Position Index Research Articles

Spatial Prediction of Landslide Susceptibility Using Logistic Regression (LR), Functional Trees (FTs), and Random Subspace Functional Trees (RSFTs) for Pengyang County, China

Landslides pose significant and serious geological threat disasters worldwide, threatening human lives and property; China is particularly susceptible to these disasters. This paper focuses on Pengyang County, which is situated in the Ningxia Hui Autonomous Region of China, an area prone to landslides. This study investigated the application of machine learning techniques for analyzing landslide susceptibility. To construct and validate the model, we initially compiled a landslide inventory comprising 972 historical landslides and an equivalent number of non-landslide sites (Data sourced from the Pengyang County Department of Natural Resources). To ensure an impartial evaluation, both the landslide and non-landslide datasets were randomly divided into two sets using a 70/30 ratio. Next, we extracted 15 landslide conditioning factors, including the slope angle, elevation, profile curvature, plan curvature, slope aspect, TWI (topographic wetness index), TPI (topographic position index), distance to roads and rivers, NDVI (normalized difference vegetation index), rainfall, land use, lithology, SPI (stream power index), and STI (sediment transport index), from the spatial database. Subsequently, a correlation analysis between the conditioning factors and landslide occurrences was conducted using the certainty factor (CF) method. Three landslide models were established by employing logistic regression (LR), functional trees (FTs), and random subspace functional trees (RSFTs) algorithms. The landslide susceptibility map was categorized into five levels: very low, low, medium, high, and very high susceptibility. Finally, the predictive capability of the three algorithms was assessed using the area under the receiver operating characteristic curve (AUC). The better the prediction, the higher the AUC value. The results indicate that all three models are predictive and practical, with only minor discrepancies in accuracy. The integrated model (RSFT) displayed the highest predictive performance, achieving an AUC value of 0.844 for the training dataset and 0.837 for the validation dataset. This was followed by the LR model (0.811 for the training dataset and 0.814 for the validation dataset) and the FT model (0.776 for the training dataset and 0.760 for the validation dataset). The proposed methods and resulting landslide susceptibility map can assist researchers and local authorities in making informed decisions for future geohazard prevention and mitigation. Furthermore, they will prove valuable and be useful for other regions with similar geological characteristics features.

Analysis of the Bottom Topography of the Reservoir Due to Sediment Trapping (According to the Krasnodar Reservoir, Russia)

Morphometric descriptions of reservoirs are usually limited to the type, shape, altitude position, bed size and volume of water in them. The article presents the results of the analysis of the bottom topography of the Krasnodar reservoir and the transformations of this for 2005-2021. The analysis was carried out based on the materials of bathymetric surveys for the usable volume of the reservoir on an area of 224 km2 with the creation of digital elevation models. The topography of the reservoir bottom is represented by flat sections of flooded accumulative plain with prevailing slopes of about 0.2–0.4°, dissected by riverbeds of lower-order tributaries. The transformation of the topography is caused by gradual silting. The total volume of sediments for this area in 2005-2021 amounted to 127 million m3 with an average siltation layer of 0.4 m. To describe the morphological properties of the bottom topography, we used geomorphometry techniques with the calculation of the BPI index (Bathymetric Position Index) and the classification of mesoscale topography forms based on it. For the riverbed, there are topography forms related to three types of surfaces: flat (Lower Bank Shelves), concave (Depressions, Deep Depressions) and convex (Reef Crests, Back Reefs, Mid-Slope Ridges). The constructed maps reflect the differentiated morphology of the bed surface, the evolution of topography forms and the change in roughness under conditions of continuous transformation of the basin and allow judging the prevailing morphogenetic processes. Morphologically, the coastal zone and the shallow part of the riverbed are the most difficult to construct. Here, along with long-shore reef crests of different genesis, deep depressions and simple depressions in the form of underwater channels on the deltas of extension can form on the accumulative shoal.

DNA-GPS: A theoretical framework for optics-free spatial genomics and synthesis of current methods.

