Novel parameters for sinkhole mapping in the anthropocene: Example from a karst-dominated landscape of the Missouri Ozarks, USA

Land subsidence susceptibility mapping in urban settlements using time-series PS-InSAR and random forest model

Windstorms may have negative consequences on forest ecosystems, industries, and societies. Extreme events related to extra-tropical cyclonic systems remind us that better recognition and understanding of the factors driving forest damage are needed for more efficient risk management and planning. In the present study, we statistically modelled forest damage caused by the windstorm Klaus in south-west France. This event occurred on 24 January 2009 and caused severe damage to maritime pine (Pinus pinaster) forest stands. We aimed at isolating the best potential predictors that can help to build better predictive models of forest damage. We applied the random forest (RF) technique to find the best classifiers of the forest damage binary response variable. Five-fold spatial block cross-validation, repeated five times, and forward feature selection (FFS) were applied to the control for model over-fitting. In addition, variable importance (VI) and accumulated local effect (ALE) plots were used as model performance metrics. The best RF model was used for spatial prediction and forest damage probability mapping. The ROC AUC of the best RF model was 0.895 and 0.899 for the training and test set, respectively, while the accuracy of the RF model was 0.820 for the training and 0.837 for the test set. The FFS allowed us to isolate the most important predictors, which were the distance from the windstorm trajectory, soil sand fraction content, the MODIS normalized difference vegetation index (NDVI), and the wind exposure index (WEI). In general, their influence on the forest damage probability was positive for a wide range of the observed values. The area of applicability (AOA) confirmed that the RF model can be used to construct a probability map for almost the entire study area.

Spatiotemporal patterns and drivers of ecosystem service interactions in karst regions: Insights for environmental protection and sustainability

Responding to Risk: The Making of Hazard Mitigation Strategy in Post‐Katrina New Orleans

Landslides are one of the most extensive geological disasters in the world. The objective of this study was to assess the performances of different landslide susceptibility models information content method (ICM), analytical hierarchy process (AHP), and random forest (RF) model) and mapping unit (slope unit and grid unit) for landslide susceptibility mapping in the Helong city, Jilin province, northeastern China. First, a total of 159 landslides were mapped in the study area based on a geological hazard survey (1:50,000) of Helong city. Then, the slope units of the study area were divided by using the curvature watershed method. Next, eight influencing factors, namely, lithology, slope angle, slope aspect, rainfall, land use, seismic intensity, distance to river, and distance to fault, were selected to map the landslide susceptibility based on geological data, field survey, and landslide information. Afterward, landslide susceptibility modeling of landslide inventory data is performed for extracting and learning the symmetry latent in data patterns and relationships by three landslide susceptibility models and utilizing it to predict landslide susceptibility. Finally, the receiver operating characteristic (ROC) curve was used to compare the landslide susceptibility models. In addition, results based on grid units were calculated for comparison. The AUC (the area under the curve) result for ICM, AHP, and RF model was 87.1%, 80.5%, and 94.6% for slope units, and 83.4%, 70.9%, and 91.3% for grid units, respectively. Based on the overall assessments, the SU-RF model was the most suitable model for landslide susceptibility mapping. Consequently, these methods can be very useful for landslide hazard mitigation strategies.

Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China

Geological disaster could pose a great threat to human development and ecosystem health. An ecological risk assessment of geological disasters is critical for ecosystem management and prevention of risks. Herein, based on the "probability-loss" theory, a framework integrating the hazard, vulnerability, and potential damage for assessing the ecological risk of geological disasters was proposed and applied to Fujian Province. In the process, a random forest (RF) model was implemented for hazard assessment by integrating multiple factors, and landscape indices were adopted to analyze vulnerability. Meanwhile, ecosystem services and spatial population data were used to characterize the potential damage. Furthermore, the factors and mechanisms that impact the hazard and influence risk were analyzed. The results demonstrate that (1) the regions exhibiting high and very high levels of geological hazard cover an area of 10.72% and 4.59%, respectively, and are predominantly concentrated in the northeast and inland regions, often distributed along river valleys. Normalized difference vegetation index (NDVI), precipitation, elevation, and slope are the most important factors for the hazard. (2) The high ecological risk of the study area shows local clustering and global dispersion. Additionally, human activities have a significant influence on ecological risk. (3) The assessment results based on the RF model have high reliability with a better performance compared with the information quantity model, especially when identifying high-level hazard areas. Our study will improve research on the ecological risk posed by geological disasters and provide effective information for ecological planning and disaster mitigation.

