The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques

Urban impervious surface information is essential for urban and environmental applications at the regional/national scales. As a popular image processing technique, spectral mixture analysis (SMA) has rarely been applied to coarse-resolution imagery due to the difficulty of deriving endmember spectra using traditional endmember selection methods, particularly within heterogeneous urban environments. To address this problem, we derived endmember signatures through a least squares solution (LSS) technique with known abundances of sample pixels, and integrated these endmember signatures into SMA for mapping large-scale impervious surface fraction. In addition, with the same sample set, we carried out objective comparative analyses among SMA (i.e. fully constrained and unconstrained SMA) and machine learning (i.e. Cubist regression tree and Random Forests) techniques. Analysis of results suggests three major conclusions. First, with the extrapolated endmember spectra from stratified random training samples, the SMA approaches performed relatively well, as indicated by small MAE values. Second, Random Forests yields more reliable results than Cubist regression tree, and its accuracy is improved with increased sample sizes. Finally, comparative analyses suggest a tentative guide for selecting an optimal approach for large-scale fractional imperviousness estimation: unconstrained SMA might be a favorable option with a small number of samples, while Random Forests might be preferred if a large number of samples are available.     

Geospatial technologies for detection and monitoring of Ganoderma basal stem rot infection in oil palm plantations: a review on sensors and techniques

Basal stem rot (BSR) is a type of disease that induces oil palm death within a short span of the appearance of symptoms. BSR early detection would facilitate to curb this by adopting appropriate strategies. In this paper, a systematic review was undertaken to demonstrate the need for authentic health condition monitoring of oil palm plantations. The currently used remotely sensed (RS) techniques for BSR detection and classification were reviewed. Several kinds of RS techniques were exerted for BSR detection and its severity classification up to four levels. It was identified that applied geospatial technologies, including multispectral and hyperspectral remote sensing, terrestrial laser scanning, spatial maps, tomography images, intelligent e-nose and Microfocus X-ray fluorescence, were capable of distinguishing infected oil palms from the non-infected ones. Furthermore, some of them are able to categorize BSR severity level up to four levels as well as of its early detection.     

Integration of remote sensing,county-level census,and machine learning for century-long regional cropland distribution data reconstruction

The Lower Mississippi Alluvial Valley (LMAV) was home to about ten million hectare bottomland hardwood (BLH) forests in the Southern U.S. It experienced over 80 % area loss of the BLH forests in the past centuries and large-scale afforestation in recent decades. Due to the lack of a high-resolution cropland dataset, impacts of land use change (LUC) on the LMAV ecosystem services have not been fully understood. In this study, we developed a novel framework by integrating the machine learning algorithm, county-level agricultural census, and satellite-based cropland products to reconstruct the LMAV cropland distribution during 1850–2018 at a 30-m resolution. Results showed that the LMAV cropland area increased from 0.78 × 10⁴ km² in 1850 to 6.64 × 10⁴ km² in 1980 and then decreased to 6.16 × 10⁴ km² in 2018. Cropland expansion rate was the largest in the 1960s (749 km² yr⁻¹) but decreased rapidly thereafter, whereas cropland abandonment rate increased substantially in recent decades with the largest rate of 514 km² yr⁻¹ in the 2010s. Our dataset has three notable features: (1) the depiction of fine spatial details, (2) the integration of the county-level census, and (3) the inclusion of a machine-learning algorithm trained by satellite-based land cover product. Most importantly, our dataset well captured the continuous increasing trend in cropland area from 1930–1960, which was misrepresented by other cropland datasets reconstructed from the state-level census. Our dataset would be important to accurately evaluate the impacts of historical deforestation and recent afforestation efforts on regional ecosystem services, attribute the observed hydrological changes to anthropogenic and natural driving factors, and investigate how the socioeconomic factors control regional LUC pattern. Our framework and dataset are crucial to developing managerial and policy strategies for conserving natural resources and enhancing ecosystem services in the LMAV.     

