Applied GeomaticsPub Date : 2025-03-04DOI: 10.1007/s12518-025-00607-9
James V. Marcaccio, Jesse Gardner Costa, Scott Parker, Jonathan D. Midwood
{"title":"High resolution satellite data and image segmentation produce accurate benthic substrate maps in clear waters of the great lakes","authors":"James V. Marcaccio, Jesse Gardner Costa, Scott Parker, Jonathan D. Midwood","doi":"10.1007/s12518-025-00607-9","DOIUrl":"10.1007/s12518-025-00607-9","url":null,"abstract":"<div><p>Benthic substrates are an important component of fish habitat and preferred substrates vary with species and life history traits. Understanding the location and areal extent of these substrates helps inform protection and management of fish and other aquatic species. Traditional methods of substrate mapping can require substantial effort and necessitate specialized equipment and personnel to work at and travel to sites. Satellite mapping of bottom types has been conducted in the past, though most of this work has been done in ocean systems and relatively little in freshwater. Using several permutations of input data and processing methods, we accurately map benthic substrates in the clear freshwater ecosystem of Fathom Five National Marine Park, Lake Huron, Canada. Using a novel approach, we were able to map substrate with relatively limited inputs to the model, making the method easily transferable among systems. An object-based approach to classification proved beneficial for accuracy, as was using higher resolution (< 2 m) satellite data to achieve our target accuracies. We also grouped accuracies by depth bins within the site to show that accuracy does not decrease linearly out to the maximum observable depth. Using a more limited depth range for classification results in higher overall and depth-specific accuracies, which may be beneficial when only a shallower portion of the site is necessary to map. With this model and information, accurate substrate maps for an area of interest could be developed to assist with the identification and management of aquatic habitat.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"343 - 356"},"PeriodicalIF":2.3,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s12518-025-00607-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145162220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-28DOI: 10.1007/s12518-025-00618-6
Peer Jeelani, Farzana Ahad, Shamim Ahmad Shah, Huma Rashid
{"title":"Site suitability evaluation for nature-based tourism using gis and ahp: a case study of Kashmir Valley, India","authors":"Peer Jeelani, Farzana Ahad, Shamim Ahmad Shah, Huma Rashid","doi":"10.1007/s12518-025-00618-6","DOIUrl":"10.1007/s12518-025-00618-6","url":null,"abstract":"<div><p>Traditionally, the expansion of nature-based tourism has involved a meticulous process, often incorporating spatial analyses. In this context, a multi-criteria decision-making (MCDM) model has been introduced and implemented to assess the suitability of natural-based tourism sites in the Kashmir Valley, India. The data used in this study comprised both primary and secondary sources, with primary data collection involving field surveys, interviews, and questionnaires administered to professionals in relevant fields of study. Leveraging Geographic Information System (GIS) technology and the Analytical Hierarchical Process (AHP) thirteen criteria were identified, encompassing assessments of natural beauty, infrastructure, and various physical and socio-economic parameters within the study area. The analysis reveals that while the lower reaches or valley floor exhibit minimal tourism potential, the upper reaches demonstrate considerable potential, with a significant proportion of this high-potential area being the most extensive. The information, data, and methodology presented in this study serve as a valuable resource for decision-makers and stakeholders in the research area, offering insights applicable to sustainable tourism development in similar environments and regions.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"239 - 253"},"PeriodicalIF":2.