Rainfall-induced landslide susceptibility assessment at the Chongren area (China) using frequency ratio,certainty factor,and index of entropy

The main objective of the study was to evaluate and compare the overall performance of three methods, frequency ratio (FR), certainty factor (CF) and index of entropy (IOE), for rainfall-induced landslide susceptibility mapping at the Chongren area (China) using geographic information system and remote sensing. First, a landslide inventory map for the study area was constructed from field surveys and interpretations of aerial photographs. Second, 15 landslide-related factors such as elevation, slope, aspect, plan curvature, profile curvature, stream power index, sediment transport index, topographic wetness index, distance to faults, distance to rivers, distance to roads, landuse, NDVI, lithology and rainfall were prepared for the landslide susceptibility modelling. Using these data, three landslide susceptibility models were constructed using FR, CF and IOE. Finally, these models were validated and compared using known landslide locations and the receiver operating characteristics curve. The result shows that all the models perform well on both the training and validation data. The area under the curve showed that the goodness-of-fit with the training data is 79.12, 80.34 and 80.42% for FR, CF and IOE whereas the prediction power is 80.14, 81.58 and 81.73%, for FR, CF and IOE, respectively. The result of this study may be useful for local government management and land use planning.     

A four‐dimensional agent‐based model: A case study of forest‐fire smoke propagation

Dynamic geospatial complex systems are inherently four‐dimensional (4D) processes and there is a need for spatio‐temporal models that are capable of realistic representation for improved understanding and analysis. Such systems include changes of geological structures, dune formation, landslides, pollutant propagation, forest fires, and urban densification. However, these phenomena are frequently analyzed and represented with modeling approaches that consider only two spatial dimensions and time. Consequently, the main objectives of this study are to design and develop a modeling framework for 4D agent‐based modeling, and to implement the approach to the 4D case study for forest‐fire smoke propagation. The study area is central and southern British Columbia and the western parts of Alberta, Canada for forest fires that occurred in the summer season of 2017. The simulation results produced realistic spatial patterns of the smoke propagation dynamics.     

Modeling potential forest fire danger using modis data

Generation of fire danger maps play a vital role in forest fire management like forest fire research, locating lookout towers, risk assessment and for various other simulation studies. The present study addresses remote sensing and GIS applications in generating fire danger maps for tropical deciduous forests. Fire danger variables such as fuel type, topography, temperature, and relative humidity have been used in modeling fire danger. Information on local climate patterns and past fire records has been used to derive fire frequency map of the study area. Intermediate indices were derived using multiple regressions, where fire frequency data is taken as dependent variable. Results indicate that forests near human settlements are more vulnerable to forest fires.     

Multi-year MODIS active fire type classification over the Brazilian Tropical Moist Forest Biome

ABSTRACT

The Brazilian Tropical Moist Forest Biome (BTMFB) spans almost 4 million km² and is subject to extensive annual fires that have been categorized into deforestation, maintenance, and forest fire types. Information on fire types is important as they have different atmospheric emissions and ecological impacts. A supervised classification methodology is presented to classify the fire type of MODerate resolution Imaging Spectroradiometer (MODIS) active fire detections using training data defined by consideration of Brazilian government forest monitoring program annual land cover maps, and using predictor variables concerned with fuel flammability, fuel load, fire behavior, fire seasonality, fire annual frequency, proximity to surface transportation, and local temperature. The fire seasonality, local temperature, and fuel flammability were the most influential on the classification. Classified fire type results for all 1.6 million MODIS Terra and Aqua BTMFB active fire detections over eight years (2003–2010) are presented with an overall fire type classification accuracy of 90.9% (kappa 0.824). The fire type user’s and producer’s classification accuracies were respectively 92.4% and 94.4% (maintenance fires), 88.4% and 87.5% (forest fires), and, 88.7% and 75.0% (deforestation fires). The spatial and temporal distribution of the classified fire types are presented and are similar to patterns reported in the available recent literature.     

A comparative study on groundwater spring potential analysis based on statistical index,index of entropy and certainty factors models

The main aim of this study is to generate groundwater spring potential maps for the Ningtiaota area (China) using three statistical models namely statistical index (SI), index of entropy (IOE) and certainty factors (CF) models. Firstly, 66 spring locations were identified by field surveys, out of which, 46 (70%) spring locations were randomly selected for training the models and the rest 20 (30%) spring locations were used for validation. Secondly, 12 spring influencing factors, namely slope angle, slope aspect, altitude, profile curvature, plan curvature, sediment transport index, stream power index, topographic wetness index, distance to roads, distance to streams, lithology and normalized difference vegetation index (NDVI) were derived from the spatial database. Subsequently, using the mentioned factors and the three models, groundwater spring potential values were calculated and the results were plotted in ArcGIS 10.0. Finally, the area under the curve was used to validate groundwater spring potential maps. The results showed that the IOE model, with the highest success rate of 0.9126 and the highest prediction rate of 0.9051, showed the preferable performance in this study. The results of this study may be helpful for planners and engineers in groundwater resource management and other similar watersheds.     

Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province,Iran

Flood is one of the most devastating natural disasters with socio-economic and environmental consequences. Thus, comprehensive flood management is essential to reduce the flood effects on human lives and livelihoods. The main goal of this study was to investigate the application of the frequency ratio (FR) and weights-of-evidence (WofE) models for flood susceptibility mapping in the Golestan Province, Iran. At first, a flood inventory map was prepared using Iranian Water Resources Department and extensive field surveys. In total, 144 flood locations were identified in the study area. Of these, 101 (70%) floods were randomly selected as training data and the remaining 43 (30%) cases were used for the validation purposes. In the next step, flood conditioning factors such as lithology, land-use, distance from rivers, soil texture, slope angle, slope aspect, plan curvature, topographic wetness index (TWI) and altitude were prepared from the spatial database. Subsequently, the receiver operating characteristic (ROC) curves were drawn for produced flood susceptibility maps and the area under the curves (AUCs) was computed. The final results indicated that the FR (AUC = 76.47%) and WofE (AUC = 74.74%) models have almost similar and reasonable results. Therefore, these flood susceptibility maps can be useful for researchers and planner in flood mitigation strategies.     

Integrated Spatio‐temporal Data Mining for Forest Fire Prediction

Forests play a critical role in sustaining the human environment. Most forest fires not only destroy the natural environment and ecological balance, but also seriously threaten the security of life and property. The early discovery and forecasting of forest fires are both urgent and necessary for forest fire control. This article explores the possible applications of Spatio‐temporal Data Mining for forest fire prevention. The research pays special attention to the spatio‐temporal forecasting of forest fire areas based upon historic observations. An integrated spatio‐temporal forecasting framework – ISTFF – is proposed: it uses a dynamic recurrent neural network for spatial forecasting. The principle and algorithm of ISTFF are presented, and are then illustrated by a case study of forest fire area prediction in Canada. Comparative analysis of ISTFF with other methods shows its high accuracy in short‐term prediction. The effect of spatial correlations on the prediction accuracy of spatial forecasting is also explored.     

A novel hybrid approach of Bayesian Logistic Regression and its ensembles for landslide susceptibility assessment

Abstract

A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC?=?0.930). However, RS model (AUROC?=?0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC?=?0.972), MB (AUROC?=?0.970) and AB (AUROC?=?0.957) models, respectively.     

Comparing Fire Severity Models from Post-Fire and Pre/Post-Fire Differenced Imagery

Wildland fires are common in rangelands worldwide. The potential for high-severity fires to affect long-term changes in rangelands is considerable, and for this reason assessing fire severity shortly after the fire is critical. Such assessments are typically carried out following Burned Area Emergency Response teams or similar protocols. These data can then be used by land managers to plan remediation and future land uses. To complement these procedures and explore fire severity modeling of sagebrush steppe rangelands, we compared models developed using (1) post-fire imagery only with (2) differenced imagery (pre-fire minus post-fire imagery). All models were developed from Classification Tree Analysis (CTA) techniques using Satellite Pour l'Observation de la Terre 5 (SPOT 5) imagery and Shuttle Radar Topography Mission (SRTM) elevation data. The results indicate that both techniques produced similar fire severity models (model agreement = 98.5%) and that little improvement in overall accuracy was gained by using differenced imagery (0.5%). We suggest the use of CTA models developed using only the post-fire imagery. The analyses and techniques described in this paper provide land managers with tools to better justify their recommendations and decisions following wildland fires in sagebrush steppe ecosystems and provide remote sensing scientists with information that will potentially improve future modeling efforts.     

