Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data

The aim of this study is to evaluate the hazard of landslides at Penang, Malaysia, using a Geographical Information System (GIS) and remote sensing. Landslide locations were identified in the study area from interpretation of aerial photographs and from field surveys. Topographical and geological data and satellite images were collected, processed and constructed into a spatial database using GIS and image processing. The factors chosen that influence landslide occurrence were: topographic slope, topographic aspect, topographic curvature and distance from drainage, all from the topographic database; lithology and distance from lineament, taken from the geologic database; land use from Thematic Mapper (TM) satellite images; and the vegetation index value from Système Probatoire de l'Observation de la Terre (SPOT) satellite images. Landslide hazardous areas were analysed and mapped using the landslide‐occurrence factors by logistic regression model. The results of the analysis were verified using the landslide location data and compared with probabilistic model. The validation results showed that the logistic regression model is better in prediction than probabilistic model.     

Detection of landslides using web-based aerial photographs and landslide susceptibility mapping using geospatial analysis

The purpose of this study is to detect landslide locations using web-based digital aerial photographs and to map landslide susceptibility using landslide locations in Jinbu, Korea. The landslide susceptibility map was generated and validated using frequency ratio, weight of evidence, logistic regression and artificial neural network models with a geographic information system (GIS). The landslide locations were identified in the study area from interpretation of digital aerial photographs that were provided on an Internet portal (http://map.daum.net) and checked by field survey. A spatial database of the topography, soil, forest, geology and land use was constructed and landslide-related factors were extracted. Using these factors, landslide susceptibility was analysed using four models. Seventy percent of the landslides were used in landslide susceptibility mapping and the remaining 30% were used for validation. The validation result showed that the frequency ratio, weight of evidence, logistic regression and artificial neural network models had 84.94%, 82.82%, 87.72% and 81.44% accuracies, respectively, representing an overall satisfactory agreement of more than 80%, with the logistic regression model giving the best result. The maps generated could be used to estimate the risk to population, property and existing infrastructure such as the transportation network.     

Local radiometric correction of digital aerial photographs for multi source forest inventory

Digitized colour infrared images are a potential information source for multi-source forest inventory applications and particularly for estimating the forest characteristics of relatively small areas. The main problem in computer-aided image analysis of aerial photographs is the presence of bidirectional reflectance, which causes the spectral values of the image pixels to depend on their location in the image. Because of this, and the lack of operational methods for radiometric correction, the full potential of aerial photographs has not been utilised. This paper presents a local radiometric correction method that can be used for reducing the effect of bidirectional reflectance. The method employs satellite images that are less affected by the bidirectional reflectance for the local adjustment of the registered pixel values of aerial photographs. Because of the different spatial resolution of the aerial and satellite imagery, the local correction coefficients are computed for units that are larger than a single aerial photo pixel. In this way, the general level of brightness of the correction units can be determined on the basis of the satellite imagery while retaining the finer spatial resolution of the original aerial photo. The main advantage of the suggested method is that it does not require complex mathematical models for simulating the effect of bidirectional reflectance, neither does it require a priori knowledge of the actual forest attributes in the inventory area, but relies only on the image data.     

Assessment of tsunami and anthropogenic impacts on the forest of the North Andaman Islands,India

Forests are being depleted drastically at higher rates to cater to the needs of growing population. In this context, an attempt was made to identify the drivers of forest changes on the vegetation of the North Andaman islands by broadly categorising the changes as anthropogenic and natural disturbances (tsunami) using satellite images of 1976, 1999 and 2005. The images were classified using visual interpretation technique to generate land cover maps of the area under study. A detailed change analysis of the 1976, 1999 and 2005 images showed that a high proportion of the natural vegetation has been converted into agriculture, settlement, sand and water. The overall forest change from 1976 to 2005 is 11,670 ha with a deforestation rate of 389 ha yr^?1. The tsunami of 26 December, 2004 was found to be a major cause of deforestation of coastal forests in the North Andaman Islands, deforesting an area of 3292.5 ha. Simulation of forest cover in the next 25 and 50 years predicted a deforestation of 13,100 and 22,700 ha with a corresponding increase in non‐forest land cover to 19,600 and 29,600 ha respectively. It is predicted that after 50 years the forest area of 131,200 ha, estimated from the 1999 satellite data, may reduce to 108,500 ha, if proper conservation measures are not taken.     

