Figure 4 - uploaded by Eder Martins
Content may be subject to copyright.
Source publication
Remote sensing has been used in karst studies to identify limestone terrain, describe exokarst features, analyze karst depressions, and detect geological structures important to karst development. The aim of this work is to investigate the use of ASTER-, SRTM- and ALOS/PRISM-derived digital elevation models (DEMs) to detect and quantify natural kar...
Contexts in source publication
Context 1
... analysis may be used to improve the accuracy of predicting doline occurrence and eliminate false dolines. Many of the false dolines can be easily eliminated as being incompatible with known characteristics of karst depressions in the study area (Figure 4). We used the following morphometric attributes to automate delineation of doline polygons: area, perimeter and circularity index (CI). ...
Context 2
... the exact polygon representation is inherently imprecise because the landform itself is hard to define precisely, i.e., the closer you look, the less well-defined the edge becomes. Figure 4 illustrates the hypothetical area of an idealized doline using different thresholds, and how the area decreases with doline depth. ...
Similar publications
The paper considers the experience of using geoinformation systems (GIS) for local geomorphologic zoning. Within the main pipeline routes (MPR) during the construction, the morphology of the relief and the surface cover of loose new deposits changes. As a result, dangerous relief-forming processes arise or are activated. Regional assessments of the...
In this article, we investigate the potential for detection and characterization of sinkholes under dense forest cover by using airborne laser scanning data. Laser pulse returns from the ground provide important data for the estimation of digital elevation model (DEM), which can be used for further processing. The main objectives of this study were...
Sinkholes are significant geologic hazards that are mainly formed in water-soluble carbonate bedrocks such as limestone, dolomite or gypsum. Sinkhole formation causes the surface to subside or collapse suddenly without any prior warning, and therefore can lead to extensive damage and even loss of life and property. Delineating sinkholes is importan...
Abstract
In Turkey, comprehensive studies about karst geomorphology are being carried out recently. In our country situates on the Alpine-Himalayan fold system and there are very large limestones of almost every geologic era. Again, in this area have tectonic factors and appropriate processes. So, karst studies are very huge in this belt. In this s...
Recharge of karst aquifers occurs when rainfall (or snowmelt) infiltration is able to cross the soil mantle, and percolate throughout the vadose zone. As a consequence of the karstification processes, in karst environment concentrated and diffused types of infiltration can occur. In Mediterranean areas, karst massifs have an important role as they...
Citations
... Previously, the most frequently used methods for the perimetry of the upper edge of the dolina involved the use of topographic maps of various scales assuming that the higher closed boundary correctly represents the perimeter of the dolina (Denizman 2003, Telbisz et al. 2009, Bauer 2015. Recently, the identification of sinkholes has become increasingly focused on automation of the perimeter using digital terrain models by combining digital elevation models (DEM) and satellite images or by combining DEM and different algorithms (de Carvalho Junior et al. 2013, Obu and Podobnikar 2013, Pardo-Igúzquiza et al. 2013, Bauer 2015, Telbisz et al. 2016. The production of very high resolution DTM (1 meter grid) generated by high density LIDAR surveys is currently a consolidated methodology (Kraus and Pfeifer 1998, Axelsson 1999, Wehr and Lohr 1999, Vosselman 2000. ...
The distribution and characteristics of karst sinkholes is critical for the understanding and evaluation of geohazards. A two-step process, involving computer vision and machine learning methods, has been developed to map and classify depressions as sinkholes. Every depression has been mapped from a LIDAR derived DTM first and later a machine learning random forest binary classifier was then used on the extracted depressions to identify karst sinkholes. The study shows that the two-step method can accurately map karst sinkholes from high resolution DTM even if a visual check must be done on the non-karst sinkhole dataset to improve the classification.
... In theory, round and aligned depressions correspond to qanat shafts. This method has been used on sink-hole depressions in karst by several authors and has provided good results in automatic or semi-automated detection (Wall, Doctor & Terziotti 2015;de Carvalho et al. 2014). While most qanat shafts were too eroded to allow the use of this tool as automated or semi-automated, some areas where shafts presented a well-visible depression provided significant results. ...
