Topographic Roughness Index Research Articles

Evaluation of potentially susceptible flooding areas leveraging geospatial technology with multicriteria decision analysis in Edo State, Nigeria

Floods have claimed lives and devastated societal and ecological systems. Because of their catastrophic tendency and the financial and fatalities they cause, floods have become more and more significant on a global scale in recent years. In Edo State, Nigeria, flooding is a frequent threat that happens annually and seriously damages both lives and property. While the potential of flooding cannot entirely be eliminated, geospatial-based technologies can greatly lessen its effects. In Nigeria's flood-prone Edo State, the study's objectives are to identify inundated places and provide nuanced mapping of the flood risk. To facilitate the determination of the flood risk index (FRI), the study's fundamental flood-predictive features were determined by taking into consideration elevation, slope, distance from the river, rainfall intensity, land use/land cover, soil texture, topographic roughness index, topographic wetness index, normalized difference vegetation index (NDVI), runoff coefficient, aspect, drainage capacity, flow accumulation, the sediment transport index, and the stream power index. The significance of each predictive factor in the analytic hierarchy procedure (AHP) was determined by gathering expert views and perspectives from public entities. A flood threat map was created by processing the gathered data using the AHP and the ArcGIS 10.5 framework. The multicollinearity (MC) estimation was applied to assess the model's predictability. The results of the FRI showed that there were high and extremely severe flood risk zones that affected roughly 26 and 9% of the area, respectively. Flood risks have been identified as predominant in the Edo south region of the study area, which is characterized by low elevation and slope, high drainage capacity, distance from the river, topographic wetness, and index. It showed that the model's resultant vulnerability to flooding maps agreed with past flood occurrences that were previously experienced in the research area, demonstrating the technique's efficacy in locating and mapping locations plagued by flooding. Linear regression (R2) analysis was further conducted on the FRI to evaluate the scientific reliability of the utilized methodology; this shows 0.816 (81.6%) dependability. Consequently, frequent and long-lasting implementation of flooding predictions, warning systems, and mitigation strategies may be achieved.

Precipitation seasonality determines the potential distribution of Hyaena hyaena in Saudi Arabia: Towards conservation planning

Hyaena hyaena is a carnivorous mammal that inhabits a broad variety of habitat types and ecological niches, H. hyaena spread in the Arabian Peninsula excluding Rub Al Khali and the desert of Nafud. In Saudi Arabia, it can be found commonly in the western mountains and the open land near agricultural areas such as valleys and lava fields (Harat). However, the H. hyaena is considered to be globally “Near Threatened” (NC) according to (IUCN) Red List as a consequence of a drop in carrion as a result of a reduction in the population of big predators and their prey, eradication practices, and fragmentation and loss of their habitat. The current study seeks to evaluate the distribution of H. hyaena in Saudi Arabia in relation to a number of environmental parameters, as well as assess the possible appropriateness of different habitats for it under climate change scenarios, and provide significant insights for future conservation strategies. The species distribution models (SDMs) tools were employed to map and monitor the distribution of H. hyaena, and then provide a prediction of species distribution patterns. Multicollinearity analysis of the total 19 bioclimatic variables and topographic roughness index resulted in seven uncorrelated variables with VIF < 5, which had been used in the ensemble modeling. The result of our study showed that the decrease in seasonal precipitation will lead to a decrease in the probability of the presence of H. hyaena in Saudi Arabia and The probability of finding H. hyaena in Saudi Arabia decreases as the driest quarter and wettest quarter mean temperature decreases.

Investigating the Role of the Key Conditioning Factors in Flood Susceptibility Mapping Through Machine Learning Approaches

This study harnessed the formidable predictive capabilities of three state-of-the-art machine learning models—extreme gradient boosting (XGB), random forest (RF), and CatBoost (CB)—applying them to meticulously curated datasets of topographical, geological, and environmental parameters; the goal was to investigate the intricacies of flood susceptibility within the arid riverbeds of Wilayat As-Suwayq, which is situated in the Sultanate of Oman. The results underscored the exceptional discrimination prowess of XGB and CB, boasting impressive area under curve (AUC) scores of 0.98 and 0.91, respectively, during the testing phase. RF, a stalwart contender, performed commendably with an AUC of 0.90. Notably, the investigation revealed that certain key variables, including curvature, elevation, slope, stream power index (SPI), topographic wetness index (TWI), topographic roughness index (TRI), and normalised difference vegetation index (NDVI), were critical in achieving an accurate delineation of flood-prone locales. In contrast, ancillary factors, such as annual precipitation, drainage density, proximity to transportation networks, soil composition, and geological attributes, though non-negligible, exerted a relatively lesser influence on flood susceptibility. This empirical validation was further corroborated by the robust consensus of the XGB, RF and CB models. By amalgamating advanced deep learning techniques with the precision of geographical information systems (GIS) and rich troves of remote-sensing data, the study can be seen as a pioneering endeavour in the realm of flood analysis and cartographic representation within semiarid fluvial landscapes. The findings advance our comprehension of flood vulnerability dynamics and provide indispensable insights for the development of proactive mitigation strategies in regions that are susceptible to hydrological perils.