An enhanced 3D model and generative adversarial network for automated generation of horizontal building mask images and cloudless aerial photographs

Information extracted from aerial photographs is widely used in the fields of urban planning and design. An effective method for detecting buildings in aerial photographs is to use deep learning to understand the current state of a target region. However, the building mask images used to train the deep learning model must be manually generated in many cases. To overcome this challenge, a method has been proposed for automatically generating mask images by using textured three-dimensional (3D) virtual models with aerial photographs. Some aerial photographs include clouds, which degrade image quality. These clouds can be removed by using a generative adversarial network (GAN), which leads to improvements in training quality. Therefore, the objective of this research was to propose a method for automatically generating building mask images by using 3D virtual models with textured aerial photographs. In this study, using GAN to remove clouds in aerial photographs improved training quality. A model trained on datasets generated by the proposed method was able to detect buildings in aerial photographs with IoU = 0.651.     

Use of remote sensing and GIS for improved natural resources management: case study from different agroecological zones of West Africa

Historical and recent aerial photograph and satellite images were analysed to study the change of land use/land cover and soil degradation in different agroecological zones of Nigeria and Benin. The sites were characterized by an expansion of farmland at the expense of forest and shrub, fallow and uncultivated land, at an increasing rate due to population growth, food demand and land scarcity. Sheet and gully erosion were the consequences of the land use intensification and have destroyed extensive areas of farmland and grazing land. Reduced agricultural and livestock production, declining revenue, as well as increased conflict from resource competition between farmers and pastoralists are expected for the future. To combat these problems, improved land use management through continuing land inventory, generating an environmental database, developing land use plans and controlling erosion through adequate soil conservation measures are recommended.     

Use of cartographic data and Landsat TM images to determine land use change in the vicinity of Mexico City

Evaluation of change in land use is important for planning further development in populated areas. Here we attempt to determine the growth of urban areas in the vicinity of Mexico City, using a 1993 Landsat Thematic Mapper (TM) image and cartographic data contained in maps published by the Instituto Nacional de Estadistica Geografia e Informatica (INEGI 1975, 1983). The area occupied by urban areas in 1975 and 1983 was quantified using raster images generated by scanning the maps. Supervised classification processes were applied to a 1993 Landsat TM image in bands 1, 2, 3, 4, 5 and 7, of the area of Chalco. The image was pre-processed and then processed to enhance the spectral response of the surface materials. The different land cover types that characterise distinct land uses in the study area were identified in the image and an overall classification accuracy of 82% was estimated using aerial photographs from the Chalco area. The resulting evaluation of the land use changes in the Chalco urban area was plotted, and a growth greater than 14% per year was estimated.     

An analysis of land use/cover change in Indonesia

The phenomena of land use/ change were evaluated by using a remote sensing approach in a case study in Yogyakarta, Indonesia. The index of changes, which was calculated by the superimposition of land use/ images of 1972, 1984, and land use maps of 1990, were introduced to analyse the pattern of change in the area. The results demonstrated that the pattern of land use/ change in the study area was that of paddy coverage to open/ land to settlement. The annual growth ratios of new settlements to absorb paddy coverage, mixed vegetation, and open/ land were 16 per cent, 20 per cent, and 64 per cent respectively. The larger the percentage of the paddy coverage, the higher the tendency for settlement growth to absorb the paddy coverage, and the larger the percentage of open/ land, the higher the tendency for settlement growth to absorb open/ land. Settlement growth had a high correlation with road accessibility. The highest settlement growth was distributed mostly in suburban areas between 200 and 400 m from secondary roads. Without intelligent intervention by the government and public awareness, the loss of these agricultural land cannot be stopped and will jeopardize the local and regional economy.     

Breaking ground: Automated disturbance detection with Landsat time series captures rapid refugee settlement establishment and growth in North Uganda

Since 2015, Uganda has welcomed over 700,000 refugees from South Sudan, Democratic Republic of the Congo, Burundi, and other East African nations, and currently hosts over 1.4 million refugees with 92% of that population living in UNHCR-managed settlements. Despite refugee settlements being essential spaces for physical protection and humanitarian aid distribution and reception, the sheer rate of refugee influx and settlement growth has introduced uncertainties around site planning, aid delivery, food security, and landscape change. For example, there is little publicly available information on settlement establishment, growth, or changes in land use/land cover for the vast majority of UNHCR-managed settlements in Uganda and around the world. To address this shortcoming, this research characterizes the spatial and temporal patterns of refugee settlement landscape dynamics using the case study of the Pagirinya Refugee Settlement in Northern Uganda, Landsat and Sentinel-2 satellite image time series, and BFAST, an automated land cover disturbance detection algorithm. To delineate the extent of the settlement and surrounding disturbance, a refugee settlement boundary was generated using a 2018 Landsat NDVI composite, which included land disturbed by settlement establishment and subsequent growth. Landsat time series data were sampled within this boundary to parametrize a BFAST model to detect settlement disturbance, which was deployed over 351 Landsat images from 2005 to 2018. This approach yielded sub-monthly land cover disturbances from 2016 to 2017 with an accuracy of 87.5% resulting from the rapid (within one month) settlement establishment, road construction, the spread of dwellings and other built-up infrastructure throughout the settlement, as well as the conversion of natural grassland to small-scale agriculture within the first six months after refugee settlement began. These results were generated using open-access data and open-source algorithms to pave the way for developing a near real-time satellite image-based settlement monitoring framework, which would aid refugee response and evaluation efforts that are central to Uganda's refugee hosting and settlement plans, as well as implementation of the Global Compact on Refugees.     

