Geo-environmental Factors Research Articles

Geo-Environmental Factors’ Influence on the Prevalence and Distribution of Dental Fluorosis: Evidence from Dali County, Northwest China

Residents living in areas with high fluorine environmental background will ingest excessive fluorine from the atmosphere, drinking water, food and other ways. Long-term effects of fluorine on the human body could cause people suffering from dental fluorosis and influence the sustainable development of the severe fluorosis areas. Previous studies have independently discussed the high fluoride environment in Dali County from the aspects of natural environment, drinking water quality and endemic fluorosis. This study carried out a detail investigation on dental fluorosis population in seven selected villages of Dali County, Shaanxi province, northwest China. The highest dental fluorosis index of 1.9 was found in Lianjia village located near the Anren depression, while the lowest dental fluorosis index of 0.0 was found in Jiaxi village near the Yellow River alluvium. Groundwater fluorine contents the range was 0.01 mg/L to 11.80 mg/L, with the highest value (2.6 mg/L) being observed in the 2nd terrace of Weihe River. The lowest groundwater fluorine content (0.8 mg/L) was observed in the Yellow River alluvium. Soil fluorine contents ranged from 1.18 mg/kg to 13.70 mg/kg, with its highest value (13.70 mg/kg) observed in Xinfeng village near the Anren depression. The lowest value of fluorine (1.18 mg/kg) was found in soil from the 1st terrace of Weihe River. As for the fluorine contents of corn, they ranged from 4.04 mg/kg to 7.72 mg/kg. The highest value (7.72 mg/kg) appeared in the 3rd terrace of Weihe River and the lowest value (4.04 mg/kg) in the 2nd terrace of Weihe River. The soil leaching was the dominant fluorine source of groundwater environment. Areas with severe dental fluorosis are located at the edge of the depression and the conjunction between steep slope and gentle slope. A poor correlation was found between the dental fluorosis index from the seven investigated villages and the corn fluorine content contrarily to the groundwater fluorine content, which positively correlated to the dental fluorosis index. Based on the obtained results, two recommendations were done to prevent and control dental fluorosis and accelerate the sustainable development in Dali County: to strengthen the use of low fluorine groundwater for drinking water supply, and to widely install the public water purifiers in the rural communities for purifying high-fluorine water to reduce the incidence of dental fluorosis in the population.

Spatiotemporal dynamics and geo-environmental factors influencing mangrove gross primary productivity during 2000–2020 in Gaoqiao Mangrove Reserve, China

BackgroundMangrove forests are a significant contributor to the global carbon cycle, and the accurate estimation of their gross primary productivity (GPP) is essential for understanding the carbon budget within blue carbon ecosystems. Little attention has been given to the investigation of spatiotemporal patterns and ecological variations within mangrove ecosystems, as well as the quantitative analysis of the influence of geo-environmental factors on time-series estimations of mangrove GPP. MethodsThis study explored the spatiotemporal dynamics of mangrove GPP from 2000 to 2020 in Gaoqiao Mangrove Reserve, China. A leaf area index (LAI)-based light-use efficiency (LUE) model was combined with Landsat data on Google Earth Engine (GEE) to reveal the variations in mangrove GPP using the Mann-Kendall (MK) test and Theil-Sen median trend. Moreover, the spatiotemporal patterns and ecological variations in mangrove ecosystems across regions were explored using four landscape indicators. Furthermore, the effects of six geo-environmental factors (species distribution, offshore distance, elevation, slope, planar curvature and profile curvature) on GPP were investigated using Geodetector and multi-scale geo-weighted regression (MGWR). ResultsThe results showed that the mangrove forest in the study area experienced an area loss from 766.26 ​ha in 2000 to 718.29 ​ha in 2020, mainly due to the conversion to farming, terrestrial forest and aquaculture zones. Landscape patterns indicated high levels of vegetation aggregation near water bodies and aquaculture zones, and low levels of aggregation but high species diversity and distribution density near building zone. The mean value of mangrove GPP continuously increased from 6.35 ​g ​C·m−2·d−1 in 2000 to 8.33 ​g ​C·m−2·d−1 in 2020, with 23.21% of areas showing a highly and significantly increasing trend (trend value ​> ​0.50). The Geodetector and MGWR analyses showed that species distribution, offshore distance and elevation contributed most to the GPP variations. ConclusionsThese results provide guidelines for selecting GPP products, and the combination of Geodetector and MGWR based on multiple geo-environmental factors could quantitatively capture the mode, direction, pathway and intensity of the influencing factors on mangrove GPP variation. The findings provide a foundation for understanding the spatiotemporal dynamics of mangrove GPP at the landscape or regional scale.