Application of advanced machine learning algorithms and geospatial techniques for groundwater potential zone mapping in Gambela Plain, Ethiopia

Abstract Groundwater availability is one of the key anxieties in most semi-arid regions of Ethiopia. The purpose of this study was to investigate the groundwater potential zone map of the alluvial plain of Gambela. The study applied analytic hierarchy process (AHP) models with four different machine learning algorithms: random forest classifier (RFC), gradient boosting classifier (GBC), decision tree classifier (DTC), and K-neighbor classifier (KNC). The features that are used as predictors include geology, geomorphology, slope, soil, lineament density, drainage density, land use and land cover (LULC), normalized difference vegetation index (NDVI), topographic wetness index (TWI), topographic roughness index (TRI), and rainfall. The final output of the groundwater potential zone was classified as low, moderate, high, and very high potential zones. The authentication through receiver operating curve (ROC) shows 78.2, 93.4, 92.5, 72.4, and 87.7% values of area under the curve (AUC) for AHP, RFC, GBC, DTC, and KNC, respectively. The results show that RFC and GBC are the best groundwater potential zone (GWPZ) map estimator. The study also shows that rainfall and geomorphology are the primary factors influencing the GWPZ. The outcome might promote improved management alternatives in other areas of the country with a comparable climate.

Identification of groundwater potential zones of Idukki district using remote sensing and GIS-based machine-learning approach

Abstract Kerala's Idukki district, which is situated on the Western Ghats of India, is susceptible to flooding and landslides. As a result of the 2018 Kerala floods, this disaster-prone region experienced drought conditions. In order to lessen the effects of future disasters, it is also necessary to identify and evaluate the district's groundwater potential (GWP). This work used three machine-learning (ML) algorithms – Random Forest (RF), Adaptive Boosting (AdaBoost), and Gradient Boosting (GB) – to model and produce GWP zonation maps for the Idukki district. Fourteen conditioning factors including elevation, slope, curvature, Topographic Roughness Index, lineament density, soil, geology, geomorphology, Topographic Wetness Index, Sediment Transport Index, drainage density, rainfall, land-use/land-cover (LULC), and Normalised Difference Vegetation Index were adopted as input parameters in the modelling. All showed prominence when they were examined for feature importance using the recursive feature elimination (RFE) method. The RF model outperformed the other two ML models in terms of fit, with an area under curve (AUC) value of 0.92, while the GB and AdaBoost models displayed less fit, with AUC values of 0.90 and 0.88, respectively. GWP maps produced by each model were reclassified into five zones – very high to very low – it was discovered that the zones were evenly spread throughout the Idukki region.

Mapping of Flood-Prone Areas Utilizing GIS Techniques and Remote Sensing: A Case Study of Duhok, Kurdistan Region of Iraq

One of the most common types of natural disaster, floods can happen anywhere on Earth, except in the polar regions. The severity of the damage caused by flooding can be reduced by putting proper management and protocols into place. Using remote sensing and a geospatial methodology, this study attempts to identify flood-vulnerable areas of the central district of Duhok, Iraq. The analytical hierarchy process (AHP) technique was used to give relative weights to 12 contributing parameters, including elevation, slope, distance from the river, rainfall, land use land cover, soil, lithology, topographic roughness index, topographic wetness index, aspect, the sediment transport index, and the stream power index in order to calculate the Flood Hazard Index (FHI). The relative importance of each criterion was revealed by a sensitivity analysis of the parameter values. This research developed a final flood susceptibility map and identified high-susceptible zones. This was classified anywhere from very low to very high classifications for its potential flood hazard. The generated map indicates that 44.72 km2 of the total land area of the study area in Duhok city has a very high susceptibility to flooding, and that these areas require significant attention from government authorities in order to reduce flood vulnerability.