Currently, climate change requires the quantification of carbon stored in forest biomass. Synthetic aperture radar (SAR) data offers a significant advantage over other remote detection measurement methods in providing structural and biomass-related information about ecosystems. This study aimed to develop non-parametric Random Forest regression models to assess the changes in the aboveground forest biomass (AGB), basal area (G), and tree density (N) of Mediterranean pine forests by integrating ALOS-PALSAR, Sentinel 1, and Landsat 8 data. Variables selected from the Random Forest models were related to NDVI and optical textural variables. For 2015, the biomass models with the highest performance integrated ALS-ALOS2-Sentinel 1-Landsat 8 data (R2 = 0.59) by following the model using ALS data (R2 = 0.56), and ALOS2-Sentinel 1-Landsat 8 (R2 = 0.50). The validation set showed that R2 values vary from 0.55 (ALOS2-Sentinel 1-Landsat 8) to 0.60 (ALS-ALOS2-Sentinel 1-Landsat 8 model) with RMSE below 20 Mg ha−1. It is noteworthy that the individual Sentinel 1 (R2 = 0.49). and Landsat 8 (R2 = 0.47) models yielded equivalent results. For 2020, the AGB model ALOS2-Sentinel 1-Landsat 8 had a performance of R2 = 0.55 (validation R2 = 0.70) and a RMSE of 9.93 Mg ha−1. For the 2015 forest structural variables, Random Forest models, including ALOS PAL-SAR 2-Sentinel 1 Landsat 8 explained between 30% and 55% of the total variance, and for the 2020 models, they explained between 25% and 55%. Maps of the forests’ structural variables were generated for 2015 and 2020 to assess the changes during this period using the ALOS PALSAR 2-Sentinel 1-Landsat 8 model. Aboveground biomass (AGB), diameter at breast height (dbh), and dominant height (Ho) maps were consistent throughout the entire study area. However, the Random Forest models underestimated higher biomass levels (>100 Mg ha−1) and overestimated moderate biomass levels (30–45 Mg ha−1). The AGB change map showed values ranging from gains of 43.3 Mg ha−1 to losses of −68.8 Mg ha−1 during the study period. The integration of open-access satellite optical and SAR data can significantly enhance AGB estimates to achieve consistent and long-term monitoring of forest carbon dynamics.

Sinkholes are significant geohazards in karst regions that pose risks to landscapes and infrastructure by disrupting geological stability. Usually, sinkholes are mapped by field surveys, which is very cost-intensive with regard to vast coverages. One possible solution to derive sinkholes without entering the area is the use of high-resolution digital terrain models, which are also expensive with respect to remote areas. Therefore, this study focusses on the mapping of sinkholes in arid regions from open-access remote sensing data. The case study involves data from the Sentinel missions over the Mangystau region in Kazakhstan provided by the European Space Agency free of cost. The core of the technique is a multi-scale curvature filter bank that highlights sinkholes (and takyrs) by their very special illumination pattern in Sentinel-2 images. Marginal confusions with vegetation shadows are excluded by consulting the newly developed Combined Vegetation Doline Index based on Sentinel-1 and Sentinel-2. The geospatial analysis reveals distinct spatial correlations among sinkholes, takyrs, vegetation, and possible surface discharge. The generic and, therefore, transferable approach reached an accuracy of 92%. However, extensive reference data or comparable methods are not currently available.

Accurate monthly runoff forecasting is vital for water management, flood control, hydropower, and irrigation. In glacierized catchments affected by climate change, runoff is influenced by complex hydrological processes, making precise forecasting even more challenging. To address this, the study focuses on the Lotschental catchment in Switzerland, conducting a comprehensive comparison between deep learning and ensemble-based models. Given the significant autocorrelation in runoff time series data, which may hinder the evaluation of prediction models, a novel statistical method is employed to assess the effectiveness of forecasting models in detecting turning points in the runoff data. The performance of Extreme Gradient Boosting (XGBoost) was compared with long short-term memory (LSTM) and random forest (RF) models for one-month-ahead runoff forecasting. The study used 20 years of runoff data (2002-2021), with 70% (2002-2015) dedicated for training and calibration, and the remaining data (2016-2021) for testing. The findings for the testing phase results show that the XGBoost model achieves the best accuracy, with R² of 0.904, RMSE of 1.554 m³/sec, an NSE of 0.797, and Willmott index (d) of 0.972, outperforming both the LSTM and RF models. The study also found that the XGBoost model estimated turning points more accurately, obtaining forecasting improvements of up to 22% to 34% compared to LSTM and RF models. Overall, the study's findings are essential for global water resource management, providing insights that can inform sustainable practices to support societies impacted by climate change.