Prediction of Flash Flood Susceptibility of Hilly Terrain Using Deep Neural Network: A Case Study of Vietnam

Flash floods are one of the most dangerous natural disasters, especially in hilly terrain, causing loss of life, property, and infrastructures and sudden disruption of traffic. These types of floods are mostly associated with landslides and erosion of roads within a short time. Most of Vietnam is hilly and mountainous; thus, the problem due to flash flood is severe and requires systematic studies to correctly identify flood susceptible areas for proper landuse planning and traffic management. In this study, three Machine Learning (ML) methods namely Deep Learning Neural Network (DL), Correlation-based Feature Weighted Naive Bayes (CFWNB), and Adaboost (AB-CFWNB) were used for the development of flash flood susceptibility maps for hilly road section (115 km length) of National Highway (NH)-6 in Hoa Binh province, Vietnam. In the proposed models, 88 past flash flood events were used together with 14 flash floods affecting topographical and geo-environmental factors. The performance of the models was evaluated using standard statistical measures including Receiver Operating Characteristic (ROC) Curve, Area Under Curve (AUC) and Root Mean Square Error (RMSE). The results revealed that all the models performed well (AUC > 0.80) in predicting flash flood susceptibility zones, but the performance of the DL model is the best (AUC: 0.972, RMSE: 0.352). Therefore, the DL model can be applied to develop an accurate flash flood susceptibility map of hilly terrain which can be used for proper planning and designing of the highways and other infrastructure facilities besides landuse management of the area.

Medical geology and overview of studies from Africa and Asia

Abstract Despite some appreciable development of Medical Geology reported in various parts of the world, Africa and Asia are still developing. Indeed, there is substantial evidence to demonstrate that research in this area holds significant relevance for the African and Asian continents. Given the importance of geo-environmental materials, factors, and processes, including both geogenic and anthropogenic activities, as well as the consistently reported cases of diseases associated with such activities in Africa and Asia, it has become imperative to explore genuine relationships. This review delves into comprehensive studies on the impact of geological factors on human health. The geologic sources of contamination by toxic elements in the environment, which lead to human exposure through food and water, are examined closely. Recent case studies, research, and development (R&D) efforts undertaken by scholars, researchers, and government institutions are also thoroughly reviewed, with the aim of charting a course toward viable solutions. Furthermore, the discussion extends to raising awareness about the harmful effects of water contamination caused by toxic metals, such as arsenic and fluoride, and addressing mining hazards in Africa and Asia. The issue of exposure to toxic metals and metalloids, including lead and chromium (II), is also tackled. Recommendations are put forth emphasizing the necessity of synergy among medical scientists, geologists, geochemists, biochemists, and other stakeholders involved in environmental health studies. The importance of creating an environment conducive to brainstorming ideas that contribute to understanding the emergence of new pathologies, as well as the development of pertinent curricula for institutions in Africa and Asia, is also thoroughly discussed.

Laboratory and field studies on the effect of geoenvironmental factors on the removal of linear alkylbenzene sulfonate during riverbank filtration

Laboratory and field studies on the effect of geoenvironmental factors on the removal of linear alkylbenzene sulfonate during riverbank filtration

Technology and Operation Mode of Sludge Deposition Polygons as Important Geoenvironmental Factors for Surrounding Areas

Technology and Operation Mode of Sludge Deposition Polygons as Important Geoenvironmental Factors for Surrounding Areas

Gully erosion susceptibility assessment based on machine learning-A case study of watersheds in Tuquan County in the black soil region of Northeast China