Evaluation of data sources for mapping glacial meltwater features

The meltwater system of disintegrating ice sheets provides an important source of information for the reconstruction of ice-retreat patterns during deglaciation. Recent method development in glacial geomorphology, using satellite imagery and digital elevation models (DEMs) for glacial landform mapping, has predominantly been focused on the identification of lineation and other large-scale accumulation features. Landforms created by meltwater have often been neglected in these efforts. Meltwater features such as channels, deltas and fossil shorelines were traditionally mapped using stereo interpretation of aerial photographs. However, during the transition into the digital era, driven by a wish to cover large areas more economically, meltwater features were lost in most mapping surveys. We have evaluated different sets of satellite images and DEMs for their suitability to map glacial meltwater features (lateral meltwater channels, eskers, deltas, ice-dammed lake drainage channels and fossil shorelines) in comparison with the traditional mapping from aerial photographs. Several sets of satellite images and DEMs were employed to map the landform record of three reference areas, located in northwestern Scotland, northeastern Finland and western Sweden. The employed satellite imagery consisted of Landsat 7 Enhanced Thematic Mapper Plus (ETM+), Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), Satellite Pour l'Observation de la Terre (SPOT) 5 and Indian Remote Sensing (IRS) 1C, and the DEMs used were from NEXTMap Britain, Panorama, National elevation data set of Sweden and National Land Survey of Finland. ASTER images yielded better results than the panchromatic band of Landsat 7 ETM+?in all three regions, despite the same spatial resolution of the data. In agreement with previous studies, this study shows that DEMs display accumulation features such as eskers suitably well. Satellite images are shown to be insufficiently detailed for the interpretation of smaller features such as meltwater channels. Hence, satellite imagery and DEMs of intermediate resolution contain meltwater system information only at a general level that allows for the identification of landforms of medium to large sizes. It is therefore pertinent that data with an appropriate spatial and spectral resolution are accessed to fulfil the need of a particular mapping effort. Stereo interpretation of aerial photographs continues to be an advisable method for local meltwater system reconstructions; alternatively, it can be replaced by mapping from high-resolution DEMs such as NEXTMap Britain. For regional to sub-continental reconstructions, the use of ASTER satellite imagery is recommended, because it provides both spectral and spatial resolutions suitable for the identification of meltwater features on a medium to large scale.     

Inundation mapping of the Sahibi river flood of 1977

A major flood occurred in the Sahibi basin in August 1977. From satellite images, the area inundated was delineated using a multispectral data analysis system. This was compared with a map based on aerial photographs showing the flooded area and was found to be satisfactory.     

Modeling different urban change trajectories and their trade-offs with food production in Jiangsu Province,China

Urban areas in China have expanded rapidly in recent decades, which mainly resulted in the conversion of fertile cropland. As the growth of urban areas is likely to continue in the next decades, there is a need for detailed assessments of urbanization impacts on food production. However, most land use models cannot simulate different types of urban change trajectories, such as expansion and densification, which constrains their capacity to inform such assessments with sufficient detail on the patterns of urbanization. In this paper, we present a land use model that represents multiple types of settlements, which allows to simulate multiple different urban change trajectories. We applied this model to Jiangsu Province, China, and assess the impact of projected urban development between 2015 and 2030 on cropland area and crop production. Results show that population growth is accommodated by different urban change trajectories, depending on the absence or presence of land use policies to maintain food security. In the absence of policies, population growth mainly leads to urban expansion, yielding losses in both cropland area and crop production. Implementing strict cropland protection policies leads to more urban densification and all population can be accommodated without a net loss of cropland. Yet, crop production decreases in this scenario as the most productive croplands are still converted and compensated by less productive areas. Protecting crop production instead leads to a small loss in cropland area combined with cropland intensification and different types of urban change, but maintains the total crop production. These results show the relevance of more nuanced representation of urban development in land use models in order to inform land use policies.     