... In recent decades, some countries have begun to realize the importance of this work. Traditional sinkhole investigations and mapping primarily rely on topographic maps, digital elevation models (DEMs), historical aerial photography, or satellite images [2,[15][16][17][18]. In recent years, many researchers have started using remote sensing [19], synthetic aperture radar interferometry (InSAR) [20], photogrammetry [21], and light detection and ranging (LiDAR) [22][23][24][25][26] to detect and identify sinkholes worldwide. ...
Soil piping erosion is an underground soil erosion process that is significantly underestimated or overlooked. It can lead to intense soil erosion and trigger surface processes such as landslides, collapses, and channel erosion. Conducting susceptibility mapping is a vital way to identify the potential for soil piping erosion, which is of enormous significance for soil and water conservation as well as geological disaster prevention. This study utilized airborne radar drones to survey and map 1194 sinkholes in Sunjiacha basin, Huining County, on the Loess Plateau in Northwest China. We identified seventeen key hydrogeomorphological factors that influence sinkhole susceptibility and used six machine learning models—support vector machine (SVM), logistic regression (LR), Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), random forest (RF), and gradient boosting decision tree (GBDT)—for the susceptibility assessment and mapping of loess sinkholes. We then evaluated and validated the prediction results of various models using the area under curve (AUC) of the Receiver Operating Characteristic Curve (ROC). The results showed that all six of these machine learning algorithms had an AUC of more than 0.85. The GBDT model had the best predictive accuracy (AUC = 0.94) and model migration performance (AUC = 0.93), and it could find sinkholes with high and very high susceptibility levels in loess areas. This suggests that the GBDT model is well suited for the fine-scale susceptibility mapping of sinkholes in loess regions.
... Sinkholes exhibit specific morphological/physical characteristics compared with the surrounding terrain, and these characteristics can be utilized to detect and map their distributions (De Carvalho et al., 2013;Shannon et al., 2019). Some of the widely known characteristic traits of sinkholes include their relatively low elevation (depression) and nearcircular shape/morphology (Filin et al., 2014;Zhang et al., 2019). ...
... Hence, further analysis was undertaken to filter out depressions exhibiting morphometric properties that are not typically associated with sinkholes in the region. The CI, which considers the area and perimeter of the polygon (De Carvalho et al., 2013;Shannon et al., 2019;Zumpano et al., 2019), was employed to eliminate non-sinkhole depressions. The CI value was calculated using the following Eq. ...
... First is the contour method, in which depressions are detected from contoured terrains [7][8][9][10]; however, the detected depressions often form a peak-depression combination, whereby neighboring peaks are classified as the same terrain unit, making it difficult to determine the exact extent of the depression. Second is the hydrological analysis method; this method involves the use of the ArcGIS software hydrological analysis module and a digital elevation model (DEM) to perform a filling process to identify and detect depressions [11][12][13][14][15]. However, the area to which this process can be applied is limited and the number of detected depressions is small; therefore, some depressions are missed. ...
... (www.preprints.org) | NOT PEER-REVIEWED | Posted: 22 April 2024 doi:10.20944/preprints202404.1331.v115 ...
Karst peaks and depressions are scattered in karst zones with strong spatial heterogeneity and fragile ecological environments and are crucial for determining the degree of karst geomorphologic development. However, realizing automatic depiction and extracting depressions with high accuracy is difficult because of their complex morphology. Herein, based on 12.5-m resolution DEM data, six typical karst peaks from depressions in southwest China were selected as the study areas and a revised terrain openness index method based on slope mutation points (ROBSMPs) was used to determine the degree of karst geomorphologic development and the boundary of karst depressions. The extent of depressions extracted by ROBSMPs and the terrain openness index method with the extent of depressions hand-drawn based on remote sensing images was compared and analyzed. The results show that compared with the topographic openness index method, the overall accuracy of karst depression extracted by ROBSMPs was improved and the perimeter, area, and raster displacement error indexes were reduced. ROBSMPs realized high-precision extraction of depressions, thereby strengthening the applicability of the topographic openness index method to karst peak zones. This study offers a new perspective and path toward the expansion of digital terrain analysis technology in karst mountainous areas and is expected to play a vital role in the extraction of similar geomorphic units in karst zones.