Owing to its unique topographic and climatic conditions, agricultural production, and anthropogenic grazing, severe gully erosion has developed in the watersheds of Tuquan County located in the black soil region of Northeast China. Using three machine learning models to assess gully erosion susceptibility in this region, the main purpose of this study was to determine the important factors affecting the occurrence of gully erosion from 25 geo-environmental factors and select the model with the best prediction performance. Field data collection was conducted for 823 gullies. 12,496 pixels corresponding to 823 gullies and 12,496 pixels without gully erosion were randomly selected to form the model calculation database. According to the principle of multiple screening, this study selected 25 geo-environmental factors affecting the occurrence of gully erosion. Two factors, coarse sand content and fine sand content, were excluded by multi-collinearity analysis and using random forest (RF), convolution neural network (CNN), and transformer models, combining the 10-fold cross-validation and related validation metrics to assess the susceptibility of gully erosion in Tuquan County’s small watersheds. The results show that the convergence index (CI), topographical wetness index (TWI), terrain ruggedness index (TRI), and distance from the river based on the RF model are important factors affecting the occurrence of gully erosion. The transformer model (mean AUC of training = 95.338 %, mean AUC of validation = 95.342 %) was superior to the RF (mean AUC of training = 99.997 %, mean AUC of validation = 92.518 %) and CNN (mean AUC of training = 86.995 %, mean AUC of validation = 84.647 %) models in predicting performance. To ensure that the management and decision-making departments take reasonable and effective measures to prevent gully erosion in the study area, the gully erosion susceptibility maps produced using the three machine learning models were beneficial.

A large-scale Sr and Nd isotope baseline for archaeological provenance in Silk Road regions and its application to plant-ash glass

Bioavailable Sr and detrital Nd isotopes are important tools for archaeological provenance. To apply Sr and Nd isotopes for provenance, regional isotope databases and baselines are generally needed. For the vast Silk Road regions of Mesopotamia, Iran, and Central Asia, detailed isotopic distribution patterns essential for determining provenance may not become available in the short term due to the severe deficiency of available data. In the present work, we investigate the geo-environmental factors controlling the Sr and Nd isotopic signatures and use published data from archaeology and Earth sciences, selected by rigorous criteria, to construct the first large-scale, semi-quantitative Sr–Nd isotope baseline for these Silk Road regions. Three isotopic zones are proposed for Central Asia: CA-1 (mountains), εNd < −7.5, 87Sr/86Sr > 0.7095; CA-2 (deserts), εNd = −5 to −2, 87Sr/86Sr ∼ 0.709; CA-3 (loess), εNd = −5 to −2, 87Sr/86Sr > 0.710. General isotopic signatures are suggested for Iran: εNd = −8 to −4, 87Sr/86Sr = 0.7075–0.7090. Three isotopic zones are proposed for Mesopotamia: MP-1 (floodplain and foothill), εNd = −6.5 to −4 (putative extended range MP-1N, εNd = −8 to −6), 87Sr/86Sr = 0.7080–0.7085; MP-2 (deserts), εNd < −8, 87Sr/86Sr > 0.7085; MP-3 (Syrian Euphrates), εNd = −5.5 to −2, 87Sr/86Sr = 0.7080–0.7085. Within the limitation of available data, these ranges indicate the overall trend of bioavailable Sr and detrital Nd isotopic signatures for each isotopic zone, which are controlled by their geological context, climate (e.g., precipitation), and various Earth surface processes (e.g., riverine versus aeolian transport). This baseline can be used as an essential guide for geochemical contexts to suggest or verify the provenance of plant-ash glass, serving as part of an integrative Sr–Nd isotopic approach. We illustrate the potential of this approach using two case studies. By investigating the isotopic compositions of Mesopotamian plant-ash glass, we suggest possible northern Mesopotamian origins for plant ash and silica raw materials used for Mesopotamian glass-making. By reassessing medieval plant-ash glass from San Lorenzo, Italy, we propose diverse origins including Central Asia and Mesopotamia. Additionally, as part of this isotopic approach, by examining the Nd isotope mixing lines in the context provided by the Nd isotope baseline, we reveal the occurrence of glass recycling for Islamic plant-ash glass from different production zones in association with a westward spread from Mesopotamia to the Eastern Mediterranean metropolises.