Identification of groundwater potential sites in the drought-prone area using geospatial techniques at Fafen-Jerer sub-basin, Ethiopia

ABSTRACT Analyzing the groundwater potential zone is a fundamental first step in investigating groundwater resources in arid and semi-arid regions. This study examined the groundwater potential zone of the Fafen-Jerer sub-basin by applying geographic information system (GIS) and remote sensing (RS). The study used ten influencing factors, including geology, geomorphology, slope, soil, lineament density, drainage density, land use, land cover, topographic wetness index, topographic roughness index, and rainfall, to identify potential sites. Based on their effect on groundwater recharge, the sub-class of each influencing factor was identified and evaluated. The weights were determined using the multi-criteria decision-making method’s analytical hierarchy process technique. At the conclusion of the investigation, the region was divided into four potential zones: low, moderate, high, and extremely high. The study region comprises 84% moderate potential zones, 14% high groundwater potential zones, and 2% low and extremely high potential zones. area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to evaluate the groundwater potential zone, and the findings show extremely good performance (AUC = 0.87). The study provides recommendations for stakeholders and water management professionals to develop a strategy for water resource management based on the conjunctive use of surface and groundwater.

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.

Remote sensing and GIS-based landslide susceptibility mapping using frequency ratio method in Sikkim Himalaya

Sikkim Himalaya is located in the North-Eastern Himalaya and is prone to landslides caused by rainfall, anthropogenic factors, earthquakes, and other natural disasters. This study aims to identify landslide susceptibility map for the Sikkim Himalaya, India, utilizing an integrated methodology of Geographic Information System (GIS), Remote Sensing (RS), and the Frequency Ratio (FR) method. Identification of landslide susceptibility map in this region has used multiple datasets as rainfall, earthquake's magnitude, slope angle, altitude, distance to drainages, topographic roughness index, geomorphology, geology, soil, gravity anomaly, distance to faults, stream transportation index, topographic witness index, stream power index, distance to roads, LULC, and NDVI. All the above-mentioned factor/thematic layers were generated using remotely sensed as well as ground data with the help of Arc GIS software. Therefore, the weights of these all-thematic layers were calculated using the FR model for the occurrence of landslides prone in the area. After that, calculated weights of all factor/thematic layers were integrated with Arc GIS software to generate a landslide susceptibility map. The landslide susceptibility zone of the study area has been divided into 5 different classes, namely ‘Very High (11.88%)’, ‘High (15.75%)’, ‘Medium (25.88%)’, ‘Low (25.30%)’, and ‘Very Low (21.19%)’. The accuracy assessment of the study area was 87.8%, which was done by the Receiver Operating Characteristic (ROC) curve method. This research investigates the possibility of using broader approaches to determine landslide-prone areas.

Flood Susceptibility Mapping Using an Analytic Hierarchy Process Model Based on Remote Sensing and GIS Approaches in Akre District, Kurdistan Region, Iraq

In recent decades, floods have been the most common, complex, and destructive natural calamities worldwide. Hence, for inclusive flood risk assessment, creating flood susceptibility mapping to demarcate flood-vulnerable zones is fundamental for decision makers. To assess flood-prone locations in the Akre, Iraqi Kurdistan Region, fundamental for susceptibility mapping was undertaken using geographic information systems, remote sensing, and an analytic hierarchy process model. To assess flood susceptibility, the geographic information systems framework used 15 ideal causative factors for flooding: altitude, slope, distance to streams, flow accumulation, drainage density, rainfall, soil type, lithology, curvature, topographic wetness index (TWI), topographic roughness index stream power index, stream transport index, land use/land cover, and normalized difference vegetation index. The factors contributing to flooding were optimally weighted with respect to the proposed model. The final flood susceptibility map was reclassified into five different classes of susceptibility to flooding: very low (16.64% of the study area); low (19.53%); moderate (38.92%); high (17.83%); and very high (7.08%). The area under curve values for the predicted rate and success rate of the AHP model were 0.956 and 0.971, respectively. Therefore, the results were accurate and reliable. The AHP model is a powerful method for fundamental for susceptibility mapping to mitigate the serious impacts of flooding and assist scholars, local governments and policymakers in future master planning.

