Plateau Region of India Using Ethnographic Geographic Information System Technique

Landslide hazard zonation (LHZ) mapping of Doon Valley using multi-criteria analysis method based on remote sensing and GIS techniques

The occurrence of landslides is a costly and cataclysmic natural hazard that mainly occurs in hilly areas due to factors like earthquakes, cloud burst, extreme rainfall, human pressure, etc. leading to loss of biodiversity, property, and life. Effective and comprehensive landslide risk management is crucial to address landslide susceptibility. Utilizing remote sensing and Geographic Information System (GIS) techniques, this work focuses on the landslide hazard zonation (LHZ) mapping. The study is specifically conducted in the Doon Valley. These advanced technologies help in identifying and categorizing the areas prone to landslides. The Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM) data at 30 m resolution and Sentinel-2B data at 10 m resolution were used to perform the remote sensing and GIS operations in ArcGIS Software. Thematic layers such as Land Use/Land Cover (LULC), Slope, Geology, Soil Type, Elevation, Drainage Density, Vegetation, and Aspect were produced utilizing remote sensing and GIS data. The weighted overlay, a multi-criteria analysis method, was applied to assign attribute values to each thematic layer based on their importance, which was then combined to calculate the landslide hazard zone. The findings of this study demonstrate that landslides are more likely to occur near and above the Main Boundary Thrust/Fault (MBT). The high to very high hazard zone covers 16.64% of the total area, making landslides occurring more frequently. Additionally, the study found that the Doon Valley rivers’ upper segments are more susceptible to landslides than their lower segments. By integrating Remote Sensing and GIS techniques, it is possible to obtain extensive knowledge of regions prone to landslides. This information will be helpful for decision-makers and planners to reduce the impact of landslides in the near future.

Effective Monitoring of Noyyal River surface water quality using remote sensing and Machine learning and GIS techniques

This study utilizes Geographic Information System (GIS) and remote sensing techniques to predict water quality metrics in the Noyyal River. Satellite data is employed to construct statistical models, with preprocessing involving adjustments from Landsat 8 images. The hybrid LASSO model demonstrates superior performance in predicting water quality parameters, supported by key performance metrics such as RMSE, R-squared, and ANOVA results. The study focuses on assessing the suitability of the hybrid LASSO model for predicting the Water Quality Index (WQI) in the Noyyal region, highlighting its ability to handle high-dimensional data and provide interpretable results. Prediction models employing the LASSO approach yield promising results, with R-squared values exceeding 0.87 for temperature and pH. Incorporating spectral indices significantly enhances model performance, with an average R-squared of 0.8. These models offer cost-effective options for monitoring water quality, revealing poor conditions in the Noyyal River and projecting deterioration for 2023. WQI ratings indicate poor conditions, particularly during July and August 2022 and April 2023, providing valuable insights for local pollution regulation enforcement.

LULC changes in the region of the proposed Pwalugu hydropower project using GIS and remote sensing technique

<p>Proper understanding of LULC changes is considered an indispensable element for modeling. It is also central for planning and management activities as well as understanding the earth as a system. This study examined LULC changes in the region of the proposed Pwalugu hydropower project using remote sensing (RS) and geographic information systems (GIS) techniques. Data from the United States Geological Survey's Landsat satellite, specifically the Landsat Thematic Mapper (TM), the Enhanced Thematic Mapper (ETM), and the Operational Land Imager (OLI), were used. The Landsat 5 thematic mapper (TM) sensor data was processed for the year 1990; the Landsat 7 SLC data was processed for the year 2000; and the 2020 data was collected from Operation Land Image (OLI). Landsat images were extracted based on the years 1990, 2000, and 2020, which were used to develop three land cover maps. The region of the proposed Pwalugu hydropower project was divided into the following five primary LULC classes: settlements and barren lands; croplands; water bodies; grassland; and other areas. Within the three periods (1990–2000, 2000–2020, and 1990–2020), grassland has increased from 9%, 20%, and 40%, respectively. On the other hand, the change in the remaining four (4) classes varied. The findings suggest that population growth, changes in climate, and deforestation during this thirty-year period have been responsible for the variations in the LULC classes. The variations in the LULC changes could have a significant influence on the hydrological processes in the form of evapotranspiration, interception, and infiltration. This study will therefore assist in establishing patterns and will enable Ghana's resource managers to forecast realistic change scenarios that would be helpful for the management of the proposed Pwalugu hydropower project.</p>