While single-cell sequencing technologies provide unprecedented insights into genomic profiles at the cellular level, they lose the spatial context of cells. Over the past decade, diverse spatial transcriptomics and multi-omics technologies have been developed to analyze molecular profiles of tissues. In thisarticle, we categorize current spatial genomics technologies into three classes: optical imaging, positional indexing, and mathematical cartography. We discuss trade-offs in resolution and scale, identify limitations, and highlight synergies between existing single-cell and spatial genomics methods. Further, we propose DNA-GPS (global positioning system), a theoretical framework for large-scale optics-free spatial genomics that combines ideas from mathematical cartography and positional indexing. DNA-GPS has the potential to achieve scalable spatial genomics for multiple measurement modalities, andby eliminating the need for optical measurement, it has the potential to position cells in three-dimensions (3D).

Relationship Between Lightning Activity and Terrain in High-Altitude Mountainous Areas

In China, the average elevation of Yunnan Province exceeds 2000 m, with a greatly fluctuating terrain. Most areas have a high-altitude mountainous terrain and relatively high ground lightning activity. Topography is one of the most critical factors affecting regional lightning characteristics. Therefore, clarifying the quantitative relationship between cloud-to-ground lightning activity and topography can help evaluate the risk of hazard-pregnant environments and adopt active protective measures. In this study, we used a mathematical statistical method to analyze the correlation between cloud-to-ground lightning density and altitude, slope, slope aspect, topographic position index, and land-cover type in Yunnan for the past 10 years. We also used the Apriori algorithm to study the coupling effects of different topographic factors and mine the topographic attribute sets that strongly correlate with high-level lightning activity. We used the entropy weight method to construct a comprehensive index of hazard-pregnant environments and quantitatively evaluate the impact weights of different factors on cloud-to-ground lightning activity. Correlation analysis of lightning density and sensitivity indicated a correlation coefficient of 0.473 between both factors, highlighting the effectiveness of evaluating regional lightning risk with the sensitivity of a hazard-pregnant environment

A dataset of paddy rice planting areas along the Yangtze River (Jiangsu section) in 2020

As a staple food crop in China, paddy rice is one of the most widely grown crops in the country. Thanks to its abundant water resources, the Yangtze River has superiority in paddy rice planting. The prompt and accurate monitoring of paddy rice planting information plays an important role in providing essential technical support to safeguard China's food security. However, there is a scarcity of studies on the extraction of paddy rice planting areas along the Yangtze River using the remote sensing technology. In this paper, guided by paddy rice growth phenology information, we selected the Sentinel-2 satellite imagery that covered the paddy rice growing period (from May to September) along the Yangtze River in 2020. On the basis of high-spatial resolution images combined with field investigation, we obtained the real distribution map of the paddy rice planting area in Menghe Town and selected samples and validation samples from the map. Based on the maximum likelihood, neural network, SVM (Support Vector Machine) and other machine learning methods, we carried out the paddy rice extraction research, compared and analyzed the accuracy of extraction results of NDVI (Normalized Difference Vegetation Index) and REP (Red Edge Position Index) spectral index sets. The results show that the REP index sets of the three time phases in May, August and September are most effectively extracted using the neural network method. The overall accuracy of the results is 92.73%, with a corresponding Kappa coefficient of 0.72. We achieved global applicability by optimizing key parameters such as timing, spectral bands, and classifier methods for paddy rice extraction. Additionally, we conducted post-processing to refine the results. Finally, we obtained a vector dataset of paddy rice growing areas along the Yangtze River (Jiangsu section) in 2020, with an overall classification accuracy of 87.15%. This dataset is expected to provide a reference for further monitoring the paddy rice planting areas and enhancing the accuracy of grain production estimates throughout the Yangtze River region.