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145169897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Systematic review and bibliometric analysis of innovative approaches to soil fertility assessment and mapping: trends and techniques","authors":"Tarchi Fatimazahra, Samira Krimissa, Maryem Ismaili, Hasna Eloudi, Abdenbi Elaloui, Oussama Nait-Taleb, Mohamed El Haou, Insaf Ouchkir, Mustapha Namous, Nasem Badreldin","doi":"10.1007/s12518-025-00611-z","DOIUrl":"10.1007/s12518-025-00611-z","url":null,"abstract":"<div><p>The twenty-first century marks a significant shift in soil fertility evaluation, driven by advancements in pedometrics and Digital Soil Mapping (DSM). Pedometrics introduces quantitative methods to assess soil variability using statistical and geostatistical techniques, enhancing understanding of soil properties. DSM builds on this by creating high-resolution predictive maps, offering valuable data for researchers and practitioners. An in-depth bibliometric analysis on the Scopus platform (2000–2023) revealed 133 articles on pedometrics and an impressive 1,172 on DSM, underscoring growing interest in these technologies.The integration of Geographic Information Systems (GIS) and Remote Sensing (RS) has further advanced these fields, enabling extensive geospatial data collection and real-time monitoring. Machine Learning (ML) has also been transformative, facilitating complex pattern recognition and predictive analysis to improve soil fertility mapping and management. A review of 364 studies from 2000 to 2023 highlights the development and impact of these technologies, detailing their advantages and limitations. The surge in related publications and citations since 2000 reflects a rising interest in sustainable agriculture and environmental management. Significant milestones occurred in 2019 and 2022 with the introduction of new soil management technologies, while RS and GIS technologies surged in popularity in 2016 and 2020, driven by satellite advancements like Sentinel and Landsat. The capabilities of ML techniques were notably effective in 2019 and 2022. Countries like India, China, and Iran have been key adopters, transforming soil fertility mapping into a non-invasive, large-scale process that enhances agricultural decision-making.This transition emphasizes the value of specialized publications that advocate for GIS, RS, pedometrics, and DSM, which are crucial for addressing environmental challenges. In conclusion, integrating traditional and advanced methodologies provides a holistic, adaptable approach to sustainable land management, supporting data-driven decisions to enhance agricultural and environmental sustainability.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"177 - 215"},"PeriodicalIF":2.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145170738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-25DOI: 10.1007/s12518-025-00615-9
Ankit Choudhary, Vishal Mishra, Rahul Dev Garg, S. S. Jain
{"title":"Spatio–temporal analysis of traffic crash hotspots- an application of GIS-based technique in road safety","authors":"Ankit Choudhary, Vishal Mishra, Rahul Dev Garg, S. S. Jain","doi":"10.1007/s12518-025-00615-9","DOIUrl":"10.1007/s12518-025-00615-9","url":null,"abstract":"<div><p>Haridwar is an expanding urban centre in the Indian state of Uttarakhand. For an emerging urban centre like Haridwar, road traffic accident (RTA) studies are crucial to address increasing traffic challenges, identify accident-prone areas, and implement targeted safety measures. This research investigates the spatio–temporal patterns of RTA blackspots in the Haridwar district of India, considering both the presence and absence of a Crash Severity Index (CSI). The study uses Kernel Density Estimation (KDE) to identify blackspots, and the comap approach to examine spatio–temporal patterns across different times of day and seasons. The methodology involves collecting and preprocessing crash data from 2016 to 2019, applying the comap technique, incorporating the severity index (SI), using KDE, and finally, investigating the blackspots. The study found that the inclusion of CSI significantly impacts the ranking of blackspots, with high severity crashes often occurring during the summer season and between 12.00 h—17:59 h, and 0:00 h—5:59 h. The research aims to provide a more nuanced approach to identifying hazardous locations by weighting crashes based on their severity and to explore how these locations change over time and across different seasons. The findings of this research indicate that blackspots are not consistent across time or seasons, with specific locations showing higher concentrations of severe crashes during certain periods. The study identified key blackspots such as the Deoband Y-intersection and Jhabrera T-intersection along NH-334, and a curve section along NH-34. These locations are characterized by heterogeneous traffic, illegal crossings, narrow roads, and inadequate infrastructure. The research suggests implementing measures such as pedestrian walkways, road widening, improved signage, and better lighting to mitigate these issues. This study is the first spatio–temporal investigation of RTA blackspots in India and can help highway authorities in Haridwar and other cities to implement targeted safety measures.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 1","pages":"129 - 146"},"PeriodicalIF":2.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-25DOI: 10.1007/s12518-025-00613-x