Application of frequency ratio,weights of evidence and evidential belief function models in landslide susceptibility mapping

The landslide hazard occurred in Taibai County has the characteristics of the typical landslides in mountain hinterland. The slopes mainly consist of residual sediments and locate along the highway. Most of them are in the less stable state and in high risk during rainfall in flood season especially. The main purpose of this paper is to produce landslide susceptibility maps for Taibai County (China). In the first stage, a landslide inventory map and the input layers of the landslide conditioning factors were prepared in the geographic information system supported by field investigations and remote sensing data. The landslides conditioning factors considered for the study area were slope angle, altitude, slope aspect, plan curvature, profile curvature, distance to faults, distance to rivers, distance to roads, normalized difference vegetation index, lithological unit, rainfall and land use. Subsequently, the thematic data layers of conditioning factors were integrated by frequency ratio (FR), weights of evidence (WOE) and evidential belief function (EBF) models. As a result, landslide susceptibility maps were obtained. In order to compare the predictive ability of these three models, a validation procedure was conducted. The curves of cumulative area percentage of ordered index values vs. the cumulative percentage of landslide numbers were plotted and the values of area under the curve (AUC) were calculated. The predictive ability was characterized by the AUC values and it indicates that all these models considered have relatively similar and high accuracies. The success rate of FR, WOE and EBF models was 0.9161, 0.9132 and 0.9129, while the prediction rate of the three models was 0.9061, 0.9052 and 0.9007, respectively. Considering the accuracy and simplicity comprehensively, the FR model is the optimum method. These landslide susceptibility maps can be used for preliminary land use planning and hazard mitigation purpose.     

Fuzzy–frequency ratio model for avalanche susceptibility mapping

Avalanche activities in the Indian Himalaya cause the majority of fatalities and responsible for heavy damage to the property. Avalanche susceptibility maps assist decision-makers and planners to execute suitable measures to reduce the avalanche risk. In the present study, a probabilistic data-driven geospatial fuzzy–frequency ratio (fuzzy–FR) model is proposed and developed for avalanche susceptibility mapping, especially for the large undocumented region. The fuzzy–FR model for avalanche susceptibility mapping is initially developed and applied for Lahaul-Spiti region. The fuzzy–FR model utilized the six avalanche occurrence factors (i.e. slope, aspect, curvature, elevation, terrain roughness and vegetation cover) and one referent avalanche inventory map to generate the avalanche susceptibility map. Amongst 292 documented avalanche locations from the avalanche inventory map, 233 (80%) were used for training the model and remaining 59 (20%) were used for validation of the map. The avalanche susceptibility map is validated by calculating the area under the receiver operating characteristic curve (ROC-AUC) technique. For validation of the results using ROC-AUC technique, the success rate and prediction rate were calculated. The values of success rate and prediction rate were 94.07% and 91.76%, respectively. The validation of results using ROC-AUC indicated the fuzzy–FR model is appropriate for avalanche susceptibility mapping.     

近实时中高空间分辨率森林火灾监测系统展望

森林火灾是最为常见的灾害之一,严重危及人类生命安全。及时准确监测森林火灾的发生及火场状况,对应对火灾及减少损失至关重要。当前,森林火灾卫星遥感监测主要以低空间分辨率的卫星遥感为主,空间分辨率过低导致无法探测规模较小火灾及掌握详细火场态势。针对这一问题,结合近些年中高空间分辨率卫星观测、共享及处理能力的发展,本文从森林火灾卫星遥感监测的基本原理、当前可用中高空间分辨率卫星数据及其特点、中高分辨率森林着火区监测算法,以及数据共享与云端存储与计算等4个技术环节,对森林火灾中高分辨率卫星遥感监测当前研究现状与存在问题进行了总结,阐述了近实时中高空间分辨率森林火灾监测系统的可行性。近实时中高空间分辨率森林火灾监测系统可对已有低空间分辨率森林火灾监测体系形成重要补充,依托其空间分辨率的优势有助于及早、准确发现小规模火情,进而为森林火灾的防治与管理提供更好支撑。     

Landslide susceptibility assessment using evidential belief function,certainty factor and frequency ratio model at Baxie River basin,NW China

This study evaluates and compares landslide susceptibility maps of the Baxie River basin, Gansu Province, China, using three models: evidential belief function (EBF), certainty factor (CF) and frequency ratio (FR). First, a landslide inventory map is constructed from satellite image interpretation and extensive field data. Second, the study area is partitioned into 17,142 slope units, and modelled using nine landslide influence parameters: elevation, slope angle, slope aspect, relief amplitude, cutting depth, gully density, lithology, normalized difference vegetation index and distance to roads. Finally, landslide susceptibility maps are presented based on EBF, CF and FR models and validated using area under curve (AUC) analysis. The success rates of the EBF, CF and FR models are 0.8038, 0.7924 and 0.8088, respectively, while the prediction rates of the three models are 0.8056, 0.7922 and 0.7989, respectively. The result of this study can be reliably used in land use management and planning.     