Spatiotemporal Variation of Anticyclonic Eddies in the South China Sea during 1993–2019

Based on the absolute dynamic topography data from the Copernicus Marine Environment Monitoring Service, this paper applies the Topographic Position Index to develop a new approach for mapping the anticyclonic eddies in the South China Sea (SCS). The results show that anticyclonic eddies are active in the deep basin of SCS, and the five selected parameters (number or frequency, lifetime, kinetic energy, amplitude, and area or radius) of anticyclonic eddies have a similar temporal variation and a similar spatial distribution pattern. (1) As for monthly variations, anticyclonic eddies are active in late spring and most active in summer. (2) The El Niño–Southern Oscillation had a stronger impact on the inter-annual variations of anticyclonic eddies in the SCS before 2013, resulting in a significant transition of inter-annual variations of these five parameters in around 2004. After 2013, most of these five parameters had a minimum in 2015 and a maximum in 2017. (3) Analyses show that the eddy activities in the SCS are significantly influenced by the monsoon wind and the western boundary current like Kuroshio. Therefore, the areas southwest of Taiwan Island and east of Vietnam are the two areas where the anticyclonic eddies are most active, with much larger eddy kinetic energy and much higher eddy amplitude.

Comparative study of sub-second temporal resolution 4D-MRI and 4D-CT for target motion assessment in a phantom model

To develop and investigate the feasibility of sub-second temporal resolution volumetric T1-weighted four-dimensional (4D-) MRI in comparison with 4D-CT for respiratory-correlated motion assessment using an MRI/CT-compatible phantom. Sub-second high temporal resolution (0.5 s) gradient-echo T1-weighted 4D-MRI was developed using a volumetric acquisition scheme with compressed sensing. An MRI/CT-compatible motion phantom (simulated liver tumor) with three sinusoidal movements of amplitudes and two respiratory patterns was introduced and imaged with 4D-MRI and 4D-CT to investigate the geometric accuracy of the target movement. The geometric accuracy, including centroid position, volume, similarity index of dice similarity coefficient (DSC), and Hausdorff distance (HD), was systematically evaluated. Proposed 4D-MRI achieved a similar geometric accuracy compared with 4D-CT regarding the centroid position, volume, and similarity index. The observed position differences of the absolute average centroid were within 0.08 cm in 4D-MRI and 0.03 cm in 4D-CT, less than the 1-pixel resolution for each modality. The observed volume difference in 4D-MRI/4D-CT was within 0.73 cm3 (4.5%)/0.29 cm3 (2.1%) for a large target and 0.06 cm3 (11.3%)/0.04 cm3 (11.6%) for a small target. The observed DSC values for 4D-MRI/4D-CT were at least 0.93/0.95 for the large target and 0.83/0.84 for the small target. The maximum HD values were 0.25 cm/0.31 cm for the large target and 0.21 cm/0.15 cm for the small target. Although 4D-CT potentially exhibit superior numerical accuracy in phantom studies, the proposed high temporal resolution 4D-MRI demonstrates sub-millimetre geometric accuracy comparable to that of 4D-CT. These findings suggest that the 4D-MRI technique is a viable option for characterizing motion and generating phase-dependent internal target volumes within the realm of radiotherapy.

Determination of Normal Anal Position Using the Anal Position Index in Pakistani Neonates.

Anterior displacement of the anus (ADA) is recognized as a common congenital abnormality of the anorectal region and is often associated with constipation. It is diagnosed through a physical examination by measuring the Anal Position Index (API) at birth. A cross-sectional study was conducted utilizing non-probability consecutive sampling of all patients presenting with ADAat our institute over a six-month period. The study focused on key variables, including the measurement of scroto-anal and scroto-coccygeal distances in boys and fourchette-anal and fourchette-coccygeal distances in girls. Data collection was carried out using a structured proforma, ensuring prospective data collection from neonates meeting the selection criteria (neonates born at our center and identified by the neonatology team as having a normal anal opening, regardless of their gestational period or birthweight). Our study comprised a cohort of 204 neonates. The Anal Position Index was determined to be 0.36 ± 0.07 for male newborns and 0.24 ± 0.06 for female newborns. Notably, a statistically significant correlation was observed between the API and factors such as gestational age, birth weight, and advancing paternal age. The assessment of the API proves highly valuable in identifying indicators of ADA in neonates, facilitating early disease detection, and guiding the prompt management of subsequent functional symptoms, such as constipation, during later stages of life.