Evaluating techniques for mapping island vegetation from unmanned aerial vehicle (UAV) images: Pixel classification,visual interpretation and machine learning approaches

We evaluate three approaches to mapping vegetation using images collected by an unmanned aerial vehicle (UAV) to monitor rehabilitation activities in the Five Islands Nature Reserve, Wollongong (Australia). Between April 2017 and July 2018, four aerial surveys of Big Island were undertaken to map changes to island vegetation following helicopter herbicide sprays to eradicate weeds, including the creeper Coastal Morning Glory (Ipomoea cairica) and Kikuyu Grass (Cenchrus clandestinus). The spraying was followed by a large scale planting campaign to introduce native plants, such as tussocks of Spiny-headed Mat-rush (Lomandra longifolia). Three approaches to mapping vegetation were evaluated, including: (i) a pixel-based image classification algorithm applied to the composite spectral wavebands of the images collected, (ii) manual digitisation of vegetation directly from images based on visual interpretation, and (iii) the application of a machine learning algorithm, LeNet, based on a deep learning convolutional neural network (CNN) for detecting planted Lomandra tussocks. The uncertainty of each approach was assessed via comparison against an independently collected field dataset. Each of the vegetation mapping approaches had a comparable accuracy; for a selected weed management and planting area, the overall accuracies were 82 %, 91 % and 85 % respectively for the pixel based image classification, the visual interpretation / digitisation and the CNN machine learning algorithm. At the scale of the whole island, statistically significant differences in the performance of the three approaches to mapping Lomandra plants were detected via ANOVA. The manual digitisation took a longer time to perform than others. The three approaches resulted in markedly different vegetation maps characterised by different digital data formats, which offered fundamentally different types of information on vegetation character. We draw attention to the need to consider how different digital map products will be used for vegetation management (e.g. monitoring the health individual species or a broader profile of the community). Where individual plants are to be monitored over time, a feature-based approach that represents plants as vector points is appropriate. The CNN approach emerged as a promising technique in this regard as it leveraged spatial information from the UAV images within the architecture of the learning framework by enforcing a local connectivity pattern between neurons of adjacent layers to incorporate the spatial relationships between features that comprised the shape of the Lomandra tussocks detected.     

Flexible delivery and social learning: Seeking a new geography of education for GIS and GIS in education

This paper looks at GIS education in the context of changes in society and technology. It argues that socio-economic pressures and technological change are both working to change the traditional dichotomous structure of tertiary education in respect of campus and distance learning models. In general, the changed lifestyles of a larger, less affluent student base are seen as combining with economic pressures on universities to create a mainstream demand for more flexible learning environments, a demand which new advances in applied information technology can assist in meeting. The paper considers these forces and how developments in educational technology in general are likely to impact on traditional methods of delivering GIS education.     

Microzonation of seismic and landslide prone areas for alternate highway alignment in a part of western coast of India using remote sensing techniques

West coast of India is a narrow and linear, a portion from Bombay to Goa in this track is known as Konkan coast. Remotely Sensed geocoded data from IRS-1B has the potentiality in identification of localized patches of change in environmental parameters, which includes changes in lineament pattern, vegetation anomaly, rock debris and occurrence of landslides. Ground protuberances in this terrain are important surface manifestations of probable seismic activity. In these areas quaquaversal drainage pattern is inferred. Landslides are also expected in places near NH-17 (National Highway — 17) which may affect the socio-economic scenario of area. Alternate highway alignment is planned based on least hazard potentiality of the terrain. Weathered Basalts inferred, near the bank of Amba river, were not recommended for tunnel construction. Anomalous clay patches need more care for road construction. Inferred joints, fractures and faults were found in some places which were marked as hazardous locations. Some areas were marked hazardous for road construction due to the presence of palaeochannels but the same were marked as potential areas for ground water exploration.     

Change detection of surface mining activity and reclamation based on a machine learning approach of multi-temporal Landsat TM imagery

Being able to quantify land cover changes due to mining and reclamation at a watershed scale is of critical importance in managing and assessing their potential impacts to the Earth system. In this study, a remote sensing-based methodology is proposed for quantifying the impact of surface mining activity and reclamation from a watershed to local scale. The method is based on a Support Vector Machines (SVMs) classifier combined with multi-temporal change detection of Landsat TM imagery. The performance of the technique was evaluated at selected open mining sites located in the island of Milos in Greece. Assessment of the mining impact in the studied areas was based on the confusion matrix statistics, supported by co-orbital QuickBird-2 very high spatial resolution imagery. Overall classification accuracy of the thematic land cover maps produced was reported over 90%. Our analysis showed expansion of mining activity throughout the whole 23-year study period, while the transition of mining areas to soil and vegetation was evident in varying rates. Our results evidenced the ability of the method under investigation in deriving highly and accurate land cover change maps, able to identify the mining areas as well as those in which excavation was replaced by natural vegetation. All in all, the proposed technique showed considerable promise towards the support of a sustainable environmental development and prudent resource management.     