Koyel Sur, V. K. Verma, Manpreet Singh, Ayad M. Fadhil Al-Quraishi, Parshottam Arora, Brijendra Pateriya
{"title":"Estimation of LAI across phenological stages of wheat using google earth engine","authors":"Koyel Sur, V. K. Verma, Manpreet Singh, Ayad M. Fadhil Al-Quraishi, Parshottam Arora, Brijendra Pateriya","doi":"10.1007/s12518-025-00613-x","DOIUrl":"10.1007/s12518-025-00613-x","url":null,"abstract":"<div><p>The Leaf Area Index (LAI) is a measure of photosynthesis and transpiration, and it has become the common currency for agro-climatic researchers. The non-destructive technique of LAI estimation using remote sensing has immense potential. The challenge lies in estimating LAI at the field scale for implementing research results for crop management using Google Earth Engine (GEE) integrated with Python. Sentinel-2A datasets empowered by high spatial, spectral, and temporal resolution over an arid region of southwest Punjab, India were used to estimate LAI at field and district level. Wheat LAI was estimated for two consecutive years, 2016–2017 and 2017–2018. The comprehensive data analysis approach comprised of processing and estimation of LAI, designed for four significant phenological stages followed by validation with in situ field observed LAI collected from the experimental plots as well as with the Moderate Resolution Imaging Spectroradiometer (MODIS)’s LAI data products. The results showed a strong positive co-relationship between observed field LAI and Sentinel-2A estimated LAI as 0.64 and 0.47, with MODIS dataset as 0.24 and 0.19 for both years. Therefore, it can be concluded that field-level LAI can be estimated from Sentinal-2A satellite images with moderate accuracy by agricultural specialists and practitioners. </p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 1","pages":"117 - 128"},"PeriodicalIF":2.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-24DOI: 10.1007/s12518-025-00614-w
Aslıhan Sezgin, Fitnat Nur Aybek, Murat Luzum
{"title":"Restricted and extended star operations for soft sets: new restricted and extended soft set operations","authors":"Aslıhan Sezgin, Fitnat Nur Aybek, Murat Luzum","doi":"10.1007/s12518-025-00614-w","DOIUrl":"10.1007/s12518-025-00614-w","url":null,"abstract":"<div><p>Soft set theory has been well-known as a technique for tackling uncertainty-related problems and modeling uncertainty since it was proposed by Molodtsov in 1999. It has been applied to a number of theoretical and real-world problems. The core concept of the theory-soft set operations-has piqued the interest of academics ever since it was introduced. A number of restricted and extended operations have been defined, and their characteristics have been examined up to now. Our proposed restricted star and extended star operations are novel restricted and extended soft set operations, and we thoroughly analyze their fundamental algebraic properties. We also look into the distributions of this operation over other types of soft set operations. By considering the algebraic properties of the extended star operation and its distribution rules, we show that when combined with other types of soft set operations, it forms several important algebraic structures, like semirings in the collection of soft sets over the universe. Since the operations of soft sets provide the basis for many applications, such as cryptology, and decision-making processes, this theoretical study is highly significant from both a theoretical and practical standpoint.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"323 - 341"},"PeriodicalIF":2.3,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145169314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-21DOI: 10.1007/s12518-025-00612-y
Katarina Glavačević, Ivan Marić, Fran Domazetović, Ante Šiljeg, Gloria Pedić, Luka Jurjević, Lovre Panđa
{"title":"Applicability of network real time kinematic (NRTK) approach in soil erosion measurement at different temporal and spatial scales","authors":"Katarina Glavačević, Ivan Marić, Fran Domazetović, Ante Šiljeg, Gloria Pedić, Luka Jurjević, Lovre Panđa","doi":"10.1007/s12518-025-00612-y","DOIUrl":"10.1007/s12518-025-00612-y","url":null,"abstract":"<div><p>Geomorphic change detection (GCD), geotechnical engineering, and hazard mapping are analyses that require the lowest possible absolute total error in digital elevation models (DEMs). One of the most common GCD analyses is the quantification of soil erosion. NRTK (Network Real-Time Kinematic) is one of the three primary modes within the broader method of direct georeferencing (DG). NRTK uses a