Investigation of the Basin Characteristics through Morphometric Analysis of Hadejia River Sub-Basin: Implications for Groundwater Recharge

Understanding the geohydrological properties of a drainage basin in relation to the topographical feature and its flow patterns depends heavily on morphometric analysis. Estimating a watershed's frequency of infiltration and runoff as well as its other hydrological characteristics is also helpful. The study was conducted using Geographical Information System (GIS) techniques with the aim of establishing relationship between surface morphometry, underlying geology and groundwater recharge. For detailed measurement and analysis, Digital Elevation Model (DEM) and high resolution imageries were employed for basin delineation, slope characterization, channel network extraction and stream ordering in order to derive the linear, areal, and relief aspects of morphometric parameters. The findings showed that a total number of 116 streams joined the 4th order stream in which 83 streams were 1st order, 25 streams were 2nd order, 7 streams were 3rd order and the major trunk was 4th order stream, occupied an area of 1486.86km2. The stream network's drainage system exhibits dendritic design. The results further indicate that the values for stream frequency, infiltration number, drainage density, drainage texture, length of overland flow, elongation ratio and basin relief are 0.08, 0.032, 0.41km/km2, 0.023, 1.22km, 0.54 and 28.59m respectively. The observed values of both linear, areal and relief parameters were generally low. Low values for the areal and relief criteria indicates that the sub-basin is at its youthful stage of development and possesses very good permeable subsurface formation and prospect with the possibility of high potential groundwater resources. The result help us understand the connections between hydrological variables and geomorphological parameters as guidance and/or decision-making instruments for the authorities to develop decisions for the environmentally friendly growth of the basin, water supply planning, water budgeting, and disaster mitigation within the Hadejia river sub-basin.

Securing water for arid regions: Rainwater harvesting and sustainable groundwater management using remote sensing and GIS techniques

Arid regions experience climatic stress under climate change: increased drought frequency coupled with intensified storm events. This disruption and lack of precipitation patterns leads to water scarcity and hinders the achievement of sustainable development goals. Egypt drainage basin exhibiting the greatest suitability for the implementation of rainwater harvesting (RWH) strategies. To facilitate the development of sustainable water resource management practices in the region, this study uses a multi-criteria methodology to delineate optimal zones for RWH within the Wadi Safaga. Integration of radar and optical remote sensing data obtained from Sentinel-1&2, Landsat-8, ALOS/PALSAR, and Sentinel-1 Interferometric SAR with climatic Tropical Rainfall Measuring Mission (TRMM), hydrological, and geological datasets emphasizes the hydrologic characteristics of the catchments. Additionally, the analysis of rainfall intensity patterns within the basin was undertaken. Thirteen factors are used in the predicted model including elevation, slope, curvature, depression, lithology, radar, InSAR CCD, drainage density (Dd), distance to river (DR), vegetation, topographic wetness index (TWI), rainfall, and lineament density. A knowledge-driven Geographic Information System (GIS) methodology, including weighted factors based on the Analytical Hierarchy Process (AHP), was implemented to delineate plausible areas for RWH and groundwater potential zones (GWPZs). The resultant map categorized the basin into five GWPZ classes: very low (14%), low (28%), moderate (27%), high (21%), and very high (10%). Furthermore, the study identified optimal locations for constructing reservoirs to store harvested rainwater and provide protection for downstream mining, industrial, and tourism activities. In conclusion, the obtained information is crucial for planners and decision-makers to implement sustainable water resource management strategies within the Wadi Safaga basin.