... This development emphasises how extensive multimodal analysis using GNNs can improve the precision and effectiveness of MDD identi cation. In Brazil's Bambuí Group, De Carvalho et al. (2014) [7] looked into karst depression detection using ASTER, ALOS/PRISM, and SRTM-derived Digital Elevation Models. Their study emphasises how well remote sensing works to detect and characterise karst landscapes, including exokarst features and limestone terrains. ...
In the quest to enhance predictive models for depression, this study introduces a novel comparative analysis of machine learning (ML) and deep learning (DL) techniques, further innovating with the development of hybrid AI models. Leveraging a dataset comprising 2,000 participants, enriched with demographic, socio-economic, behavioral, and clinical variables, including pre- and post-treatment Montgomery-Åsberg Depression Rating Scale (MADRS) scores, we embarked on a comprehensive exploration of factors influencing depression outcomes. Through meticulous data collection, we harmonized diverse variables ranging from basic demographic details to intricate clinical outcomes, paired with a rigorous feature selection process employing Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA). Our analytical journey was underpinned by a robust hyper parameter tuning phase, ensuring the optimization of each model's predictive capacity. The study's core contribution lies in its exhaustive comparison of standalone ML and DL models against our crafted hybrid AI models, revealing a marked superiority of the latter in predicting depression with unparalleled accuracy. The hybrid models, through their synergetic integration of ML and DL methodologies, demonstrated a profound ability to navigate the complexity of depression's multifactorial nature, achieving a perfect prediction accuracy rate in our tests. Our findings advocate for a paradigm shift in predictive analytics for depression, underscoring the potential of hybrid AI models in transcending the limitations of traditional standalone approaches. This research not only paves the way for more nuanced and effective predictive tools in mental health care but also sets a benchmark for future studies at the intersection of biology, psychology, and artificial intelligence. The implications of this work are vast, offering a beacon of hope for personalized and preemptive mental health interventions.
... Remote sensing provides useful information on different objects on the ground. Researchers have been using such data in many studies to study lineaments [20,21] of various geologic formations, for geologic mapping [22], to identify karst in vulnerable areas [17,19,23], and land cover/land use [24]. It has also been used for environmental monitoring [25,26]. ...
Tabular Middle Atlas of Morocco holds the main water reservoir that serves many cities across Morocco. Dolomite and limestone are the most dominant geologic formations in this region in which water resources are contained. The recent studies conducted to evaluate the quality of this water suggest that it is very vulnerable to pollutants resulting from both anthropogenic and natural phenomenon. High and very high-resolution satellite imagery have been used in an attempt to gain a better understanding of this karstic system and suggest a strategy for its protection in order to reduce the impact of these phenomenon. Based on the surface reflectance of land cover benchmarks, the karstic system has been horizontally delineated, as well as regions with intense human activities. Using band combination in the portion of the infrared, shortwave infrared, and visible parts of the electromagnetic spectrum, we identified bare lands which have been interpreted as carbonate rocks, clay minerals, uncultivated fields, basalts rocks, and built-up areas. Other classes such as water and vegetation have been identified. Carbonate rocks have been identified as areas with a high rate of water infiltration through their fracture system. Using a Sobel operator filter, these fractures have been mapped and their results have revealed new and existing faults in two major fracture directions, NE-SW and NW-SE, where NE-SW is the preferable pathway for surface water infiltration towards the groundwater reservoir, while the NW-SE direction drains groundwater from the Cause to the basin of Saiss. Over time, the infiltration of surface water through fractures has contributed to a gradual erosion of the carbonate rocks, which in turn developed karst landforms. This karst system is vulnerable due to the flow of pollutants in areas with shallow sinkholes. Using GDEM imagery, we extracted karst depressions, and their analysis shows that they are distributed along the fracture system and many of them were located on curvilinear or linear axes along the NE-SW fracture direction. We found also dolines scattered in areas with a high intensity of fractures. This distribution has been validated by both on-the-ground measurements and very high-resolution satellite images, and depressions of different forms and shapes dominated by dolines, poljes, lapiez, and avens have been identified. We also found many water springs with a highly important water output, such as the Ain Maarrouf water spring. The aim of this study is to enhance the understanding of the hydrogeological system of TMA, to improve the existence of the fracture database in the Cause of Agourai, and to establish a new morpho-structural picture of the Ain Maarrouf water spring.