A comparison of multiple methods for mapping groundwater levels in the Mu Us Sandy Land, China

Study regionMu Us Sandy Land, China. Study focusThe groundwater table in unconfined aquifers is often a subdued replica of the topography or land surface. In hilly terrain, spatial interpolation methods are prone to errors such as higher interpolation water level than the ground surface due to sparse observation wells. Meanwhile, in ridge areas, groundwater depth can easily be overestimated with limited groundwater observations. To address these issues, this paper proposes a framework to learn groundwater depth using related groundwater variables based on the extreme gradient boosting (XGB) machine learning method. Moreover, the groundwater level map is drawn based on the predicted groundwater depths and elevation data.New Hydrological Insights for the RegionThe results obtained by the XGB algorithm are compared with those of common interpolation methods (including inverse distance weighting, ordinary kriging, and collaborative ordinary kriging) and machine learning methods (including multiple linear regression, geographically weighted regression, support vector regression, and random forest). The results showed that the XGB using the Tweedie loss function performs best in learning groundwater depth compared with interpolation methods and other machine learning methods, and almost completely overcomes the effects of imbalanced data. The topographic factors such as elevation, topographic position index, and topographic roughness index are key factors for groundwater depth. This study provides a reference for improving regional GL mapping, especially in areas of complex terrain.

An Integrated Approach of Machine Learning, Remote Sensing, and GIS Data for the Landslide Susceptibility Mapping

Landslides triggered in mountainous areas can have catastrophic consequences, threaten human life, and cause billions of dollars in economic losses. Hence, it is imperative to map the areas susceptible to landslides to minimize their risk. Around Abbottabad, a large city in northern Pakistan, a large number of landslides can be found. This study aimed to map the landslide susceptibility over these regions in Pakistan by using three Machine Learning (ML) techniques, specifically Linear Regression (LiR), Logistic Regression (LoR), and Support Vector Machine (SVM). Several influencing factors were used to identify the potential landslide areas, including elevation, slope degree, slope aspect, general curvature, plan curvature, profile curvature, landcover classification system, Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), soil, lithology, fault density, topographic roughness index, and road density. The weights of these factors were calculated using ML techniques. The weightage overlay tool is adopted to map the final output. According to three ML models, lithology, NDWI, slope, and LCCS significantly impact landslide occurrence. The area under the ROC curve (AUC) is applied to validate the performance of models, and the results show the AUC value of LiR (88%) is better than SVM (86%) and LoR (85%) models. ML models and final susceptibility map gives good accuracy, which can be reliable for the results. The study’s outcome provides baselines for policymakers to propose adequate protection and mitigation measures against the landslides in the region, and any other researcher can adopt this methodology to map the landslide susceptibility in another area having similar characteristics.

A liquefaction occurrence model for regional analysis

Liquefaction causes damage and economic losses that can exceed the impact caused by ground shaking in earthquakes. However, probabilistic models to predict liquefaction occurrence on a regional scale are scarce and uncertain. We developed a non-parametric model using a database with more than 40 events worldwide. We trained and tested a supervised machine-learning model to predict liquefaction occurrence and non-occurrence, using a well-established methodology to select the optimal explanatory variables that correlate best with liquefaction occurrence. The optimal variables include strain proxy, slope, topographic roughness index, water-table depth, average precipitation, and distance to the closest water body. We compared the proposed model with existing proposals from the literature using the area under the Receiver Operating Characteristic (ROC) curve and the Brier score. Lastly, we apply the proposed model to assess liquefaction occurrence for one historical event and two hypothetical scenarios in Montenegro and Albania.

Assessing the importance of conditioning factor selection in landslide susceptibility for the province of Belluno (region of Veneto, northeastern Italy)

Abstract. In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important, as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (frequency ratio and evidence belief function) and two machine learning (ML) models (random forest and XGBoost; eXtreme Gradient Boosting) for LSM in the province of Belluno (region of Veneto, northeastern Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least “important” features by using a common threshold of 0.30 for statistical and 0.03 for ML algorithms. Conclusively, we found that removing the least important features does not impact the overall accuracy of LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least important ones, namely the aspect plan and profile curvature, topographic wetness index (TWI), topographic roughness index (TRI), and normalized difference vegetation index (NDVI) in the case of the statistical model and the plan and profile curvature, TWI, and topographic position index (TPI) for ML algorithms. This confirms that the requirement for the important conditioning factor maps can be assessed based on the physiography of the region.