Assessment of slope failure susceptibility along road networks in a forested region, northern Iran

The risk of slope failure is always associated with the roads constructed in mountain regions. Estimation of the susceptibility of roads to slope failure is a part of the solutions for decreasing road maintenance costs. In this study, we modeled the susceptibility of slope failure along a forest road in northern Iran using the random forest (RF) method. The distribution of past failures was surveyed during field reconnaissance to produce an inventory map. Then the failures were randomly divided into two groups such that 70% (176 locations) were used for model training and the remaining 30% (75 locations) were used for model validation. Eleven geoenvironmental factors (i.e., altitude, slope degree, slope direction, plan curvature, flow accumulation, stream power index, topographic wetness index, topographic position index, topographic roughness index, slope-length, and valley depth) that thought directly or indirectly affected slope failure were selected and linked to the failure locations. The spatial associations between the influencing factors and the failure locations were assessed using the RF method and used for generating spatially explicit maps of slope failure susceptibility. The results showed that stream power index, flow accumulation, and plan curvature with Gini coefficients of 74%, 66%, and 51%, respectively, were the most influential factors in the occurrence and distribution of slope failures. The slope failure susceptibility maps were classified using the natural breaks and geometrical intervals classification methods and showed that nearly 38.11% and 42.42% of the study area are in high to very high risk classes, respectively. Model validation using the sensitivity (92.31%), specificity (85.68%), accuracy (88.54%), root mean square error (RMSE) (0.303), and area under the curve (0.902) proved the excellent performance of the RF model in elucidating the failure mechanisms and predicting future failures. The slope failure susceptibility maps produced in this study allow the development of mitigation strategies for road construction projects.

Development of geo-environmental factors controlled flash flood hazard map for emergency relief operation in complex hydro-geomorphic environment of tropical river, India.

The occurrences of flash floods in sub-tropical climatic regions like India are ubiquitous phenomena, particularly during the monsoon season. This type of flood occurs within a short period of time and makes it distinctive from all-natural hazards, which causes huge loss of economy and causalities of life. Therefore, its prediction is crucial and one of the challenging tasks for researchers to mitigate this sustainably. Furthermore, identifying flash flood susceptible regions is the foremost responsibility in managing flood events, which helps the local administration take emergency relief operations in flood-prone regions. In September 2021, the flood in the Gandheswari river basin was the most severe compared to the past decade. The occurrences of flash floods in the lower course of the Gandheswari river has been affected riparian habitats rigorously. Thus, in this study, we proposed the bivariate logistic regression (LR) method to delineate this river basin's flash flood hazard (FFH) map. Here, sixteen flood conditioning factors were selected for modeling purposes with the help of a multicollinearity test, and a total of 71 flood points were identified from the historical dataset. The produced result was validated by six distinctive validating techniques, including receiver operating characteristics (ROC) analysis, specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and F-score. These techniques have shown that present modeling has high predictive performance in both training and testing dataset with the values of ROC (training-0.928, validating-0.892), specificity (training-0.911, validating-0.882), sensitivity (training-0.915, validating-0.885), PPV (training-0.912, validating-0.874), NPV (training-0.91, validating-0.875), and F-score (training-0.92, validating-0.89). Therefore, the proposed method in this and the outcome result will help the disaster manager make proper decisions to mitigate the hazardous situation and take sustainable emergency relief operations.

Psychological review of geo-environmental factors in three Persian folk stories

Cognitive narratology has been recognised as one of the most important ways of understanding human nature as expressed in the stories and narrations. In the present preliminary study, we aimed to use Turner and Fauconnier’s concepts of mental spaces and conceptual blending to explain the peculiarities of three stories belonging to three different cultural and geo-climate regions in Iran. In the present study, after collecting data from a set of texts, which included written, oral or visual, the content analysis method was used. We found some similarities among the mental spaces of different geographic regions in these three stories. They are, however, not solely influenced by environmental and cultural factors. The paper recommends that studies and investigations similar to the present one can be considered a basic but crucial step in demonstrating the extent to which a person's cognition and cognitive processing in general and the creation of meaning in particular are a continuation and representation of embodied experiences. Keywords: Cognitive, conceptual blending, geo-environmental, narratology, storytelling

Dengue risk zone mapping of Thiruvananthapuram district, India: a comparison of the AHP and F-AHP methods.