Research on the Spatiotemporal Distribution Characteristics and Accessibility of Traditional Villages Based on Geographic Information Systems—A Case Study of Shandong Province, China

The traditional settlements are of paramount significance as indispensable elements of China’s cultural heritage, simultaneously functioning as prime assets for the enhancement of rural economic and social dynamics. Nestled within the comprehensive framework of China’s rural revitalization endeavor and Shandong Province’s proactive initiatives toward the amalgamation of cultural and tourism sectors, a meticulous exploration of the spatiotemporal evolution and connectivity of traditional villages in Shandong Province is indispensable for their preservation and forward-thinking evolution. For this study, 557 traditional villages across Shandong Province are identified as pivotal points, with the application of geographic information system (GIS) techniques to scrutinize their spatiotemporal transformation patterns and spatial characteristics. Additionally, a suite of analytical instruments, encompassing metrics for accessibility assessment, ordinary least squares (OLS) linear regression, and geographically weighted regression (GWR) models, are deployed to evaluate the accessibility levels and influential factors shaping traditional villages within the region. The analytical outcomes reveal the following: (1) Chronologically, approximately 80% of the traditional villages in the province of Shandong were established during the Ming and Qing epochs, and they demonstrate a migratory pattern that is spatially and temporally oriented from “southwest to northeast”; geographically, these traditional villages are characterized by pronounced clustering, predominantly situated at the confluence of Jinan and Zibo Cities, the Shantou District of Zaozhuang City, Zhaoyuan City of Yantai City, and Rongcheng City of Weihai City, forming a coherent “four-core” spatial distribution configuration. (2) Considering the criteria for village location, traditional villages in Shandong are predominantly found in areas with a predominantly flat landscape and a certain proximity to water bodies. (3) On the whole, the accessibility of traditional villages in Shandong is relatively high, with the average accessibility assessed at 199.92 min, a range spanning from 175 min, and approximately 57.99% of the villages falling within the 100 to 200 min accessibility bracket, indicating a systematic decline in accessibility from the central areas to the periphery. (4) The pivotal factors influencing the accessibility of traditional villages in Shandong are primarily altitude, slope, and road network density, with altitude and slope showing a negative correlation with accessibility, whereas road network density exhibits a positive correlation, and the proximity to water bodies has a relatively minor impact on accessibility.

Geospatial assessment of built environment on land surface temperature in district Sheikhupura, Punjab Pakistan

The built environment is associated with higher air and surface temperatures in urban areas compared to rural counterparts. This study focuses on the Sheikhupura district in Punjab, Pakistan, where rapid urbanization and deforestation have significantly impacted land surface temperature (LST) from 2000 to 2020. Utilizing Geographic Information Systems (GIS) and Remote Sensing (RS) techniques, four Landsat images from the United States Geological Survey (USGS) were analyzed to assess spatiotemporal variations in LULC and LST. The single infrared channel approach was employed to calculate LST, and LULC maps were created using supervised classification for the years 2000, 2010, and 2020. The results indicate a substantial increase in built-up areas from 66.9708 square kilometers in 2000 to 259.8147 square kilometers in 2020, accompanied by a significant reduction in vegetation and agricultural land. Correspondingly, the maximum LST rose from 28.9354 °C in 2000 to 31.5173 °C in 2020, highlighting the urban heat island effect. Zonal statistics revealed a decrease in mean high temperatures from 24.45 to 20.3 °C over the same period, suggesting variability in temperature distribution due to changes in land cover types. These findings underscore the need for sustainable urban planning to mitigate the adverse effects of urbanization on local climates. Future work should focus on developing strategies to increase green spaces and reforestation efforts to counteract rising temperatures. Additionally, further research is recommended to explore the long-term impacts of these changes on local biodiversity and ecosystem services, providing a holistic approach to urban sustainability.

Exploring gender norms in Neolithic Northern China: A GIS analysis of the Jiangzhai site

This study employs Geographic Information Systems (GIS) techniques to analyze the Jiangzhai site, a significant Neolithic settlement in northern China. Our aim is to challenge existing biases in gender interpretations of this and similar sites. By examining the distribution of various types of burial goods across different areas of the cemetery, we reveal significant spatial heterogeneity, indicating that mortuary practices at Jiangzhai should not be considered a unified entity. Our findings highlight no universal correlation between gender and grave good distribution: various types of goods are present in both male and female graves. However, in certain areas of the cemetery, specific types of production tools exhibit clear gender preferences. This suggests that gender roles within the Jiangzhai community were flexible and gender was not the central aspect of funerary practices. At Jiangzhai, gender and gender norms were intertwined with other aspects of funerary practices and social identity, influenced by economic structural differences between households. We call for more case studies based on new methods and encourage scholars to continue critically examining past gender narratives.