... Sinkholes or dolines are the most common karst features [60]. A DEM combined with a topographical map delineated the karst depression [60,61]. As one of the prevalent features of karstification, closed depressions were categorised as potential (future) karst depressions. ...
Understanding complex carbonate fracture networks and karstification at various geological scales is challenging, especially with limited multi-scale datasets. This paper aims to reduce uncertainty in the fracture architecture of Central Luconia karstified reservoirs by narrowing observational gaps between seismic and well data by using the discrete fracture models of exposed limestone outcrops as analogues for the subsurface carbonate reservoir. An outcrop-based fracture network characterisation of a near-surface paleo-karst at Subis Limestone combined with lineament analysis was conducted to extract fracture parameters. The karst structure was first delineated using a digital elevation map and outcrop examination. Then, topology analysis was performed, following the creation of two-dimensional discrete fracture models. Two main fracture sets oriented northeast–southwest and northwest–southeast and 79 potential dolines were identified. Fracture intersections, northeast–southwest major orientations, and drainage systems highly influenced the karst features. The Subis Limestone fracture model revealed that the highest number of fractures and total length of fractures were concentrated in the northern part of the Subis Limestone build-up (X: 250–350, Y: 150–250) and became denser towards the northwest direction of the outcrop (X: 600–800). The fractures in the Subis paleo-karsts appear isolated, with I-nodes ranging from 0.74 to 0.94. Hence, it is crucial to incorporate matrix porosity into multiple scales of fracture network modelling to improve upscaling and the modelling of fracture–vug networks, as well as to minimise the underestimation of discrete fracture networks in fractured and karstified limestone.
... In cases related to functional quality, quality assessment and applied perspective (use-case centered), specific reference data are used for each use case. Ref. [51] counted detected dolines (karst depressions) with reference to manually interpreted data, while [52] relied on in-situ observations. Other terrain features like gullies are also possible [53]. ...
... • Detection of depressions and peaks. Ref. [51] investigates the use of GDEMs to detect and quantify natural karst depressions. For the evaluation, ref. uses the overall accuracy and also a morphometric analysis based on the circularity index. ...
From an extensive search of papers related to the comparison of Global Digital Elevation Models (hereinafter GDEMs), an analysis is carried out that aims to answer several questions such as: Which GDEMs have been compared? Where have the comparisons been made? How many comparisons have been made? How have the assessments been carried out? Which is the GDEM option with the lowest RMSE? Analysis shows that SRTM and ASTER are the most popular GDEMs, that the countries where more comparisons have been made are Brazil, India, and China, and that the main type of reference data for evaluations is the use of points surveyed by GNSS techniques. A variety of criteria have been found for the comparison of GDEMs, but the most used are the RMSE and the standard deviation of the elevation error. There are numerous criteria with a more user-centric character in thematic areas, such as morphometry, geomorphology, erosion, etc. However, in none of the thematic areas does there exist a standard method of comparison. This limits the possibilities of establishing a ranking of GDEMs based on their user-focused quality. In addition, the methods and reference data set are not adequately explained or shared, which limits the interoperability of the studies carried out and the ability to make robust comparisons between them.
... Due to the scarcity of information regarding the dolines, the semi-automatic method of identifying karst depressions was used to determine the locality of these features. The method consists in identifying closed depressions from Digital Elevation Models based on procedures in a GIS environment and with the application of morphometric parameters (Carvalho Júnior et al., 2014;Silva et al., 2022). It is noteworthy that the method use must be accompanied by visual inspection of the polygons generated, discarding the use of false positives. ...