Land Use Change and Landscape Ecological Risk Assessment Based on Terrain Gradients in Yuanmou Basin

Investigating the distribution characteristics of landscape ecological risk (LER) on terrain gradients is of great significance for optimizing the landscape pattern of ecologically vulnerable areas in mountainous regions and maintaining the sustainable development of the ecological environment. The Yuanmou Basin is a typical ecologically vulnerable area in the southwestern mountainous region of China, where issues such as soil erosion are pronounced, becoming one of the main factors restricting regional economic development. This study selected the Yuanmou Basin as the study area, and, using land use data from 2000, 2010, and 2020, constructed an LER assessment model based on disturbance and vulnerability. By integrating elevation and topographic position index data, we examined the spatiotemporal evolution characteristics of LER under different terrain gradients. The LER assessment results are summarized as follows: (1) From 2000 to 2020, the land use types of the Yuanmou Basin were mainly grassland, forest land and cropland. The land use showed a sharp increase in the cropland area and a simultaneous decrease in the grassland area, indicating a main land use evolution direction from grassland to cropland. (2) Over the span of 20 years, the average landscape ecological risk in the Yuanmou Basin slightly increased, specifically manifesting as a significant reduction in low ecological risk areas, while areas of medium and slightly lower ecological risks saw an increase. (3) The spatial distribution of LER in the Yuanmou Basin presents a pattern of being low on the periphery and high in the center, with significant positive spatial correlation, obvious spatial aggregation, as well as “high-high” and “low-low” clustering. (4) Low- and lower-risk areas in the Yuanmou Basin are distributed in the non-arid thermal zone and the medium–high terrain zone, while areas of medium, higher and high risk levels are mainly distributed in the arid thermal zone and the low terrain zone. The research results provide a scientific basis for optimizing and developing the land resources of the Yuanmou Basin.

THE EXPLAINABILITY OF GRADIENT-BOOSTED DECISION TREES FOR DIGITAL ELEVATION MODEL (DEM) ERROR PREDICTION

Abstract. Gradient boosted decision trees (GBDTs) have repeatedly outperformed several machine learning and deep learning algorithms in competitive data science. However, the explainability of GBDT predictions especially with earth observation data is still an open issue requiring more focus by researchers. In this study, we investigate the explainability of Bayesian-optimised GBDT algorithms for modelling and prediction of the vertical error in Copernicus GLO-30 digital elevation model (DEM). Three GBDT algorithms are investigated (extreme gradient boosting - XGBoost, light boosting machine – LightGBM, and categorical boosting – CatBoost), and SHapley Additive exPlanations (SHAP) are adopted for the explainability analysis. The assessment sites are selected from urban/industrial and mountainous landscapes in Cape Town, South Africa. Training datasets are comprised of eleven predictor variables which are known influencers of elevation error: elevation, slope, aspect, surface roughness, topographic position index, terrain ruggedness index, terrain surface texture, vector roughness measure, forest cover, bare ground cover, and urban footprints. The target variable (elevation error) was calculated with respect to accurate airborne LiDAR. After model training and testing, the GBDTs were applied for predicting the elevation error at model implementation sites. The SHAP plots showed varying levels of emphasis on the parameters depending on the land cover and terrain. For example, in the urban area, the influence of vector ruggedness measure surpassed that of first-order derivatives such as slope and aspect. Thus, it is recommended that machine learning modelling procedures and workflows incorporate model explainability to ensure robust interpretation and understanding of model predictions by both technical and non-technical users.