A novel ensemble approach of bivariate statistical-based logistic model tree classifier for landslide susceptibility assessment

Abstract

This study addresses landslide susceptibility mapping (LSM) using a novel ensemble approach of using a bivariate statistical method (weights of evidence [WoE] and evidential belief function [EBF])-based logistic model tree (LMT) classifier. The performance and prediction capability of the ensemble models were assessed using the area under the ROC curve (AUROC), standard error, 95% confidence intervals and significance level P. Model performance analyses indicated that the AUROC values of the WoE–LMT ensemble model using the training and validation data-sets were 86.02 and 85.9%, respectively, whereas those of the EBF–LMT ensemble model were 88.2 and 87.8%, respectively. On the other hand, the AUC curves for the four landslide susceptibility maps indicated that the AUC values of the ensemble models of WoE–LMT (85.11 and 83.98%) and EBF–LMT (86.21 and 85.23%) could improve the performance and prediction accuracy of single WoE (84.23 and 82.46%) and EBF (85.39 and 81.33%) models for the training and validation data-sets.     

Frequency ratio modelling using geospatial data to predict Kimberlite Clan of rock emplacement zones in Dharwar Craton,India

Kimberlite clan of rocks (KCR) comprising of mantle derived ultrabasic rocks such as Kimberlite and related Lamproites and Lamprophyres,are the primary source of diamond. Locating the KCR is first step in the diamond exploration, which is highly challenging in the field due to (i) very small spatial extent of KCR pipes (ii) high susceptibility of KCR to weathering and alteration on exposure to atmosphere, owing to their ultrabasic composition. Predictive statistical models using the geospatial data are often used to minimize the search and the present work attempts to apply the Frequency Ratio (FR) based predictive model in GIS to prepare KCR potential zone maps based on the relationship between the already explored KCR locations and the factors that favour their emplacement. Wajrakarur Kimberlite Field (WKF) in the Dharawar Craton of India, with more than 30 explored kimberlite pipes is selected as the study area. Geospatial technology has been used to generate thematic maps such as known KCR pipe locations, lineament density, lineament buffer zone, lineament intersection buffer zone, drainage anomaly buffer zone, geomorphology, and classified image showing distribution of mineral such as clay, iron oxide and calcrete, which are surface expression of KCR emplacement from various sources. Landsat 8 OLI satellite data, ASTER DEM were used in preparing the geomorphology, lineament map, and band ratio based mineral classified map. The thematic maps were converted to raster grid of 10 sq. m. FR values for each unit in each thematic map were obtained by correlating the spatial relationship between thematic map and the 25 locations of the 33 “known” KCR locations in WKF used for FR modelling. Cumulative FR value were obtained by carrying out overlay analysis of the thematic maps, which are classified into five classes by Natural Breaking method as (i)Very Low Favourable (VLF), (ii) Low Favourable (LF), (iii)Moderate favourable (MF), (iv)High Favourable (HF), and (v)Very High Favourable (VHF). The model was validated by ground verification at random sites and statistical method. During the ground visit, we observed KCR-like lithology’s at four new sites that have calcrete exposure at limited spatial extent and also some pieces of ultrabasic rocks similar to the explored sites. To ascertain their chemical composition of the samples were plotted in the MgO-K₂O-Al₂O₃ ternary diagram. All the four samples fall in the Kimberlite/Lamproite field confirming them to be KCR. The FR predictive model was also validated statistically. Total 13 locations, including 8 site out of 33 known KCR locations, one newly discovered pipe by GSI and the four locations discovered during this study were used for the validation. Statistical validation shows that 84% of model accuracy is achieved. The study reveals that Lineament Intersection, and circular drainage anomaly in 3rd order streams, lineament density are significant themes in predicting KCR emplacement zones. The study demonstrates the utility of statistical based model such as FR model in predicting the location of KCR emplacement, even with statistically insignificant distribution of KCRs and can be applied elsewhere in the world to locate the KCRs. In the process, we report discovery of four new KCR pipes in the WKF.     