Dengue fever, which is spread by Aedes mosquitoes, has claimed many lives in Kerala, with the Thiruvananthapuram district bearing the brunt of the toll. This study aims to demarcate the dengue risk zones in Thiruvananthapuram district using the analytical hierarchy process (AHP) and the fuzzy-AHP (F-AHP) methods. For the risk modelling, geo-environmental factors (normalized difference vegetation index, land surface temperature, topographic wetness index, land use/land cover types, elevation, normalized difference built-up index) and demographic factors (household density, population density) have been utilized. The ArcGIS 10.8 and ERDAS Imagine 8.4 software tools have been used to derive the risk zone maps. The area of the risk maps is classified into five zones. The dengue risk zone maps were validated using dengue case data collected from the Integrated Disease Surveillance Programme portal. From the receiver operating characteristic (ROC) curve analysis and the area under the ROC curve (AUC) values, it is proved that the F-AHP method (AUC value of 0.971) has comparatively more prediction capability than the AHP method (AUC value of 0.954) in demarcating the dengue risk zones. Also, based on the comparison of the risk zone map with actual case data, it was confirmed that around 82.87% of the dengue cases occurred in the very high and high-risk zones, thus proving the efficacy of the model. According to the dengue risk map prepared using the F-AHP model, 9.09% of the area of Thiruvananthapuram district is categorized as very high risk. The prepared dengue risk maps will be helpful for decision-makers, staff with the health, and disaster management departments in adopting effective measures to prevent the risks of dengue spread and thereby minimize loss of life.

A Combined Method for Preparation of Landslide Susceptibility Map in Izmir (Türkiye)

Landslide susceptibility maps (LSMs) have been used frequently by researchers for many years in prediction of the occurrence of landslides. Since many landslides have occurred there in the past, Izmir, which is the third largest city of Türkiye, was selected for landslide susceptibility assessment using geographical information systems (GIS) and remote sensing (RS) techniques. The aim of this study is to create a better landslide susceptibility map (LSM) for the Izmir metropolitan area and its surroundings by minimizing the shortcomings of some of the commonly used methods. For this purpose, four different LSMs were prepared using the logistic regression (LR), analytical hierarchy process (AHP), frequency ratio (FR) and index of entropy (IOE) methods with susceptibility classes ranging from extremely low to extremely high. These four maps were then overlaid. The highest susceptibility class was chosen for each pixel to form a combined landslide susceptibility map (CLSM). The final CLSM is a thematic map presenting landslide susceptibility using five different classes. The geo-environmental factors selected for use in this analysis were slope angle, slope aspect, lithology, slope curvature, elevation, density of discontinuity, stream power index (SPI), land use and distance from stream. Finally, the areas under receiver-operating characteristic (ROC) curves were employed to compare the predictive capability of the five models used. Overall, the Combined Method (CM) (AUC = 0.887) performed very well for landslide susceptibility assessment. Out of all the models, the IOE model (AUC = 0.841) had a slightly lower predictive capability than the CM model, and AHP (AUC = 0.816) was better than FR (AUC = 0.738) and LR (AUC = 0.727). It was observed that, compared to rural areas, residential areas of Izmir city are particularly susceptible to landslides.

Novel ensemble of deep learning neural network and support vector machine for landslide susceptibility mapping in Tehri region, Garhwal Himalaya

Over the years, landslide has become one of the most destructive events that can happen in hilly areas. Tehri, a region in the Himalayas is no different. Current research aids in the construction of ensemble models of DLNN and SVM, which are then compared with various SVM kernels. Landslide susceptibility mapping in the Tehri region of the Himalayas has been worked upon using a deep learning (DLNN), four machine learnings (SVM-RBF, SVM-Linear, SVM-Polynomial, SVM-Sigmoid), and their novel ensembles i.e., DLNN with SVM-RBF, DLNN with SVM-Linear, DLNN with SVM-Polynomial and DLNN with SVM-Sigmoid. 16 geo-environmental landslide conditioning factors (LCFs) have been considered. These models were trained using 70% of inventory landslides and tested using 30% of the same. The results revealed the superiority of DLNN, DLNN-SVM (RBF), DLNN-SVM (Linear) models which quantified 28.32, 26.96 and 22.41% of the area highly susceptible for landslide, respectively.