network of multiple GNSS reference stations to provide real-time correction data to a UAV, enabling centimeter-level positioning accuracy. This approach eliminates the need for ground control points (GCPs), reducing both costs and survey time. However, its application in multi-temporal soil erosion analysis remains insufficiently researched. In this paper the NRTK approach in GCD analysis is evaluated using Matrice 210 RTK V2 at two case studies. In addition, the absolute accuracy of the NRTK was tested on three other sites. Although achieved results can be regarded as promising, especially at lower altitudes, this research highlights drawbacks when employing the NRTK in analysing soil erosion measurement. Namely, the use of the DG-based models in GCD analysis generated unreliable results when compared with the reference model derived using the SfM photogrammetry with GCP. In both study sites, the NRTK approach significantly overestimated the amount of accumulated sediment, affected the total net sediment difference, and eliminated a substantial amount of change. Although the NRTK approach shows limitations in reliably quantifying volumetric changes in soil erosion measurements, results indicate that NRTK can be applied for analyzing linear gully headcut retreat rates. For applications where achieving the lowest absolute total error is not a priority, NRTK can be a relatively reliable solution. However, researchers should exercise caution when using it to analyze soil erosion over different time scales, particularly if the rate of morphological change is low.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"295 - 321"},"PeriodicalIF":2.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145167799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-19DOI: 10.1007/s12518-025-00617-7
Najib Ansari, Rukhsana
{"title":"Modelling of urban land-use and land-cover and urban sprawl in the Siliguri Urban agglomeration: a geospatial analysis","authors":"Najib Ansari, Rukhsana","doi":"10.1007/s12518-025-00617-7","DOIUrl":"10.1007/s12518-025-00617-7","url":null,"abstract":"<div><p>The largest urban agglomeration in North Bengal is in Siliguri, which has experienced fast peri-urban expansion and a steady loss of natural environment due to the city’s rapid urbanization and migrant influx over the past three decades. This study examines the relation between built-up area and population in the Siliguri Urban Agglomeration as well as the spatiotemporal dynamics of landuse/landcover changes during for 2031, 2041, 2051, and 2100 using a number of driving variables. Additionally, to illustrate urban sprawl, Shannon’s entropy approach has been used to estimate built-up expansion, and the integrated cellular automata (CA)-Markov model was used to predict future land use/land cover scenarios. The results indicate that vegetation and agricultural land would decrease as a result from 1991 to 2100, from 9.19 km2 in 1991 to 73.62 km2 in 2100. Over the next 110 years, a large increase is anticipated in the built-up area, from 7.43% of the total land use area to 61.62%. In addition, the results suggest that between 1991 and 2021, the built-up area significantly increased from 9.63 km2 to 49.25 km2, while agricultural land and vegetation cover decreased by 13% and 50%, respectively. The percentage growth of intra-district in-migration to the Siliguri urban agglomeration was also observed to increase by 170% from 31% between 1991 and 2021, which put a lot of pressure on urban land and transformed agricultural and vegetated land into built-up areas. According to the gain and loss technique, agriculture and vegetation suffered the greatest losses, at 36.16 km2 and 29.79 km2, respectively. The population in 1991 was estimated to be 364,000 according to census statistics and Landsat pictures, although the built-up area was just 9.19 km2. The predicted population increase within 30 years was 1,050,000, and the built-up area was 49.25 km. As a result, in the next days, this city may turn into an urban heat island. The results of this study will assist policymakers in creating management strategies for environmentally friendly and orderly urban expansion.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"217 - 238"},"PeriodicalIF":2.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145166529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-19DOI: 10.1007/s12518-025-00610-0
Lucas dos Santos Bezerra, Paulo Sérgio de Oliveira Jr., Claudia Pereira Krueger, João Francisco Galera Monico