Satellite-based rainwater harvesting sites assessment for Dera Ghazi Khan, Punjab, Pakistan.

Water scarcity in arid regions poses significant livelihood challenges and necessitates proactive measures such as rainwater harvesting (RWH) systems. This study focuses on identifying RWH sites in Dera Ghazi Khan (DG Khan) district, which recently experienced severe water shortages. Given the difficulty of large-scale ground surveys, satellite remote sensing data and Geographic Information System (GIS) techniques were utilized. The Analytic Hierarchy Process (AHP) approach was employed for site selection, considering various criteria, including land use/land cover, precipitation, geological features, slope, and drainage. Landsat 8 OLI imagery, GPM satellite precipitation data, soil maps, and SRTM DEM were key inputs. Integrating these data layers in GIS facilitated the production of an RWH potential map for the region. The study identified 9 RWH check dams, 12 farm ponds, and 17 percolation tanks as suitable for mitigating water scarcity, particularly for irrigation and livestock consumption during dry periods. The research region was classified into four RWH zones based on suitability, with 9% deemed Very Good, 33% Good, 53% Poor, and 5% Very Poor for RWH projects. The generated suitability map is a valuable tool for hydrologists, decision-makers, and stakeholders in identifying RWH potential in arid regions, thereby ensuring water reliability, efficiency, and socio-economic considerations.

Analysis of Urban Expansion and Land Use/ Land Cover Changes in Abeokuta, Nigeria using Remote Sensing and Geographic Information System Techniques

Analysis of Urban Expansion and Land Use/ Land Cover Changes in Abeokuta, Nigeria using Remote Sensing and Geographic Information System Techniques

Urban Flood Modelling: A Geospatial Evaluation of Drainage Systems for Resilient City Planning in Lusaka

This study presents a flood modelling approach aimed at enhancing planning strategies to mitigate flooding impacts in LusakaCity. By integrating factors such as slope, hydrostatic potential surface, and the built environment, a predictive flood modelwas developed. The methodology involved using Geographic Information System (GIS) techniques and digital elevationmodels (DEMs) to assess geological features and manmade structures. Precipitation patterns and water demand analysesaided in computing a hydrostatic potential surface through watershed delineation. The generated flood model producedcomprehensive flood maps illustrating water drainage in Lusaka, identifying vulnerable areas using Multi-Criteria DecisionAnalysis (MCDA) techniques. Results highlight the complex interaction between geographical features and humaninfrastructure in flood dynamics. This study contributes to informing zoning policies and disaster response planning, aimingto reduce the impact of future flooding events.

Pemetaan Sebaran Titik Hotspot Menggunakan Arcgis di Kota Banjarbaru Tahun 2019-2023

Hotspot point mapping is mapping in which to find out which areas have the largest distribution of hotspot points and make it possible for these areas to be prone to fire, this research uses a literature study method. In processing the map the author used data from the Sipongi website (Early Detection Information System for Controlling Forest and Land Fires) to determine Hotspot points in Banjarbaru City and the data obtained was processed using Arcgis 10.8 software. Based on map results that have been processed with data for 2019-2023, Lianganggang District is the district with the most hotspots at 46 points. Mapping the distribution of hotspots is an important step in understanding forest and land fire patterns and identifying areas that are vulnerable to these events. There are several factors that allow forest fires to occur apart from human activities, other activities such as natural factors from the dry season can also cause forest and land fires. This research aims to map the distribution of hotspot points in Banjarbaru City during the period 2019 to 2023. Hotspot point data was obtained from remote sensing satellites which were then analyzed using GIS (Geographic Information System) techniques to produce a hotspot distribution map. It is hoped that future research can use more sophisticated technology to map the distribution of hotspot points over a certain period of time, and it is also hoped that the results of this research can be useful for local government agencies with an interest in handling forest and land fires.