Erbil Basin Groundwater Recharge Potential Zone Determination Using Fuzzy-Analytical Hierarchy Process (AHP) in North Iraq

Severe water scarcity has occurred in the Erbil Basin (EB) due to climate change and mismanagement of water resources during the past three decades. Assessment of the potential area of groundwater recharge is extremely significant for the protection and management of groundwater systems and water quality. This research aims to use the Fuzzy-Analytic Hierarchy Process (F-AHP) technique to recharge the aquifer in places in the EB that are likely to be groundwater recharge areas in a geographic information system (GIS) environment. GIS, remote sensing (RS), and F-AHP techniques were used to map the groundwater recharge potential zone in EB. Eight different geo-environmental factors were used to determine potential groundwater areas, namely: rainfall, lithology, geology, soil, slope, lineament density, land use/land cover (LULC), and drainage density (Dd). Then, the weights of the different thematic layers were assigned using a pairwise comparison matrix through the F-AHP. The total groundwater potential zone was shown to cover a very high area of 210.85 square kilometers (km2), a high area of 188.94 km2, a moderate area of 573.06 km2, a low area of 1956.48 km2, and a very low area of 216.34 km2, according to the groundwater recharge potential zones (GWRPZs) map. As a result, nearly one-third of the areas investigated were found to have moderate-to-very high groundwater recharge potential. This type of research can provide decision-makers and local governments with a broad perspective on current and future planning for groundwater scarcity.

Regional distribution and characteristics of major badland landscapes in Turkey

Badlands are extremely rugged, outstanding landscapes that can be seen in all ice-free climate regions over erosion-susceptible unconsolidated materials, and they have drawn attention with their spectacular and iconic forms. Unlike nearly all badlands researches conducted at the experimental site and watershed scale, so far, the broader-scale evaluation has been neglected in the analysis of badland distribution, characteristics, and dynamics. Our study provides an integrative new insight into badland landscapes by investigating the distribution, characteristics and controlling factors of Turkish badlands on a broad, regional scale. We inventoried Turkish badlands using aerial imagery and studied their distribution using K-means clustering, an unsupervised machine learning algorithm, based on a set of major conditional geo-environmental factors that control the regional distribution and characteristics of badlands, including tectonics, lithology, topography, climate, and vegetation. Here, we identified, a total of 4494 km2 of badland areas which are non-uniformly distributed across Turkey, substantially clustered in the Central Anatolian Plateau (CAP). According to our regional analyses, we have determined a total of five badland regions comprising three major types classified as Semi-arid, Mediterranean, and Montane (humid), together with two transitional types in-between the Semi-arid and Montane badland regions. Our results indicate that temperature seasonality (0.83), mean annual precipitation (0.83), and precipitation seasonality (0.76) are predominantly assigned to the badlands clusters. The clastic rocks are revealed as the most crucial and inevitable factor for the development of Turkish badlands, which are represented in a wide geologic time-scale (Cretaceous to Quaternary) and diverse lithological units (i.e., lacustrine, volcaniclastics, and terrestrial). Neogene and Paleogene terrestrial clastics (77 %) constitute the majority of the lithologic settings of these badland landscapes. The active and complex tectonic history of Turkey has portrayed the fundamental frame of the identified badland regions, by providing a susceptible environment (i.e., development of sedimentary basins) and promoting badland development through successive base-level changes. Furthermore, tectonically-modulated (i.e., formation of orogenic belts, and uplifting of CAP) climate dynamics outline the distribution pattern and differentiation of the regional characteristics of badlands in Turkey. Overall, our regional-scale approach to badland mapping and regional synthesis may decipher not only the tectonic and climatic conditions of the identified badlands regions, but it may also contribute to the implementation of future effective strategies for the detection and mapping of erosion susceptible and high sediment flux areas in very broad spatial contexts of similar unexplored territories.