{"title":"Integrity monitoring of GAST-C and GAST-D simulations in low-latitude region under quiet and disturbed ionospheric activity","authors":"Lucas dos Santos Bezerra, Paulo Sérgio de Oliveira Jr., Claudia Pereira Krueger, João Francisco Galera Monico","doi":"10.1007/s12518-025-00610-0","DOIUrl":"10.1007/s12518-025-00610-0","url":null,"abstract":"<div><p>Ground-based augmentation systems (GBAS) enhance precision approach procedures by providing differential corrections from ground reference receivers, improving airborne accuracy and transmitting integrity data. This allows aircraft to calculate protection levels (PL) and ensure position error (PE) remains within acceptable bounds. However, ionospheric irregularities, particularly in low-latitude regions like Brazil, challenge GBAS efficiency, affecting availability and continuity during critical flight phases. To mitigate these disturbances, GBAS employs monitoring systems that assess integrity by tracking ionospheric conditions and other potential anomalies, ensuring computed PLs reflect the system’s ability to maintain safe operations under adverse environments. In this context, this study evaluates a simulated GBAS facility in Presidente Prudente, Brazil, using EUROCONTROL PEGASUS software to analyze the performance of GBAS approach service types C (GAST-C) and D (GAST-D) under quiet and disturbed ionospheric conditions. Results show that during periods of intense ionospheric activity, availability fell below the International Civil Aviation Organization (ICAO) threshold of 99%, with GAST-C and GAST-D achieving 94.3% and 93.5%, respectively. The study also investigated the effects of inflating the standard deviation of the vertical ionospheric gradient (<span>(:{sigma:}_{vig})</span>) to improve integrity, finding reduced occurrences of misleading information (MI) and no instances of hazardously misleading information (HMI). Availability, nevertheless, was further impacted, notably during disturbed periods. Satellite geometry and ionospheric scintillation were identified as significant factors in degrading positioning accuracy and protection levels. These findings highlight the importance of robust monitoring systems to ensure reliable GBAS operations in low-latitude regions and provide key insights for future deployment in Brazil.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"281 - 294"},"PeriodicalIF":2.3,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145166816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeomaticsPub Date : 2025-02-18DOI: 10.1007/s12518-025-00616-8
Gyan Prakash, Sindhuja Kasthala, Akshay Loya
{"title":"Deep learning for automatic post-disaster debris identification for precise damage assessments using UAV footage","authors":"Gyan Prakash, Sindhuja Kasthala, Akshay Loya","doi":"10.1007/s12518-025-00616-8","DOIUrl":"10.1007/s12518-025-00616-8","url":null,"abstract":"<div><p>With increased frequency and intensity of extreme climate events, unprecedented volumes of debris are created. Disaster debris can often be hazardous, and it obstructs relief activities by blocking the roads and preventing access to disaster sites. This highlights the importance of timely debris identification and removal efforts for effective relief and preliminary damage assessments. This work aims to automatically extract post-disaster debris from UAV footage using instance segmentation with YOLOv8-seg model. Automatic detection of debris, its type and geographical distribution allows efficient allocation of resources, prioritization of relief efforts and significant reduction in the time taken for disaster recovery. We use UAV images of Hurricane IAN, specifically of Julies Island along the coast of Florida. We trained and compared YOLOv8n (nano), YOLOv8m (medium), and YOLOv8x (extra-large) model architectures, to select the suitable model for post-disaster debris detection. Since debris clearance efforts typically depend on debris type, we trained and built specialized models for vegetation and non-vegetation debris separately. The YOLOv8x model exhibited the highest accuracy—83% accuracy for vegetation debris and 85% for non-vegetation debris, with corresponding mAP values of 62.2 and 66.1, respectively. The model detected non-vegetative debris as small as 0.13 square meters. Furthermore, we used YOLOv8 model to detect and track damaged, hazardous and non-hazardous assets on the street from UAV videos. We developed an algorithm to automatically produce georeferenced results from UAV images, enhancing the model's usability in real-world applications. The developed model automatically outputs precise location, size and area of debris, aiding post-disaster planning.</p></div>","PeriodicalId":46286,"journal":{"name":"Applied Geomatics","volume":"17 2","pages":"269 - 279"},"PeriodicalIF":2.3,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145166283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}