Modeling of multi-strata forest fire severity using Landsat TM Data

Most of fire severity studies use field measures of composite burn index (CBI) to represent forest fire severity and fit the relationships between CBI and Landsat imagery derived differenced normalized burn ratio (dNBR) to predict and map fire severity at unsampled locations. However, less attention has been paid on the multi-strata forest fire severity, which represents fire activities and ecological responses at different forest layers. In this study, using field measured fire severity across five forest strata of dominant tree, intermediate-sized tree, shrub, herb, substrate layers, and the aggregated measure of CBI as response variables, we fit statistical models with predictors of Landsat TM bands, Landsat derived NBR or dNBR, image differencing, and image ratioing data. We model multi-strata forest fire in the historical recorded largest wildfire in California, the Big Sur Basin Complex fire. We explore the potential contributions of the post-fire Landsat bands, image differencing, image ratioing to fire severity modeling and compare with the widely used NBR and dNBR. Models using combinations of post-fire Landsat bands perform much better than NBR, dNBR, image differencing, and image ratioing. We predict and map multi-strata forest fire severity across the whole Big Sur fire areas, and find that the overall measure CBI is not optimal to represent multi-strata forest fire severity.     

GIS-based spatiotemporal analysis of forest fires in Turkey from 2010 to 2020

Forests are essential in contributing to the continuity of the natural balance. Therefore, their protection and sustainability are vital. However, all over the world, forest fires occur, and forests are destroyed due to both human factors and unknown causes. It is necessary to carry out studies to prevent this destruction. At this point, GIS-based location–time relationship-based hot spot clustering analysis can provide significant advantages in detecting risky spots of forest fires. In this study, GIS-based emerging hot spot clustering analysis was carried out to determine the risky areas where forest fires will occur and to carry out preventive studies in the relevant areas. Turkey was chosen as the pilot region, and analyses were carried out using the data obtained from the official statistics of the Ministry of Agriculture and Forestry General Directorate of Forestry according to the causes of the fires (negligence, intentional, accidental, unknown cause and natural) between the years 2010 and 2020. Spatial autocorrelation analysis was conducted for each fire type, and threshold distances were determined {with a number of distance bands = 20,000, distant increment = 10,000}. Emerging hot spot analyses were then conducted, and the results were presented as maps and statistical outputs. According to all fire types, 15 new hot spots, 14 persistent hot spots, 33 sporadic hot spots, 9 consecutive hot spots, 15 intensifying, and 2 diminishing hot spot regions were obtained throughout the country.     

Mapping burns and natural reforestation using thematic Mapper data

Remote sensing techniques are specially suitable to detect and to map areas affected by forest fires. In this work, Landsat 5 Thematic Mapper (TM) data has been used to study a number of forest fires that occurred in the province of Valencia (Spain) and to monitor the vegetation regeneration over burnt areas.

A reference area (non‐burnt forest) was established to assess the change produced by fire. The radiance in the thermal band (10.4–12.5 μm) and the normalized difference in reflectance between near 1R (0.76–0.90 μm) and middle IR (2.08–2.35 μm) were the most suitable parameters to map burnt areas. This index can also be used for monitoring vegetation regeneration in burnt areas. About a month after the fire, the burns show temperatures of 5–6 °C higher than those found in the reference area, and the vegetation index shows negative values whereas the reference area values remain positive. The differences between the burns and the reference area for the vegetation index decrease with time as vegetation regenerates.     

MAPS OF COMBUSTIBLE FOREST MATERIALS

An article devoted to applied forest-fire mapping outlines principles for the compilation of maps depicting “raw materials” for such fires. Various types and densities of vegetation cover are classified in terms of combustibility, i.e., according to the intensity of burning expected once they are fully exposed to flames. These maps are used in conjunction with weather data and forecasts to predict and combat the spread of fire across an area. Particular attention is devoted to identification and mapping of “basic conductors” of combustion–layers of forest litter and mossypeaty vegetation along which a forest fire normally spreads. Translated from: Geografiya i prirodnyye resursy, 1987, No. 3, pp. 138-144.     

Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang,Korea

Landslides susceptibility maps were constructed in the Pyeong-Chang area, Korea, using the Random Forest and Boosted Tree models. Landslide locations were randomly selected in a 50/50 ratio for training and validation of the models. Seventeen landslide-related factors were extracted and constructed in a spatial database. The relationships between the observed landslide locations and these factors were identified by using the two models. The models were used to generate a landslide susceptibility map and the importance of the factors was calculated. Finally, the landslide susceptibility maps were validated. Finally, landslide susceptibility maps were generated. For the Random Forest model, the validation accuracy in regression and classification algorithms showed 79.34 and 79.18%, respectively, and for the Boosted Tree model, these were 84.87 and 85.98%, respectively. The two models showed satisfactory accuracies, and the Boosted Tree model showed better results than the Random Forest model.