Seasonal predictability of summer north african subtropical high in operational climate prediction models

Seasonal predictability of summer North African Subtropical High (NASH) is investigated in this study by utilizing the hindcast data from four operational climate prediction models, including BCC_CSM1.1(m), NCEP CFSv2, ECMWF System 4, and JMA CPSv2. By reconstructing indices describing the variations in intensity, area, eastern boundary and ridge line of the NASH, it is shown that the intensity and area indices present high prediction skills compared to the relatively low prediction skills of position indices. The multi-model ensemble (MME) mean, calculated as the arithmetic average of the four models, presents relatively higher and stabler skills than individual models. Further investigation indicates that the prediction skill of the NASH is largely reliant on the models’ ability in reproducing the relationship between the NASH indices and the tropical-to-subtropical sea surface temperature (SST) anomalies associated with the El Niño/Southern Oscillation (ENSO). The pattern of atmospheric circulation anomaly over the North Africa in response to ENSO is well captured by the models, which suggests the dominant source of predictability of the NASH.

Predictive spatial analysis for a critical assessment of the preservation potential of Palaeolithic record in the Leiria region (central Portugal)

Predictive spatial analysis in archaeology refers to the use of geostatistical and computational techniques to assess the relationships between the distribution of archaeological sites and the environmental context. It is increasingly becoming an essential tool in scientific-academic research and rescue archaeology. In the interconnection between these two working contexts, this study aims to explore the advantages of applying an inductive approach, combining Geographical Information Systems (GIS) and geostatistical methods, to identify areas with different degrees of probability for the preservation of the Palaeolithic record in the lower valley of the Lis River (Leiria region, central Portugal). Topographic, hydrographic, geological, and geomorphological data were collected, processed, and integrated into a spatial database, using a GIS, to define the environmental conditioning factors. After applying a spatial multicollinearity procedure, slope, topographical position index, cost-weighted distance to access the watercourses, heat load index and lithology were chosen as input variables for the predictive modelling. Archaeological data, corresponding to the location of known Palaeolithic sites, were also retrieved from the official records. Three models were implemented using regression and multi-criteria methods; for Model 1 a Generalised Additive Model (GAM) was applied, while for Model 2 and Model 3 two distinct combinations of Probabilistic Frequency Ratio (PFR) and Analytic Hierarchy Process (AHP) were used. The spatial cross-tabulation between the obtained predictive maps and the location of the known Palaeolithic sites shows that all the models are acceptable. However, the combinations of PFR + AHP seem to evidence greater efficacy compared to the GAM. Model 3 offers the best performance (90%), followed by Model 2 (87%) and Model 1 (68%). Possible sources of inaccuracies in the input data and the spatial modelling results were critically discussed. Model 3 generated the most robust and reliable predictive prototype map. The maps produced can serve local and regional agencies as a complement and aid decision-making in public policies for spatial planning, and in the conservation/management of cultural heritage. These cartographic representations can provide quicker identification of areas of interest, for example, in the context of rescue archaeology, along with a substantial reduction in time and costs for project promoters, as well as helping in the environmental impact assessments.

Developing SEP65: A Census-Derived Index of Socio-Economic Position Specifically for the Older Population in Aotearoa New Zealand

BackgroundGlobally, societies are ageing as life expectancy increases and fertility rates decline. Many studies exploring associations between socioeconomic position (SEP) and health outcomes among the older population use conventional working-age measures of SEP (education, occupation, and income) or an area-based deprivation index.MethodsMicrodata from the 2013 New Zealand Census was used to create a new measure of socioeconomic position specifically for the population aged ≥65 years (SEP65), using information about housing tenure, wealth, and receiving government benefits. We dichotomised variables representing income, assets, and housing tenure to apportion 489,264 older people in our analytic sample into low, medium and high levels of SEP. A multivariable logistic regression was used to investigate the relationship between smoking and SEP65, controlling for age, sex, ethnicity and area-level deprivation.ResultsWe report inequities between European, Māori and Pacific populations, which increase with age. We found an inverse relationship between the odds of smoking and levels of SEP65. Moreover, we further validated the SEP65 measure against the New Zealand Index of Deprivation (NZDep2013).At the third SPINE20 summit 2022 which took place in Bali, Indonesia, in August 2022, 17 associations endorsed its recommendations.ConclusionUsing an age-specific measure of SEP for the older population will aid policymakers in the appropriate allocation of resources according to need more effectively than working-age indicators.