Monitoring cropland changes along the Nile River in Egypt over past three decades (1984–2015) using remote sensing

The Nile River basin is the main agricultural area in Egypt. In recent decades, human activities and climate change have remarkably influenced the ecological environment there. Those changes have caused land degradation, sea level rise, and conflicts between land and population, threatening the agricultural system and food security of Egypt. In this study, cropland mapping along the Nile in Egypt over the past three decades (1984–2015) was conducted at annual frequency, using 961 Landsat TM/ETM+/OLI images. Spectral features of selected growing season images and band ratio-based indices were used in supervised classification. Thereafter, terrain and time series information were used to filter possible classification errors on the basis of logical judgment and statistical analysis. The average overall classification accuracy of cropland was greater than 90%. Furthermore, temporal and spatial characteristics of cropland expansion were analysed. The results highlight the annual geographical distribution of cropland dynamics from the Nile Valley to desert. In total, cropland areas had increased by 33.7% from 2848.1 kha in 1984 to 3807.8 kha in 2015, with an annual average increase of 31.0 kha in these 32 years.     

Modelling of urban growth using spatial analysis techniques: a case study of Ajmer city (India)

The concentration of people in densely populated urban areas, especially in developing countries like India and China, calls for the use of sophisticated monitoring systems, like remote sensing and Geographical Information Systems (GIS). Time series of land use/cover changes can easily be generated using sequential satellite images, which are required for the prediction of urban growth, verification of growth model outputs, estimation of impervious area, parameterization of various hydrological models, water resources planning and management and environmental studies. In the present work, urban growth of Ajmer city (India) in the last 29 years has been studied at mid‐scale level (5–25 m). Remote sensing and GIS have been used to extract the information related to urban growth, impervious area and its spatial and temporal variation. Statistical classification approaches have been used to derive the land use information from satellite images of eight years (1977–2005). The Shannon's entropy and landscape metrics (patchiness and map density) are computed in order to quantify the urban form (impervious area) in terms of spatial phenomena. Further, multivariate statistical techniques have been used to establish the relationship between the urban growth and its causative factors. Results reveal that land development (200%) in Ajmer is more than three times the population growth (59%). Shannon's entropy and landscape metrics has revealed the spatial distribution of the sprawl.     

Extraction of landslide-related factors from ASTER imagery and its application to landslide susceptibility mapping

The aim of this study is to extract landslide-related factors from remote-sensing data, such as Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite imagery, and to examine their applicability to landslide susceptibility near Boun, Korea, using a geographic information system (GIS). Landslide was mapped from interpretation of aerial photographs and field surveying. Factors that influence landslide occurrence were extracted from ASTER imagery. The slope, aspect and curvature were calculated from the digital elevation model (DEM) with 25.77 m root mean square error (RMSE), which was derived from ASTER imagery. Lineaments, land-cover and normalized difference vegetation index (NDVI) layers were also estimated from ASTER imagery. Landslide-susceptible areas were analysed and mapped using the occurrence factors by a frequency ratio and logistic regression model. Validation results were 84.78% in frequency ratio and 84.20% in logistic regression prediction accuracy for the susceptibility map with respect to ground-truth data.     

Single tree species classification with a hypothetical multi-spectral satellite

The requirements for high resolution multi-spectral satellite images to be used in single tree species classification for forest inventories are investigated, especially with respect to spatial resolution, sensor noise and geo-registration. In the hypothetical setup, a 3D tree crown map is first obtained from very high resolution panchromatic aerial imagery and subsequently each crown is classified into one of a set of known tree species such that the difference between a model multi-spectral image generated from the 3D crown map and an acquired multi-spectral satellite image of the forested area is minimized. The investigation is conducted partly by generating synthetic data from a 3D crown map from a real mixed forest stand and partly on hypothetical high resolution multi-spectral satellite images obtained from very high resolution colour infrared aerial photographs, allowing different hypothetical spatial resolutions. Conclusions are that until a new generation of even higher resolution satellites becomes available, the most feasible source of remote sensing data for single tree classification will be aerial platforms.     