Spatial variability of soil water erosion: Comparing empirical and intelligent techniques

Soil water erosion (SWE) is an important global hazard that affects food availability through soil degradation, a reduction in crop yield, and agricultural land abandonment. A map of soil erosion susceptibility is a first and vital step in land management and soil conservation. Several machine learning (ML) algorithms optimized using the Grey Wolf Optimizer (GWO) metaheuristic algorithm can be used to accurately map SWE susceptibility. These optimized algorithms include Convolutional Neural Networks (CNN and CNN-GWO), Support Vector Machine (SVM and SVM-GWO), and Group Method of Data Handling (GMDH and GMDH-GWO). Results obtained using these algorithms can be compared with the well-known Revised Universal Soil Loss Equation (RUSLE) empirical model and Extreme Gradient Boosting (XGBoost) ML tree-based models. We apply these methods together with the frequency ratio (FR) model and the Information Gain Ratio (IGR) to determine the relationship between historical SWE data and controlling geo-environmental factors at 116 sites in the Noor-Rood watershed in northern Iran. Fourteen SWE geo-environmental factors are classified in topographical, hydro-climatic, land cover, and geological groups. We next divided the SWE sites into two datasets, one for model training (70% of the samples = 81 locations) and the other for model validation (30% of the samples = 35 locations). Finally the model-generated maps were evaluated using the Area under the Receiver Operating Characteristic (AU-ROC) curve. Our results show that elevation and rainfall erosivity have the greatest influence on SWE, while soil texture and hydrology are less important. The CNN-GWO model (AU-ROC = 0.85) outperformed other models, specifically, and in order, SVR-GWO = GMDH-GWO (AUC = 0.82), CNN = GMDH (AUC = 0.81), SVR = XGBoost (AUC = 0.80), and RULSE. Based on the RUSLE model, soil loss in the Noor-Rood watershed ranges from 0 to 2644 t ha–1yr−1.

A novel method using explainable artificial intelligence (XAI)-based Shapley Additive Explanations for spatial landslide prediction using Time-Series SAR dataset

As artificial intelligence (AI) techniques are becoming more popular in landslide modeling, it is important to understand how decisions are made. Fairness, and transparency becomes ever more vital due to ethical concerns and trust. Despite the popularity of machine learning (ML) algorithms in landslide modeling, the explainability of these methods are often considered as black box. This paper aims to propose an explainable artificial intelligence (XAI) for landslide prediction using synthetic-aperture radar (SAR) time-series data, NDVI (normalized difference vegetation index) time-series data and other geo-environmental factors such as DEM (digital elevation model) derivatives. We employed a Shapley Additive Explanations (SHAP) approach to understand how and what decisions ML-based models are making. 37 features were extracted from various sources such as ALOS-PALSAR (ALOS Phased Array type l-band Synthetic Aperture Radar), ALOS-2 (SAR), Landsat-8, topographic maps, and DEM for landslide susceptibility mapping in a landslide prone area in Chukha, Bhutan as a test site. The result was then compared using two standard ML methods: random forest (RF) and support vector machine (SVM). As per results, the RF model outperformed (0.914) the SVM. Moreover, the higher reliability of the RF model was proved by the area under the curve (AUC) of 0.941. XAI results revealed, features like altitude, aspect, NDVI-2014, NDVI-2017, and NDVI-2018 were the most effective features for landslide prediction by both models. Interestingly, among those features, NDVI-2014, aspect, and NDVI-2017 negatively correlated with the landslide prediction; whereas positively correlated when SVM was utilized. This interpretation ability indicates the advantages of XAI over the conventional methods as it measures the impact, interaction and correlation of conditioning factors within a model. The current research finding can provide more transparency and explainability when working with MLs in landslide studies. This could help to build trust among the geoscientists and decision-makers while making geohazard prediction.