Landslide Susceptibility Mapping Using Bivariate Statistical Models and GIS in Chattagram District, Bangladesh

Landslide is one of the most devastating hazards in Chattagram Dsitrict and has become a recurrent phenomenon in this region. This study attempts to produce Landslide Susceptibility Map (LSM) for Chattagram District of Bangladesh by using five GIS based bivariate statistical models, namely the Frequency Ratio (FR), Shanon’s Entropy (SE), Weight of Evidence (WofE), Information Value (IV) and Certainty Factor (CF). Landslide Inventory (2001–2017) of Chittagong Hilly Areas database was used to measure the relationship between the previous landslides with the landslide conditioning factors. SRTM DEM and Landsat satellite images were collected from USGS and the geological data were collected from GSB to produce the thematic layer of conditioning factors. Sixteen landslide conditioning factors of Slope Aspect, Slope Angle, Geology, Elevation, Plan Curvature, Profile Curvature, General Curvature, Topographic Wetness Index, Stream Power Index, Sediment Transport Index, Topographic Roughness Index, Distance to Stream, Distance to Anticline, Distance to Fault, Distance to Road and NDVI were used. The Area Under Curve (AUC) was used for validation of the LSMs. The predictive rate of AUC for FR, SE, WofE, IV and CF were 76.11%, 70.11%, 78.93%, 76.57% and 80.43% respectively. CF model indicates 15.04% of areas are highly susceptible to landslide. All the models showed that the high elevated areas are more susceptible to landslide where the low-lying river basin areas have a low probability of landslide occurrence. The findings of this research will contribute to land use planning, management and hazard mitigation of the CHT region.

Slide type landslide susceptibility assessment of the Büyük Menderes watershed using artificial neural network method.

The Büyük Menderes watershed is the largest drainage watershed in Western Anatolia with an area of approximately 26,000km2. In the study area, almost 863 landslides occurred, extending over 222km2 with a mean landslide area of 0.21km2. In this study, landslide susceptibility assessments were carried out using artificial neural network method, which is one of the data-driven methods. In this study, that will contribute to the mitigation or control of the landslides caused by the reasons controlling the spatial and temporal distribution of landslides created in the GIS and MATLAB environment by using scientific and technological approaches within the framework. Since derivative activation function is also used in back-propagation artificial neural networks, its derivative is easily calculated in order not to slow down the calculation. Levenberg-Marquardt back-propagation (LM), resilient back propagation back-propagation (trainrp), scaled conjugate gradient back-propagation (trainscg), conjugate gradient with Powell/Beale restarts back-propagation (traincgb), and Fletcher-Powell conjugate gradient back-propagation (traincgf) algorithms are used, which constantly interrogate the link between the input parameter and the result output, and at least one cell's output is given as an input to any other cell. Geology, digital elevation model, slope, topographic wetness index, roughness index, plan, profile curvatures, and proximity to active faults and rivers were used as landslide conditioning factors. In susceptibility assessments, landslides were separated by 70% analysis, 15% test, and 15% validation datasets by random selection method. The performances of the landslide susceptibility maps were assessed by the area under the ROC curve (AUC), accuracy (ACC), precision, recall, F1 score, Kappa test error histogram, and confusion matrix, respectively. The area under the receiver operating characteristic curves, analysis, testing, validation, landslides, and study areas were found between 0.873 and 0.911. The susceptibility map had a high prediction rate in which high and very high susceptible zones corresponded to 26% of the study area including 82% of the recorded landslides.

Implementation of Remote Sensing and GIS Techniques to Study the Flash Flood Risk at NEOM Mega-City, Saudi Arabia

Southern Red Sea flooding is common. Assessing flood-prone development risks helps decrease life and property threats. It tries to improve flood awareness and advocate property owner steps to lessen risk. DEMs and topography data were analyzed by RS and GIS. Fifth-through seventh-order rivers were studied. Morphometric analysis assessed the area’s flash flood danger. NEOM has 14 catchments. We determined each catchment’s area, perimeter, maximum length, total stream length, minimum and maximum elevations. It also uses remote sensing. It classifies Landsat 8 photos for land use and cover maps. Image categorization involves high-quality Landsat satellite images and secondary data, plus user experience and knowledge. This study used the wetness index, elevation, slope, stream power index, topographic roughness index, normalized difference vegetation index, sediment transport index, stream order, flow accumulation, and geological formation. Analytic hierarchy considered all earlier criteria (AHP). The geometric consistency index GCI (0.15) and the consistency ratio CR (4.3%) are calculated. The study showed five degrees of flooding risk for Wadi Zawhi and four for Wadi Surr, from very high to very low. 9.16% of Wadi Surr is vulnerable to very high flooding, 50% to high flooding, 40% to low flooding, and 0.3% to very low flooding. Wadi Zawhi’s flood risk is 0.23% high, moderate, low, or extremely low. They’re in Wadi Surr and Wadi Zawhi. Flood mapping helps prepare for emergencies. Flood-prone areas should prioritize resilience.