Estimation of the fractional canopy cover of pecan orchards using Landsat 5 satellite data,aerial imagery,and orchard floor photographs

Pecan orchards are the largest agricultural water consumer in the lower part of the Mesilla Valley, NM, USA. Knowledge of fractional canopy (FC) cover allows better crop water use assessment and orchard management. FC can be estimated from vegetation indices (VIs), such as the normalized difference vegetation index (NDVI), the soil-adjusted vegetation index (SAVI), the simple ratio (SR), and the triangular vegetation index (TVI), using satellite imagery. The main objective of this research is to develop an approach to determine the FC from a simultaneous imagery campaign consisting of aerial imagery, orchard floor photographs, and satellite images. All the required data were collected based on satellite overpass times at three different times during the initial part of the growing season to enhance the quality of data and reduce errors. The data were processed using the software package Environment for Visualizing Images (ENVI^® 4.6.1; ITT Research Systems Inc.). The orchard floor digital photographs were used as a ground truth data set that gave a good correlation to the aerial photography. The aerial images were then used to determine the relationship between the FC and the VIs using these ‘corrected FCs’. The results showed significant correlation between NDVI and FC (R ² = 0.80; p < 0.0001). Likewise, the calculated SR not only showed good correlation to the FCs but also verified the calculated NDVI. The results indicated that the methodology of this research can be applied to other tree crops as an aid in estimating the FC.     

Improvement of land-cover classification over frequently cloud-covered areas using Landsat 8 time-series composites and an ensemble of supervised classifiers

Recent abundance of moderate-to-high spatial resolution satellite imagery has facilitated land-cover map production. However, in cloud-prone areas, building high-resolution land-cover maps is still challenging due to infrequent satellite revisits and lack of cloud-free data. We propose a classification method for cloud-persistent areas with high temporal dynamics of land-cover types. First, compositing techniques are employed to create dense time-series composite images from all available Landsat 8 images. Then, spectral–temporal features are extracted to train an ensemble of five supervised classifiers. The resulting composite images are clear with at least 99.78% cloud-free pixels and are 20.47% better than their original images on average. We classify seven land classes, including paddy rice, cropland, grass/shrub, trees, bare land, impervious area, and waterbody over Hanoi, Vietnam, in 2016. Using a time series of composites significantly improves the classification performance with 10.03% higher overall accuracy (OA) compared to single composite classifications. Additionally, using time series of composites and the ensemble technique, which combines the best of five experimented classifiers (eXtreme Gradient Boosting, logistic regression, Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel – SVM–RBF and Linear kernel – SVM–Linear, multilayer perceptron), performed best with 84% OA and 0.79 kappa coefficient.     

Monitoring change in the extent of salt-affected soils in northern India

A large area of barren salt-affected soils has been reclaimed in recent years in the Ganges Plains or Uttar Pradesh, India, Increased canal irrigation in the area, on the other hand, is also leading to salinization of new areas. A study was conducted using aerial photographs and Landsat Thematic Mapper (TM) data to monitor change in the status of salt-affected soils in the Kanpur district of Uttar Pradesh. Old survey maps prepared using ground methods in 1956, showing large salt-affected soil blocks of more than 80 ha, were used as a basis for comparison. These maps were compared with the maps prepared using aerial photographs of 1972 and Landsat TM images of 1986. Aerial photographs on a 1:40 000 scale and standard Landsat TM false colour composite (FCC) image on 1:50000 scale provided a minimum delineation of 2 ha size, which was considered sufficient for change detection in the present case. The average increase in cultivation due to reclamation within the salt-affected soil blocks during 1956-86 was found to be 22 per cent. This increase was also corroborated by the increase in the rice area during the above period in the district since these soils are used mainly for rice cultivation. During 1972-86, an increase in the extent of salt-affected soils on the periphery of large blocks was also observed, which was limited to 3 per cent.     

Probabilistic landslide hazard mapping using GIS and remote sensing data at Boun,Korea

The aim of this study is to evaluate the hazard of landslides at Boun, Korea, using a Geographic Information System (GIS) and remote sensing. Landslide locations were identified in the Boun area from interpretation of aerial photographs and field surveys. The topographic, soil, forest, geologic, lineament and land cover data were collected, processed and constructed into a spatial database using GIS and remote sensing data. The factors that influence landslide occurrence, such as slope, aspect and curvature of the topography, were calculated from the topographic database. Texture, material, drainage and effective soil thickness were extracted from the soil database, and type, age, diameter and density of timber were extracted from the forest database. The lithology was extracted from the geological database and lineaments were detected from Indian Remote Sensing (IRS) satellite images. The land cover was classified based on the Landsat Thematic Mapper (TM) satellite image. Landslide hazard areas were analysed and mapped, using the landslide-occurrence factors, by the probability–likelihood ratio method. The results of the analysis were verified using actual landslide location data. The validation results showed satisfactory agreement between the hazard map and the existing data on landslide locations.