Geomorphic factors influencing the spatial distribution of eroded Chernozems in automated digital soil erosion mapping

Among the factors influencing the intensity of soil erosion by water, the relief sets the basic conditions for the occurrence of erosion-sedimentation processes: the geometry of the contact surface with water runoff and its primary spatial characteristics. We developed a model that describes the categories of the intensity of soil erosion by water only by geomorphic parameters using a DEM. The study was conducted in arable soils in the southeastern part of the Central Russian Upland, namely, typical Chernozems (TCh) in the forest-steppe zone and ordinary Chernozems (OCh) of the northern steppe of the temperate climate zone. Based on 1146 ground soil-erosion survey points, the relationship between the category of soil erosion intensity and terrain parameters (slope steepness, slope length and exposure, topographic position index, and slope profile curvature, etc.) was analyzed. The results of the revealed dependencies for the studied soils made it possible to develop prognostic models using ordinal logistic regression with an assessment of their accuracy. It was found that the model for OCh soils shows in all parameters a stronger relationship between geomorphic factors and the category of soil erosion intensity than the model for TCh soils. The regression model for OCh exceeds the model for TCh by 12 % in overall accuracy. For both soils, eroded areas are determined with much less accuracy (50–60 %) than non-eroded areas (80–95 %). Based on the modeling results, maps of soil erosion by water were constructed, where belonging to the category of soil erosion intensity was determined by the maximum probability. It is also shown that soil erosion intensity modeling based only on a set of geomorphic predictors is not inferior in accuracy to the conventional visual-expert cartographic method and can be a more objective and efficient alternative in automated digital soil erosion mapping.

Groth’s algorithm to detect the possible presence of landmines using changes in the reflection of plants

Abstract. Post-conflict reconstruction includes the removal of land mines and remnants of war. The CSIR conducted field experiments to determine the impact of TNT in the soil on plants as a possible means to detect landmines. All the leaf clip readings were done using a spectrometer to determine reflection and absorption of light at one micrometre intervals between 350 to 2500 micrometre. Laboratory analysis such as UPLC qTOF MS indicated that the TNT have an influence on the plants. Several indices such as Modified Red Edge Normalized Difference Vegetation Index (mNDVI705), Red Edge Position (REP) and Moisture Stress Index (MSI) did not show any significant differences between control plants and experimental plants with different TNT concentrations. Groth’s pattern matching algorithm designed to match several photographs of the same part of the universe. A set of triangles using dominant stars are created for each photograph and matched using an error band. If the selected triangles from the two photographs fit within the error band, then they are from the same section of the universe. Bands for the Pléiades instruments were simulated using the data from the spectrometer for each plant. The reflectance value of the band and the normalised midpoint wavelength of each Pléiades band were used to construct the triangles. The control plant triangle is then matched with the experimental plant and if the triangles do not match, then the effect of TNT on the plant is significant. The initial results with the control plants and experimental plants are positive.

Characterization and Analysis of Landslide Evolution in Intramountain Areas in Loja (Ecuador) Using RPAS Photogrammetric Products

