filter by: Publication Year
(Descending) Articles
International Journal of Environmental Science and Technology (17351472) 22(9)pp. 7797-7814
Modeling PM2.5 concentrations in urban environments is complex due to the irregular distribution of air pollution monitoring (APM) stations, uncertainties in spatiotemporal relationships, and the dynamic, heterogeneous nature of urban environments. To address these challenges, this study proposes a novel three-stage framework to enhance PM2.5 modeling accuracy. First, a graph attention network (GAT) effectively handles the irregular distribution and uncertainty in spatiotemporal relationships by using multi-graphs to capture both spatial and temporal correlations between APM stations. The GAT's attention mechanism adaptively assigns greater weights to more relevant inputs, improving both interpretability and prediction precision. In the final stage, reinforcement learning, through the use of a Deep Q-Network (DQN), a reinforcement learning algorithm, optimizes the ensemble of GAT with deep recurrent networks long short-term memory (LSTM), and Gated recursive unit (GRU), dynamically adjusting model weightings to better adapt to rapidly changing urban environments. This framework significantly outperforms thirteen state-of-the-art models, demonstrating superior adaptability and accuracy in capturing PM2.5 dynamics. These findings offer a robust and scalable solution for air pollution prediction, with direct implications for public health interventions and urban policy planning. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2025.
Plant and Soil (15735036) 509(1)pp. 377-397
Aims: Land surface emissivity (LSE) is an important variable in soil studies. Although there are various remote sensing methods to estimate LSE, accurately predicting LSE still remains a major challenge. Typically, the correlation between LSE and the Visible Near Infrared bands is employed for LSE estimation. However, some studies have raised some concerns about this correlation, especially in bare soil areas. Therefore, it is necessary to conduct further investigation to determine if there exists a nonlinear relationship between the LSE and other spectral bands, which was not detected by simple linear correlation/regression. Methods: In this study, firstly, a deep Auto-encoder network has been used to investigate the correlation between LSE and other spectral bands. Subsequently, we have applied a Conditional Generative Adversarial Network (CGAN) to estimate the LSE. The proposed CGAN was trained using the Landsat and ECOSTRESS satellite datasets. The performance of the developed network was then compared with NDVI-based method on satellite/simulated-based bare soil pixels. Results: For satellite data, the RMSE (Root Mean Squared Error) and correlation coefficient (R) between the estimated LSE using proposed CGAN and ECOSTRESS LSE are 0.005 and 0.97, respectively. For the simulated data, the RMSE and R between the estimated LSE and the simulated one are 0.01 and 0.92, respectively. Conclusion: The results of the deep Auto-encoder show considerable relationship between the LSE and Short-Wave Infrared bands which not be seen using simple linear correlation. In cases of satellite/simulated data of bare soils, the developed network showed superior performance compared to NDVI-based method. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.
Environmental Science and Pollution Research (09441344) 31(40)pp. 53140-53155
Accurately predicting the spatial-temporal distribution of PM2.5 is challenging due to missing data and selecting an appropriate modeling method. Effective imputation of missing data must consider the relationships between variables while preserving their inherent variability and uncertainty. In this study, we employed machine learning techniques to impute missing data by analyzing the relationships between meteorological variables and other pollutants. Subsequently, we introduced an innovative spatiotemporal hybrid model, AC_GRU, which integrates a one-dimensional convolutional neural network (CNN), GRU, and an attention-based network to predict PM2.5 concentrations in urban areas. The AC_GRU model utilizes meteorological variables, PM2.5 concentrations from nearby air quality monitoring stations, and concentrations of other pollutants as inputs. This approach allows the model to learn spatiotemporal correlations within the time-series data, enhancing the accuracy of PM2.5 predictions. Additionally, the attention mechanism improves prediction accuracy by automatically weighting the past input variables based on their importance for future PM2.5 predictions. The experimental results demonstrate that our AC_GRU model outperforms state-of-the-art methods, making it a valuable tool for urban air quality management and public health protection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.