Change analyses and prediction of land use and land cover changes in Bernam River Basin, Malaysia

Land use and land cover (LULC) change is a dynamic process which is significantly influenced by anthropogenic activities. Analysing historical LULC trends and predicting future dynamics is critical to provide insights for decision-makers and planners aiming for sustainable land management and development. This study focuses on the Bernam River Basin (BRB). It employs an integrated approach that combines the Multi-Layer Perceptron (MLP), the Cellular Automata (CA)-Markov algorithm, remote sensing, and Geographical Information System (GIS) techniques. Using multi-temporal 10m resolution Sentinel-2 Landsat imagery from 2010, 2020, and 2022, the study classified LULC into seven categories: water, forest, wetlands, agriculture, urban, barren, and rangeland areas. Change analysis from 2010 to 2020 was conducted, with 2022 validating predicted LULC transitions. The MLP model, trained on land change driver variables, facilitated the generation of transition potentials for simulating future LULC changes. A spatially explicit CA-Markov model implemented LULC change projections for 2022, 2025, 2050, and 2075, based on the transition potentials. The analysis reveals an annual increase of 0.24% in water, 0.61% in forest, and 2.11% in urban areas, while wetlands (2.69%), agriculture (2.47%), barren (3.51%), and rangeland (4.58%) experienced declines. The CA-Markov approach accurately predicted LULC transitions for 2022, validated through an error matrix with an overall accuracy of 91.56% based on 450 sampling points. Predictions for 2025–2075 indicate rising trends in water (1.76%), wetlands (29.18%), agriculture (60.08%), urban (96.53%), barren (0.59%), and rangeland areas (3.57%). Forests are expected to decrease by 12% (261.52 km2). The study identified agriculture and urban expansion as the primary drivers of LULC changes in the river basin. These findings provide critical information for regional authorities to formulate evidence-based policies and management strategies, ensuring the environmental sustainability of BRB. Furthermore, these predicted LULC patterns can be integrated into complementary models, such as the Soil and Water Assessment Tool, to assess the impacts of LULC changes on water resources.

Cultural Heritage Sites Risk Assessment and Management Using a Hybridized Technique Based on GIS and SWOT-AHP in the Ancient City of Ibb, Yemen

ABSTRACT The conservation of Cultural Heritage (CH) sites is vital for conserving a nation’s historical, architectural, and socio-cultural identity, especially in areas like Yemen, where such sites are threatened by natural hazards, urban development, and various anthropogenic activities. This study addresses these challenges by introducing a comprehensive risk assessment and management framework, with a focused case study on the ancient city of Ibb – a region with significant CH. The study employs a novel hybridized approach that combines Geographic Information Systems (GIS) with the Strength, Weakness, Opportunity, and Threat (SWOT) – Analytic Hierarchy Process (AHP) to identify thirteen critical factors influencing site suitability. These factors are classified into natural and anthropogenic categories and are systematically analyzed using GIS techniques. Additionally, the study identified and evaluated 16 SWOT factors using structured questionnaire surveys, which inform an integrated SWOT and AHP methodology. The findings revealed that the study area is mainly classified from very high to very low-risk areas, representing very high (37.2%), high (24.3%), moderate (17.7%), low (12.3%), and very low (8.5%), of the total study area, indicating that most of them are in highly hazardous environments, necessitating urgent attention and the implementation of protective measures. This study offers valuable insights and optimization strategies for safeguarding the CH sites of the ancient City of Ibb. It is particularly useful for policymakers, conservationists, and local stakeholders, providing a scalable approach that can be adapted to manage risks at other CH sites facing similar threats, thus making a significant contribution to the field of heritage risk management.

Hoping the best, expecting the worst: Forecasting forest fire risk in Algeria using fuzzy logic and GIS