Using Remote Sensing and Machine Learning to Locate Groundwater Discharge to Salmon-Bearing Streams

We hypothesized topographic features alone could be used to locate groundwater discharge, but only where diagnostic topographic signatures could first be identified through the use of limited field observations and geologic data. We built a geodatabase from geologic and topographic data, with the geologic data only covering ~40% of the study area and topographic data derived from airborne LiDAR covering the entire study area. We identified two types of groundwater discharge: shallow hillslope groundwater discharge, commonly manifested as diffuse seeps, and aquifer-outcrop groundwater discharge, commonly manifested as springs. We developed multistep manual procedures that allowed us to accurately predict the locations of both types of groundwater discharge in 93% of cases, though only where geologic data were available. However, field verification suggested that both types of groundwater discharge could be identified by specific combinations of topographic variables alone. We then applied maximum entropy modeling, a machine learning technique, to predict the prevalence of both types of groundwater discharge using six topographic variables: profile curvature range, with a permutation importance of 43.2%, followed by distance to flowlines, elevation, topographic roughness index, flow-weighted slope, and planform curvature, with permutation importance of 20.8%, 18.5%, 15.2%, 1.8%, and 0.5%, respectively. The AUC values for the model were 0.95 for training data and 0.91 for testing data, indicating outstanding model performance.

Flood susceptibility mapping using extremely randomized trees for Assam 2020 floods

The year 2020 proved disastrous for the north eastern state of India, Assam. The state witnessed terrible floods in the midst of the pandemic. The current study aims to better understand the role played by various factors that contributed to the deluge. To this end, the current study undertakes a flood susceptibility mapping using a seldom employed decision tree based ensemble machine learning technique of extremely randomized trees (ERT). The model was trained and tested on a flood inventory superimposed with 14 flood influencing factors, namely slope, elevation, aspect, normalized difference vegetation index (NDVI), topographic wetness index (TWI), slope length, land use, geology, soil type, topographic roughness index (TRI), rainfall, distance from rivers, plan and profile curvature. The model was compared against other mapping techniques and produced an area under the receiver operating characteristic curve (AUC) of 0.901 outperforming others. The generated susceptibility map deduced the presence of low elevation, high rainfall and close proximity to rivers as major factors leading up to the disaster. It prophesizes a very high flood risk for approximately 18.32% of the study area concentrated in the northern and western part of the study region.

The spatial distribution of the woodland communities and their associated environmental drivers in the Golden Gate Highlands National Park, South Africa

The extreme variability in the topography, altitude and climatic conditions in the temperate Grassland Mountains of Southern Africa is associated with the complex mosaic of grassland communities with pockets of woodland patches. Understanding the relationships between plant communities and environmental parameters is essential in biodiversity conservation, especially for current and future climate change predictions. This article focused on the spatial distribution of woodland communities and their associated environmental drivers in the Golden Gate Highlands (GGHNP) National Park in South Africa. A generalized linear model (GLM) assuming a binomial distribution, was used to determine the optimal environmental variables influencing the spatial distribution of the woodland communities. The Coefficient of Variation (CV) was relatively higher for the topographic ruggedness index (68.78%), topographic roughness index (68.03), aspect (60.04%), coarse fragments (37.46%) and the topographic wetness index (31.33) whereas soil pH, bulk density, sandy and clay contents had relatively less variation (2.39%, 3.23%, 7.56% and 8.46% respectively). In determining the optimal number of environmental variables influencing the spatial distribution of woodland communities, roughness index, topographic wetness index, soil coarse fragments, soil organic carbon, soil cation exchange capacity and remote-sensing based vegetation condition index were significant (p 0.05) and positively correlated with the woodland communities. Soil nitrogen, clay content, soil pH, fire and elevation were also significant but negatively correlated with the woodland communities. The area under the curve (AUC) of the receiver operating characteristics (ROC) was 0.81. This was indicative of a Parsimonious Model with explanatory predictive power for determination of optimal environmental variables in vegetation ecology.Conservation implications: The isolated woodland communities are sources of floristic diversity and important biogeographical links between larger forest areas in the wider Drakensberg region. They provide suitable habitats for a larger number of forest species and harbour some of the endemic tree species of South Africa. They also provide watershed protection and other important ecosystem services. Understanding the drivers influencing the spatial distribution and persistence of these woodland communities is therefore key to conservation planning in the area.