Many jurisdictions presently utilize, or are now considering the utilization of, high-volume wells as a municipal water supply source. Withdrawal of groundwater in karst regions implicates rights to use groundwater and possible interference with other rights of nearby landowners. Drought conditions and increased population contribute to an increased incidence of legal disputes over the use of groundwater as a municipal water supply source in karst regions. High-volume pumping of groundwater may cause land subsidence, including sinkholes, drying of springs and/or streams and loss in value of nearby land. This paper examines the legal causes of action available to landowners adversely affected by high-volume groundwater pumping: groundwater rights, "loss of lateral and subjacent support", nuisance, and "takings". The author concludes that the law fails to include environmental and geoscience considerations. State legislatures should consider legislative changes to unify legal and scientific principles.

Assessment of the risk arising from near surface natural hazard is a crucial step in overcoming foundation problems commonly encountered in engineering projects. It helps clients and other related parties to apply suitable procedures for ground treatment, mitigate potential natural hazards, and minimize human and economic losses. Karstic terrains in KSA is a major challenge for engineering constructions due to extensive occurrence of cavities and/or sinkholes that cause ground subsidence and building collapse. Cavities are air/sediment filled underground voids, commonly developed in limestone rocks by the infiltration of rainwater into the ground, opening up, over a long period of time, holes and tunnels. Mitigation of natural hazards can best be achieved through careful geotechnical studies. Traditionally, engineers use destructive probing techniques for the detection of cavities across regular grids or random distances. Such probing is insufficient on its own to provide confidence that cavities will not be encountered; particularly when the project site is sizable. Frequency of probing and depth of investigation may become prohibitively expensive. Besides, probing is intrusive, non-continuous, slow, expensive, and cannot provide a complete lateral picture of the subsurface geology. Geophysical investigation methods are best suited in site risk assessment (i.e. cavity detection) due to their capability to delineated near-surface cavities and overcome the limitations of traditional probing techniques. This of course helps engineers to develop the appropriate plans of hazard mitigation and implement accordingly the suitable engineering design. Several studies reported in literatures have utilized geophysical techniques for site characterization of karstic regions (Dunscomb and Rehwoldt, 1999; Kaufmann and Quinif, 2001; Roth and Nyquist, 2003). Although these techniques (e.g. resistivity, Seismic…etc) are disparate in their application and efficiency, they have proven good satisfactory results in different geological situations.

Landslides are among the most destructive natural hazards in the Western Ghats region of Kerala, driven by complex interactions between geological, hydrological, and anthropogenic factors. This study aims to generate a high-resolution Landslide Susceptibility Level Map (LSLM) using a machine learning (ML)-based Random Forest (RF) model integrated with Geographic Information Systems (GIS). A total of 231 historical landslide locations obtained from the Bhukosh portal were used as reference data. Eight predictive factors—Stream Order, Drainage Density, Slope, Aspect, Geology, Land Use/Land Cover (LULC), Normalized Difference Vegetation Index (NDVI), and Moisture Stress Index (MSI)—were derived from remote sensing and ancillary datasets, preprocessed, and reclassified for model input. The RF model was trained and validated using a 50:50 split of landslide and non-landslide points, with variable importance values derived to weight each predictive factor of the raster layer in ArcGIS. The resulting Landslide Susceptibility Index (LSI) was reclassified into five susceptibility zones: Very Low, Low, Moderate, High, and Very High. Results indicate that approximately 17.82% of the study area falls under high to very high susceptibility, predominantly in the steep, weathered, and high rainfall zones of the Western Ghats. Validation using Area Under the Curve–Receiver Operating Characteristic (AUC-ROC) analysis yielded an accuracy of 0.890, demonstrating excellent model performance. The output LSM provides valuable spatial insights for planners, disaster managers, and policymakers, enabling targeted mitigation strategies and sustainable land-use planning in landslide-prone regions.