Towards a framework for learning with GIS: The case of Urban World, a hypermap learning environment based on GIS

Off-the-shelf GIS toolboxes are inadequate for pedagogic purposes. Urban World , an Arc View application, attempts to address this shortcoming by including special features designed to foster student progress towards a better understanding of urban environments. This paper provides context for the Urban World system in an active, authentic learning environment for students of urban geography and planning at junior and senior levels in undergraduate curricula at universities in the United States. The paper describes the rationale for, and implementation of, several components of Urban World : a special graphid user interface; productivity tools for facilitating the acquisition of practical skills of mapping and spatial analysis; tools for accessing, undertaking, and submitting homework assignments in a paper-less class; and various devices for assisting students to undertake spatial reasoning. GIS are Seen as an enabling technology for improving understanding by means of engaging students in empirical analysis. Spatial problem solvers and decision makers reach sound conclusions by employing reasoning skills applied to well-formed databases; scientific research makcs progress with sound reasoning of many types. The effective teaching and learning about the geography of our world requires a strong foundation of spatid reasoning.     

Evaluation of different machine learning methods for land cover mapping of a Mediterranean area using multi-seasonal Landsat images and Digital Terrain Models

Land cover monitoring using digital Earth data requires robust classification methods that allow the accurate mapping of complex land cover categories. This paper discusses the crucial issues related to the application of different up-to-date machine learning classifiers: classification trees (CT), artificial neural networks (ANN), support vector machines (SVM) and random forest (RF). The analysis of the statistical significance of the differences between the performance of these algorithms, as well as sensitivity to data set size reduction and noise were also analysed. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land cover categories in south Spain. Overall, statistically similar accuracies of over 91% were obtained for ANN, SVM and RF. However, the findings of this study show differences in the accuracy of the classifiers, being RF the most accurate classifier with a very simple parameterization. SVM, followed by RF, was the most robust classifier to noise and data reduction. Significant differences in their performances were only reached for thresholds of noise and data reduction greater than 20% (noise, SVM) and 25% (noise, RF), and 80% (reduction, SVM) and 50% (reduction, RF), respectively.     

20 years of active deformation on volcano caldera: Joint analysis of InSAR and AInSAR techniques

InSAR (interferometric synthetic aperture radar) techniques are applied to investigate last two decades of surface deformation of the Cerro Blanco/Robledo Caldera (CBRC). The objective is the identification of deforming patterns that alter the shape of these complex structures when they show low or null activity. The joint analysis between results by using different methods over a long time span, represents a unique opportunity to improve knowledge of volcanic structures located in remote area and, for this, poorly or not monitored.In this work we identify displacement patterns over the volcanic area, by using both classical differential InSAR analysis, and A-InSAR (advanced InSAR) analysis based on SAR data acquired by ERS-1/2 and ENVISAT sensors during the 1996–2010 time interval. The satellite-derived information allows us to characterize the deformation pattern that affected the CBRC and shows that the actively deforming CBRC is subsiding in the observed period. In order to figure out the deformation history of CBRC, we analyzed the four sub-periods 1992–1996, 1996–2000, and 2005–2010 by using standard differential InSAR technique, and the interval 2003–2007 by adopting an A-InSAR technique.Subsidence velocities of the CBRC caldera are about 2.6 cm/yr in the time interval 1992–1996 (measured with ERS descending data), 1.8 cm/yr in 1996–2000 (ERS descending data), 1.2 cm/yr in 2003–2007 (ENVISAT descending data), and finally, 0.87 cm/yr in 2005–2010 (ENVISAT ascending data). Moreover, outside the caldera and in particular in the NW area, we observe the presence of positive velocity values. Results show that: (a) a decreasing subsidence rate might be related to the reduction of volcanic activity in correspondence of the CBRC; (b) positive velocity signal, decreasing with time, might be interpreted as follows: – evidence of volcano structure lateral spreading, according to the velocity pattern distribution in this area and to the relative local flanks topographic convexity of the volcano structure; – uplift signal of this sector of mountain chain; – combination of the two mechanisms above.     

Inverse problems theory and application: analysis of the two-temperature method for land-surface temperature and emissivity estimation

The two-temperature method (TTM) allows the separation of land-surface temperature and land-surface emissivity information from radiance measurements, and therefore, the solution can be uniquely determined by the data. However, the inverse problem is still an ill-posed problem, since the solution does not depend continuously on the data. Accordingly, we have used some mathematical tools, which are suited for analyses of ill-posed problems in order to show TTM properties, evaluate it, and optimize its estimations. Related to this last point, we have shown that it is necessary to constrain the problem, either by defining a region of physically admissible solutions and/or by using regularization methods, in order to obtain stable results. Besides, the results may be improved by using TTM with systems that possess a high temporal resolution, as well as by acquiring observations near the maximum and minimum of the diurnal temperature range.     