A study on adsorption of anionic surfactant from water during riverbank filtration

Riverbank filtration (RBF) is a low-cost and environmentally friendly alternative to advanced treatment technologies for pre-treatment or removal of various synthetic organic micro-pollutants from surface water. Through laboratory-scale batch tests employing aquifer soil with varying fine content and particle size, the removal of Linear Alkylbenzene Sulfonate (LAS) from river water during riverbank filtration (RBF) was investigated to determine its adsorption behavior. In addition to it, the effect of adsorbent dosage (3–60 g/L), adsorbate conc. (2–60 mg/L), contact time (10–240 min), agitation speed (80–200 rpm), and pH (2 to 10) on the adsorption for nine types of aquifer soil were studied in batch experiments. The optimal conditions for maximum rate of LAS adsorption on aquifer soil were found to be as initial LAS conc. of 15 mg/L, pH at 7, contact time of 150 min, agitation speed at 160 rpm and adsorbent dosage of 15 g/L respectively. The removal efficiency of LAS was obtained as 88.9% for aquifer soil with 15% fine content and 86.3% for fine sand at an adsorbent dose of 15 g/L, initial LAS conc. of 15 mg/l, neutral pH, agitation speed of 160 rpm, and contact time of 150 mins. Equilibrium data were fitted to Langmuir and Freundlich isotherms, and Langmuir isotherm (R2 = 0.99) was revealed to be the best fit of these models. From multiple linear regression, the LAS removal by soil samples was found to be strongly associated with all five geo-environmental factors (R2 = 0.91). So during the design of the RBF system, suitable contact time or travel time should be maintained in addition to the selection of proper aquifer site conditions for the RBF.

Assessing the effectiveness of alternative landslide partitioning in machine learning methods for landslide prediction in the complex Himalayan terrain

Several devastating landslides have occurred in the NW Himalayas, which has prompted several researchers to strive for improvement in landslide susceptibility modelling (LSM) methodologies. This research analyzes the effectiveness of alternative landslide partitioning techniques on LSM in the landslide-prone district, Muzaffarabad, Pakistan. We developed a landslide inventory of 961 landslides and then traditionally divided it into training (672; 70%) and testing (289; 30%) samples. These training samples (672) are processed by the Average Nearest Neighbour Index (ANNI) method to estimate the spatial pattern of landslides in nature. The results provide an ANNI ratio of 0.672 confirming that the landslides distribution pattern is cluster in the complex Himalayan terrain of Muzaffarabad. Among 672, the majority of landslides (529; 79%) depict cluster behaviour, while 189 landslides (21%) depict random behaviour. To evaluate the effectiveness of landslide cluster samples in prediction, five machine learning algorithms (MLAs), that is, K-Nearest Neighbour (KNN), Naïve Bayes (NB), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Logistic Regression (LR) using proposed cluster (529) and traditional (672) random training samples along with 17 geo-environmental factors are executed. However, testing samples (289; 30%) separated at the initial stage remained the same to check the model’s effectiveness. The areas under the curve (AUC-ROC), sensitivity, specificity, Kappa index and accuracy (ACC) have been used to evaluate the MLA’s performances. An alternative partitioning technique (cluster) shows the highest predictive power with AUC-ROC values ranging from 0.96 to 0.86, Kappa index ranges from 0.76 to 0.60 and ACC ranges from 0.90 to 0.83. Conversely, the random partitioning approach performs less well with AUC-ROC values ranging from 0.95 to 0.83, Kappa index ranges from 0.70 to 0.49 and ACC ranges from 0.87 to 0.80. In comparison, the RF cluster sampling-based model outperforms the other models and their counterparts. The RF model achieved the highest accuracy (0.902), highest AUC (0.962) and highest Kappa index (0.755) followed by XGboost having ACC (0.885), AUC (0.95) and Kappa index (0.724) employing proposed cluster training samples. However, traditional random training samples yield comparatively low ACC of RF (0.868) and XGboost (0.862). These results confirm that cluster training sampling performs well in obtaining reliable and precise LSMs for complex Himalayan terrain. Although random landslide partitioning for training datasets is seldom utilized in LSM, this study highlights that cluster partitioning for landslide training datasets might be a realistic and reliable approach.