Research Article| January 01, 1976 Tracing Subsurface Flow in Karst Regions Using Artificially Colored Spores GEORGE D. GARDNER; GEORGE D. GARDNER George D. Gardner and Richard E. Gray are with GAI Consultants, Inc., Monroeville, Pennsylvania. Search for other works by this author on: GSW Google Scholar RICHARD E. GRAY RICHARD E. GRAY George D. Gardner and Richard E. Gray are with GAI Consultants, Inc., Monroeville, Pennsylvania. Search for other works by this author on: GSW Google Scholar Environmental & Engineering Geoscience (1976) xiii (3): 177–197. https://doi.org/10.2113/gseegeosci.xiii.3.177 Article history first online: 02 Mar 2017 Cite View This Citation Add to Citation Manager Share Icon Share Twitter LinkedIn Tools Icon Tools Get Permissions Search Site Citation GEORGE D. GARDNER, RICHARD E. GRAY; Tracing Subsurface Flow in Karst Regions Using Artificially Colored Spores. Environmental & Engineering Geoscience 1976;; xiii (3): 177–197. doi: https://doi.org/10.2113/gseegeosci.xiii.3.177 Download citation file: Ris (Zotero) Refmanager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentBy SocietyEnvironmental & Engineering Geoscience Search Advanced Search Abstract Subsurface drainage divides in limestone karst regions often are not coincident with surface divides because of complex, often unpredictable solution channels in the limestone. Accurate delineation of these divides is requisite for determining the leakage potential of reservoirs and for pollution potential studies in karst areas. Conventional methods used for establishing subsurface conditions, such as water wells and piezometers do not always work in karst terrains, and direct tracing of subsurface flow is required.Among the tracers commonly used for tracing in karst regions, dyed-spores is one of the most successful. The technique involves coloring the minute spores from clubmoss (Lycopodium), which are available in bulk due to their use in the pharmaceutical industry, with biological stains, injecting the dyed-spores into sinkholes and trapping the spores with plankton nets that are strategically placed at all the potential resurgences. Dyed-spores make excellent tracers in karst regions because they are extremely small (30μ dia.) and can pass through very small openings; they have a density only slightly greater than cave water and will not readily settle out in somewhat turbulent flow; they are virtually indestructible and not affected by water chemistry; they are not harmful to biota or industrial processes; they travel at velocities close to that of the actual flow; they can be easily identified in trapped sediment using a microscope; and most importantly, at least five different tracings can be conducted simultaneously. Many commonly used techniques do not have all these attributes. The main disadvantages of the technique are that somewhat turbulent flow is required, and preparation and analysis are time consuming. This content is PDF only. Please click on the PDF icon to access. First Page Preview Close Modal You do not have access to this content, please speak to your institutional administrator if you feel you should have access.

As an essential data-driven model, machine learning can simulate runoff based on meteorological data at the watershed level. It has been widely used in the simulation of hydrological runoff. Considering the impact of snow cover on runoff in high-altitude mountainous areas, based on remote sensing data and atmospheric reanalysis data, in this paper we established a runoff simulation model with a random forest model and ANN (artificial neural network) model for the Xiying River Basin in the western Qilian region The verification of the measured data showed that the NSE (Nash–Sutcliffe efficiency), RMSE (root mean square error), and PBIAS (percent bias) values of the random forest model and ANN model were 0.701 and 0.748, 6.228 m3/s and 4.554 m3/s, and 4.903% and 8.329%, respectively. Considering the influence of ice and snow on runoff, the simulation accuracy of both the random forest model and ANN model was improved during the period of significant decreases in the annual snow and ice water equivalent in the Xiying River Basin from April to May, after the snow remote sensing data were introduced into the model. Specifically, for the random forest model, the NSE increased by 0.099, the RMSE decreased by 0.369 m3/s, and the PBIAS decreased by 1.689%. For the ANN model, the NSE increased by 0.207, the RMSE decreased by 0.700 m3/s, and the PBIAS decreased by 1.103%. In this study, based on remote sensing data and atmospheric reanalysis data, the random forest model and ANN model were used to effectively simulate hydrological runoff processes in high-altitude mountainous areas without observational data. In particular, the accuracy of the machine learning simulations of snowmelt runoff (especially during the snowmelt period) was effectively improved by introducing the snow remote sensing data, which can provide a methodological reference for the simulation and prediction of snowmelt runoff in alpine mountains.