Forest fires pose severe threats to ecosystems and communities globally, especially in vulnerable semi-arid regions like North Africa. Understanding the key factors influencing forest fire dynamics is essential for effective management and mitigation. This study aims to comprehensively analyze forest fire risk patterns in Djebel El Ouahch's massif (Algeria), focusing on integrating bioclimatic, fuel, geomorphological, and human factors through advanced fuzzy logic and geographic information system (GIS) techniques. Climatic station data, satellite imagery, and GIS were employed to map bioclimatic parameters, land cover, and geomorphological features. Fuzzy logic systems were applied to integrate these factors, assigning appropriate weights based on their significance. The resulting forest fire prediction model was defuzzified to generate predictive maps indicating varying vulnerability levels within the study area. Predictive maps delineated areas of low to high forest fire risk. Low-risk zones were characterized by sparse vegetation, while high-risk regions featured densely vegetated slopes near human settlements. The study identified critical factors influencing vulnerability, emphasizing the impact of climate, terrain, and human activities. Urgent attention was directed toward high-risk areas, necessitating tailored fire prevention measures and strategic urban planning to minimize human-induced risks. The results underscored the complex interaction of natural and anthropogenic factors in shaping forest fire susceptibility. Understanding these dynamics facilitates evidence-based policymaking, enhancing forest fire preparedness, biodiversity preservation, and community safety. Additionally, the study emphasized the need for continuous research incorporating real-time climate data and socio-economic factors to refine predictive models. This research provided valuable insights into forest fire risk patterns in Djebel El Ouahch, serving as a foundation for targeted fire management strategies. By bridging the gap between theoretical knowledge and practical application, this study contributes significantly to sustainable forest management and disaster mitigation efforts globally, emphasizing the importance of proactive measures in safeguarding vulnerable ecosystems and communities.

Effects of Land Use Change on Land Erosion and Land Critical Level Using GIS in the Mayang Watershed

The increasing population in an area often triggers heightened development, leading to diminished land availability and subsequent land conversion. This transformation, predominantly observed in agricultural and plantation lands, is driven by the need for residential areas. However, continuous land use changes contribute to erosion, a natural process wherein soil is transported, leading to sedimentation and eventual flooding. This study aims to identify critical areas prone to erosion and land degradation. To address this, we used the Universal Soil Loss Equation (USLE) method for erosion prediction, leveraging its simplicity and accuracy. This study focuses on the Mayang watershed in East Java, utilizing a combination of USLE, spectral index modeling, and Geographic Information System (GIS) techniques to estimate soil erosion and land criticality. By integrating methodologies and analyzing data spanning from 2011 to 2021, the study reveals shifts in erosion danger levels and land use patterns. While regions with low erosion remained stable, areas with medium to high erosion declined, yet those with very high erosion exhibited a worrisome increase. Changes in land use, including forest loss and urban expansion, underscore the ecological shifts exacerbating erosion hazards. The study emphasizing the necessity for targeted conservation strategies and comprehensive land management plans to mitigate erosion risks and preserve environmental sustainability.

Performance of logistic regression and support vector machine conjunction with the GIS and RS in the landslide susceptibility assessment: Case study in Nakhon Si Thammarat, southern Thailand

The occurrence of landslides has risen in the past few decades, particularly in mountainous regions worldwide, including Nakhon Si Thammarat, southern Thailand. Despite various methods being employed for the initial management of landslide disasters, none have proven universally effective. The goal of this research is to create and assess landslide susceptibility maps (LSMs) within this area by employing support vector machine (SVM) and logistic regression, together with Geographic Information System (GIS) and Remote Sensing (RS) techniques. Eleven factors contributing to landslides were identified as topographic, environmental, and geological influences. The 365 landslides in the past were aimlessly selected into training (70%) and testing (30%) datasets. The four LSMs indicated that approximately 13%–20% of this study area exhibit a high susceptibility to landslides corresponding to the regions of high elevation with relatively steep slope angles. To evaluate and compare LSM models, the AUC value for training dataset were 0.977, 0.975, 0.958, and 0.967 and testing dataset were 0.973, 0.969, 0.956, and 0.964 for SVM with the radial basis function (rbf) kernel, SVM with polynomial deg 2, SVM with linear kernel and logistic regression models, respectively. Among these models, SVMs with rbf demonstrated the highest prediction rate. However, it requires a significant amount of time to choose the best parameters for achieving the highest accuracy prediction. In summary, these maps are applicable at the regional level to enhance the management of landslide hazards.

Quantitative study of storm surge risk assessment in an undeveloped coastal area of China based on deep learning and geographic information system techniques: a case study of Double Moon Bay

Quantitative study of storm surge risk assessment in an undeveloped coastal area of China based on deep learning and geographic information system techniques: a case study of Double Moon Bay