Advanced differential interferometry synthetic aperture radar techniques for deformation monitoring: a review on sensors and recent research development

This paper reviews the advanced differential interferometry synthetic aperture radar (A-DInSAR) techniques, with two major components in focus. First is the basic concepts, synthetic aperture radar (SAR) data sources and the different algorithms documented in the literature, primarily focusing on persistent scatterers. In the second part, the techniques are compared in order to establish more linkage in terms of the variability of their applications, strength and validation of the interpreted results. Also, current issues in sensor and algorithm development are discussed. The study identified six existing A-DInSAR algorithms used for monitoring various deformation types. Generally, reports of their performance indicate that all the techniques are capable of measuring deformation phenomena at varying spatial resolution with high level of accuracy. However, their usability in suburban and vegetated areas yields poor results, compared to urbanized areas, due to inadequate permanent features that could provide sufficient coherent point targets. Meanwhile, there is continuous development in sensors and algorithms to expand the applicability domain of the technology for a wide range of deformable surfaces and displacement patterns with higher precision. On the sensor side, most of the latest SAR sensors employ longer wavelength (X and P bands) to increase the penetrating power of the signal and two other sensors (ALOS-2 PALSA-2 and SENTINEL-1) are scheduled to be launched in 2013. Researchers are investigating the possibility of using single-pass sensors with different look angles for SAR data collection. With these, it is expected that more data will be available for various applications. Algorithms such as corner reflector interferometry SAR, along track interferometry, liqui-InSAR, and squeeSAR are emerging to increase reliable estimation of deformation from different surfaces.     

时序InSAR滑坡形变监测与预测的N-BEATS深度学习法——以新铺滑坡为例

滑坡通常发生突然,破坏力巨大,经常造成重大生命安全事故和财产损失。高可靠性、高精度及具有抗差性能的滑坡形变监测预测手段和方法对于国家防灾减灾需求具有切实意义。InSAR技术是一种能够全天时和全天候观测获取高空间分辨率和宽覆盖率影像,高灵敏性捕捉时空维动态变化的监测手段,然而目前应用InSAR时序影像对滑坡区进行滑坡预测的工作仅是凤毛麟角。基于时序InSAR观测结果,本文提出了一种能够有效解决中短期滑坡预测问题的深度学习滑坡预测方法。在三峡新铺滑坡区应用N-BEATS网络模型和Sentinel-1 SAR数据进行形变预测,以均方根误差1.1 mm的预测精度完成了滑坡预测工作,并对预测结果进行了数据结构影响的规律性分析、传统方法效果对比、抗差性评估及置信区间估计等多方位的剖析,结果显示出了其高精度、高可靠性及具有一定抗差能力的突出优势。     

Evaluation of deflections of the vertical on the sphere and the plane: a comparison of FFT techniques

This paper presents a set of efficient formulas to evaluate the deflections of the vertical on the sphere using gridded data. The Vening-Meinesz formula, the topographic indirect effect on the deflections of the vertical as well as the terrain corrections are expressed as both 2D and 1D convolutions on the sphere, and consequently can be evaluated by the 2D and the 1D fast Fourier transform (FFT). When compared with the results obtained from pointwise integration, the use of the 1D FFT gives identical results, and therefore these results were used as control values in this paper. The use of the spherical 2D FFT improves significantly the computational efficiency with little sacrifice of accuracy (0.6^″ rms difference from the 1D FFT results). The planar 2D FFT, which is as efficient as the spherical 2D FFT, gives worse results (1.2^″ rms difference from the 1D FFT results) because of the extra approximations. Received: 27 February 1996; Accepted: 24 January 1997     

Urban sprawl and its impact on sustainable urban development: a combination of remote sensing and social media data

Urbanization is one of the most impactful human activities across the world today affecting the quality of urban life and its sustainable development. Urbanizat...     