This case study focuses on the area of El Plateado near the city of Loja, Ecuador, where landslides with a high impact on infrastructures require monitoring and control. The main objectives of this work are the characterization of the landslide and the monitoring of its kinematics. Four flights were conducted using a remotely piloted aerial vehicle (RPAS) to capture aerial images that were processed with SfM techniques to generate digital elevation models (DEMs) and orthoimages of high resolution (0.05 m) and sufficient accuracy (below 0.05 m) for subsequent analyses. Thus, the DEM of differences (DoD) and profiles are obtained, but a morphometric analysis is conducted to quantitatively characterize the landslide’s elements and study its evolution. Parameters such as slope, aspect, topographic position index (TPI), terrain roughness index (TRI), and topographic wetness index (TWI) are analyzed. The results show a higher slope and roughness for scarps compared to stable areas and other elements. From TPI, slope break lines have been extracted, which allow the identification of landslide features such as scarps and toe tip. The landslide shows important changes in the landslide body surface, the retraction of the main scarp, and advances of the foot. A general decrease in average slope and TRI and an increase in TWI are also observed due to the landslide evolution and stabilization. The presence of fissures and the infiltration of rainfall water in the unsaturated soil layers, which consist of high-plasticity clays and silts, contribute to the instability. Thus, the study provides insights into the measurement accuracy, identification and characterization of landslide elements, morphometric analysis, landslide evolution, and the relationship with geotechnical factors that contribute to a better understanding of landslides. A higher frequency of the RPAS surveys and quality of geotechnical and meteorological data are required to improve the instability analysis together with a major automation of the GIS procedures.

Proposing Optimal Locations for Runoff Harvesting and Water Management Structures in the Hami Qeshan Watershed, Iraq

Iraq, including the investigated watershed, has endured destructive floods and drought due to precipitation variability in recent years. Protecting susceptible areas from flooding and ensuring water supply is essential for maintaining basic human needs, agricultural production, and industry development. Therefore, locating and constructing storage structures is a significant initiative to alleviate flooding and conserve excessive surface water for future growth. This study aims to identify suitable locations for Runoff Harvesting (RH) and dam construction in the Hami Qeshan Watershed (HQW), Slemani Governorate, Iraq. We integrated in situ data, remotely sensed images, and Multi-Criteria Decision Analysis (MCDA) approaches for site selection within the Geographical Information Systems (GIS) environment. A total of ten criteria were employed to generate the RH suitability maps, including topographic position index, lithology, slope, precipitation, soil group, stream width, land cover, elevation, distance to faults, and distance to town/city. The weights of the utilized factors were determined via Weighted Linear Combination (WLC) and Analytic Hierarchy Process (AHP). The resulting RH maps were validated through 16 dam sites preselected by the Ministry of Agriculture and Water Resources (MAWR). Findings showed that the WLC method slightly outperformed AHP regarding efficiency and exhibited a higher overall accuracy. WLC achieved a higher average overall accuracy of 69%; consequently, it was chosen to locate new multipurpose dams for runoff harvesting in the study area. The overall accuracy of the 10 suggested locations in HQW ranged between 66% and 87%. Two of these sites align with the 16 locations MAWR has recommended: sites 2 and 5 in the northwest of HQW. It is noteworthy that all MAWR dam sites were situated in medium to excellent RH zones; however, they mostly sat on ineffective geological localities. It is concluded that a careful selection of the predictive factors and their respective weights is far more critical than the applied methods. This research offers decision-makers a practical and cost-effective tool for screening site suitability in data-scarce rugged terrains.

Using a Decision Tree Approach to Analyze Key Factors Influencing Intraoperative-Acquired Pressure Injury.

To determine the key factors influencing intraoperative-acquired pressure injury (IAPI). Researchers assessed 413 surgical patients in a Shanghai tertiary hospital using an information collection form and an IAPI occurrence record form. Analysis took place using the classification and regression tree algorithm and multiple logistic regression. A total of 43 surgical patients (10.4%) had IAPI, including 32 stage 1 cases (74.4%), and 11 stage 2 cases (25.6%). The multiple logistic regression analysis indicated that operation duration, surgical position, preoperative hypertension, and preoperative Braden Scale risk score were independently associated with IAPI development. The decision tree showed that preoperative Braden Scale score, surgical position, operation grade, operation duration, age, prealbumin level, and body mass index were important factors and that preoperative Braden Scale score was the most critical decision variable. The cross-validation method was used to indicate a model accuracy of 91.8%. The decision tree effectively identified key factors for IAPI, complementing the logistic regression analysis and providing a scientific basis for the further development of structural risk assessment, prevention, and treatment strategies for IAPI.