联合InSAR和SSA的膨胀土边坡形变特征分析——以南水北调工程为例

膨胀土边坡具有吸水剧烈膨胀、失水剧烈收缩及反复胀缩形变的特性,工程中与外界接触极易引发膨胀土滑坡。南水北调中线工程是一项缓解我国华北平原水资源短缺、优化水资源配置的国家重大战略工程。中线总干渠约有1/3段穿越膨胀土区域,增加了南水北调工程沿线边坡失稳的可能性,亟须开展膨胀土边坡形变监测和特征分析。基于此,本文收集了112景Sentinel-1A升轨SAR数据,采用时间序列InSAR技术获取了中线某渠道沿线2017年3月12日—2021年4月8日的时间序列形变,并基于奇异谱分析(SSA)对时间序列形变进行分解提取膨胀土边坡形变特征。研究结果表明:干渠挖方膨胀土边坡由于卸荷回弹作用表现为抬升形变,最大年抬升速率约为18 mm/a;填充膨胀土边坡由于土体固结作用表现为下沉形变,最大年下沉速率约为15 mm/a;膨胀土形变量大小与填挖深度正相关,挖方越深抬升形变越大,填充越高下沉形变越大;降雨和温度是影响干渠膨胀土边坡形变的主要外部因素,其造成的形变会时滞2~3个月。本文研究将为南水北调工程膨胀土边坡稳定性评估提供科学依据。     

Functional relation of land surface albedo with climatological variables: a review on remote sensing techniques and recent research developments

Surface albedo has been documented as one of the Essential Climate Variables (ECV) of the Global Climate Observing System (GCOS) that governs the Earth's Radiation Budget. The availability of surface albedo data is necessary for a comprehensive environmental modelling study. Thus, both temporal and spatial scale issues need to be rectified. This study reports about the availability of surface albedo data through in-situ and remote sensing satellite observations. In this paper, we reviewed the existing models for surface albedo derivation and various initiatives taken by related environmental agencies in order to understand the issues of climate with respect to surface albedo. This investigation evaluated the major activities on albedo-related research specifically for the retrieval methods used to derive the albedo values. Two main existing albedo measurement methods are derived through in-situ measurement and remotely sensed observations. In-situ measurement supported with number of instruments and techniques such aspyrheliometers, pyranometers and Baseline Surface Radiation Network (BSRN) and remotely sensed observations using angularly integrated Bi-directional Reflectance Distribution Function (BRDF) by both geostationary and polar orbit satellites. The investigation results reveals that the temporal and spatial scaling is the major issues when the albedo values are needed for microclimatic study, i.e. high-resolution time-series analyses and at heterogeneity and impervious surface. Thus, an improved technique of albedo retrieval at better spatial and temporal scale is required to fulfil the need for such kind of studies. Amongst many others, there are two downscaling methods that have been identified to be used in resolving the spatial scaling biased issues: Smoothing Filter-based Intensity Modulation (SFIM) and Pixel Block Intensity Modulation (PBIM). The temporal issues can be resolved using the multiple regression techniques of land surface temperature, selected air quality parameters, aerosol and daily skylight.     

Channeling the water data deluge: a system for flexible integration and analysis of hydrologic data

The hydrologic cycle and understanding the relationship between rainfall and runoff is an important component of earth system science, sustainable development, and natural disasters caused by floods. With this in mind, the integration of digital earth data for hydrologic sciences is an important area of research. Currently, it takes a tremendous amount of effort to perform hydrologic analysis at a large scale because the data to support such analyses are not available on a single system in an integrated format that can be easily manipulated. Furthermore, the state-of-the-art in hydrologic data integration typically uses a rigid relational database making it difficult to redesign the data model to incorporate new data types. The HydroCloud system incorporates a flexible document data model to integrate precipitation and stream flow data across spatial and temporal dimensions for large-scale hydrologic analyses. In this paper, a document database schema is presented to store the integrated data-set along with analysis tools such as web services for data access and a web interface for exploratory data analysis. The utility of the system is demonstrated based on a scientific workflow that uses the system for both exploratory data analysis and statistical hypothesis testing.     

Evaluation of linear discriminant and support vector machine classifiers for classification of nitrogen status in mature oil palm from SPOT-6 satellite images: analysis of raw spectral bands and spectral indices

Nitrogen (N) management is important in sustaining oil palm production. Remote sensing-based approaches via spectral index have promise in assessing the N nutrition content. The objectives of this study are; (i) to examine the N classification capability of three spectral indices (SI) such as visible (Vis), near infrared (NIR) and a combination of visible and NIR (Vis + NIR) from the SPOT-6 satellite, and (ii) to compare the performance of linear discriminant analysis (LDA) and support vector machine (SVM) in discriminating foliar N content of mature oil palms. Nitrogen treatments varied from 0 to 2 kg per palm. The N-sensitive SIs tested in this study were age-dependent. The Vis index (BGRI₁) (CVA = 79.55%) and Vis + NIR index (NDVI, NG, IPVI and GNDVI) (CVA = 81.82%) were the best indices to assess N status of young and prime mature palms through the SVM classifier.