Comparative Analysis of Tree-Based Ensemble Learning Algorithms for Landslide Susceptibility Mapping: A Case Study in Rize, Turkey

The Eastern Black Sea Region is regarded as the most prone to landslides in Turkey due to its geological, geographical, and climatic characteristics. Landslides in this region inflict both fatalities and significant economic damage. The main objective of this study was to create landslide susceptibility maps (LSMs) using tree-based ensemble learning algorithms for the Ardeşen and Fındıklı districts of Rize Province, which is the second-most-prone province in terms of landslides within the Eastern Black Sea Region, after Trabzon. In the study, Random Forest (RF), Gradient Boosting Machine (GBM), CatBoost, and Extreme Gradient Boosting (XGBoost) were used as tree-based machine learning algorithms. Thus, comparing the prediction performances of these algorithms was established as the second aim of the study. For this purpose, 14 conditioning factors were used to create LMSs. The conditioning factors are: lithology, altitude, land cover, aspect, slope, slope length and steepness factor (LS-factor), plan and profile curvatures, tree cover density, topographic position index, topographic wetness index, distance to drainage, distance to roads, and distance to faults. The total data set, which includes landslide and non-landslide pixels, was split into two parts: training data set (70%) and validation data set (30%). The area under the receiver operating characteristic curve (AUC-ROC) method was used to evaluate the prediction performances of the models. The AUC values showed that the CatBoost (AUC = 0.988) had the highest prediction performance, followed by XGBoost (AUC = 0.987), RF (AUC = 0.985), and GBM (ACU = 0.975) algorithms. Although the AUC values of the models were close to each other, the CatBoost performed slightly better than the other models. These results showed that especially CatBoost and XGBoost models can be used to reduce landslide damages in the study area.

Toward broad-scale mapping and characterization of prairie dog colonies from airborne imagery using deep learning

Monitoring wildlife is fundamental to managing the health of rangelands but challenging due to the extensive and dynamic nature of these ecosystems. The black-tailed prairie dog (Cynomys ludovicianus) is considered both a keystone species of conservation concern and an agricultural pest. This animal is an example of a wildlife species for which detailed monitoring is both high priority and difficult to accomplish cost-effectively using ground-based methods. In this study, we conducted a robust evaluation of the potential to use deep learning to detect prairie dog burrows from remotely sensed imagery acquired from unoccupied aerial systems (UAS). We processed UAS imagery to create RGB, topographic position index (TPI) and normalized difference vegetation index (NDVI) products at varying spatial resolutions (2–30 cm). We then evaluated the minimum set of inputs and image resolution required to train a deep convolutional neural network (CNN) for burrow detection and scale this up to identify entire colonies. We validated results at the scale of individual burrows, sub-colony burrow density and range-wide colony area using ground and digitized observations. We found the 2 cm imagery proved computationally impractical for scaling, but performance did not decline between 2 and 5 cm imagery, and models performed well up to 10–15 cm. The top models always included TPI and the combination of RGB + TPI tended to perform best across spatial resolutions. Adding NDVI generally did not improve model performance. At 5 cm resolution, the top models achieved high precision and recall for detecting individual burrows (F-score 0.84–0.87) and burrow density was strongly correlated with validation data (r = 0.94–0.95). In pastures with active colonies, overlap between predicted and ground delineated colonies was high (60–94%). The CNN-based approach could not distinguish between currently active colonies and a colony that had recently become inactive due to a sylvatic plague (Yersinia pestis) epizootic. However, further analysis showed that CNN-derived burrow density was related to colony age and satellite-derived vegetation conditions in active colonies, and that the plague-affected colony deviated from expected vegetation trends. We conclude that a deep learning algorithm can accurately detect prairie dog burrows from UAS imagery acquired at 5–10 cm resolution, and that scaling from individual burrows to entire colonies is achievable but warrants further research. Combining CNN-derived burrow density maps with satellite-derived vegetation conditions may help identify recent colony abandonment, despite ongoing presence of burrows.