Atmospheric Pollution Research (13091042) 15(1)
Aerosol Optical Depth (AOD) retrieved using Cloud-Aerosol LIDAR with Orthogonal Polarization (CALIOP) and Moderate Resolution Imaging Spectroradiometer (MODIS) plays a crucial role in aerosol sensing. However, the performance of these products varies across different aerosol concentrations. This research assessed the performance of CALIOP and MODIS AOD products over a three-year period (January 2017 to June 2019) under various aerosol concentrations in the Red Sea and the Persian Gulf. The products were compared with ship-based AERONET (Aerosol Robotic Network) measurements conducted in the study area. The findings reveal that MODIS AOD products exhibit greater reliability during clear days, whereas CALIOP AOD products are more accurate in regions characterized by high aerosol concentrations. However, CALIOP's limited product resolution prevents it from providing adequate spatial-temporal coverage under heavy aerosol concentrations. To enhance the accuracy of MODIS AOD, this paper proposes a methodology based on various machine learning (ML) algorithms, including Random Forest (RF), Multi-layer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVR), and Bayesian network. The study explores the performance of MODIS and CALIOP AOD products during moderate and pollution days in the Persian Gulf and Red Sea regions. The ML models are ranked based on their accuracy, with the order being XGBoost > MLP > SVRrbf > RF > Bayesian > SVRlinear for the annual and two semi-annual networks. In other words, the Bayesian method demonstrates higher efficiency (R2 = 0.97, 0.91, and 0.90) in handling seasonal subsets. The proposed model's outcomes are validated using ship-based AERONET AOD data. By comparing the estimated AOD values with the ship-based AERONET AOD values and analyzing the overall correlation results, it is evident that machine learning techniques effectively provide accurate AOD estimates for moderate and pollution days. © 2023 Turkish National Committee for Air Pollution Research and Control
Remote Sensing Applications: Society and Environment (23529385) 33
Drought is a complex natural disaster characterized by unique features influenced by environmental factors, particularly at a regional scale. Remote Sensing (RS) indices have proven to be valuable in assessing drought conditions. In this study, we utilized the five most commonly used RS indices: Normalized Difference Vegetation Index (NDVI), Deviation/Anomaly of NDVI (NDVI-Dev/ANDVI), Temperature Condition Index (TCI), Vegetation Condition Index (VCI), and 2-band Enhanced Vegetation Index (EVI2). These indices were extracted over a 30-year period (1988–2017) using Google Earth Engine (GEE) for modeling the Standardized Precipitation Index (SPI) with various time-spans (1, 3, 6, 9, 12, and 24 months) as the Ground-Based (GB) drought indices. The models were trained from 1988 to 2014 and tested on data from 2015 to 2017. To enhance RS-based drought modeling over the complex and diverse study area of Iran, we proposed two different data clustering methods based on distinct environmental factors – climatic condition and land-cover type – and compared the results. The first method employed an enhanced-climate-based approach to improve upon the standard-climate-based method. This approach considered variations in the environment caused by seasonal changes in different climatic zones, which had received less attention in previous studies. Unique Support Vector Machine (SVM) models were trained using various clusters of inputs/outputs to assess the efficiency of the RS indices in predicting different drought conditions under various circumstances. Furthermore, we introduced an innovative data clustering method based on RS-derived land-cover similarity, which resulted in further improvements in drought modeling compared to agroclimatic zoning. The fusion-based drought modeling approach, using all RS indices as inputs in the enhanced-climate-based and land-cover-based methods, demonstrated an aggregated Overall Accuracy (OA) of 92.93% and 95.11% for predicting SPI-3, respectively. Notably, within the land-cover-based method, TCI exhibited the highest aggregated performance compared to other RS indices in predicting SPI-3 with an OA of approximately 95%. © 2023 Elsevier B.V.
Atmospheric Pollution Research (13091042) 15(7)
Aerosol Optical Depth (AOD) across various altitudes is crucial for gaining a comprehensive understanding of aerosol dynamics. However, current methodologies utilizing passive remote sensing and active sensors have limitations in providing precise vertical coverage. In our methodology, we introduce a Seasonal-Independent model employing Machine Learning (ML) algorithms to retrieve AOD values at both 1.5 km and 3 km layers. The propose approach is assessed the performance of various ML algorithms, including XGBoost, Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Regression (SVR). Remarkably, our study successfully overcame seasonal constraints, yielding impressive R2 values of 0.94, 0.93, 0.93, and 0.87 for the 1.5 km layer, and 0.83, 0.79, 0.82, and 0.78 for the 3 km layer across the mentioned models for 2017, 2018 and 2019 data. Evaluating the proposed Seasonal-Independent XGBoost model against CALIOP AOD values for the 2020 data, we observed substantial agreement with R2 values of 0.93 and 0.81, and minimal RMSE values of 0.002 and 0.004 for the AODs at 1.5 km and 3 km, respectively. Furthermore, a comparative analysis of trends between estimated and CALIOP AODs revealed a strong resemblance in both altitude layers. © 2024 Turkish National Committee for Air Pollution Research and Control
Earth Science Informatics (18650473) 16(3)pp. 2529-2543
Classifying urban land use/cover types poses significant challenges due to the complex and heterogeneous nature of urban landscapes. Recent years have witnessed notable advancements in land use/cover classification, driven by improvements in classification methods and the utilization of data from multiple sources. Deep learning networks, especially, have gained prominence in various image analysis tasks, including land use/cover classification. However, when it comes to urban areas, the classification of urban land use/cover encounters additional obstacles, including the complexity of classes, limited training data, and the presence of numerous urban categories. To overcome the limitations arising from similar classes and insufficient training data, we propose a novel approach that integrates hyperspectral and LiDAR data through a Conditional Generative Adversarial Network (CGAN) for semantic segmentation. Our methodology leverages the UNet + + generator and PatchGAN discriminator to achieve accurate segmentation. The CGAN-generated segmented images are then processed by a fully connected neural network (FCN) to classify 20 land use/cover classes. By validating our approach on the 2018 GRSS Data Fusion dataset, our study demonstrates its exceptional operational performance. The CGAN architecture outperforms previous algorithms in terms of class diversity and training data volume. By generating synthetic data that closely resembles the ground truth, the CGAN enhances the classification performance. Clear visual distinctions are observed among various urban features, such as vegetation, trees, buildings, roads, and cars. Classes associated with healthy grass, stressed grass, bare earth, and stadium seats achieve high accuracy. However, road and railway classes exhibit poorer performance due to their similarity with sidewalk, highway, major thoroughfare, and crosswalk classes. Overall, our study showcases a significant improvement in classification accuracy, achieving an approximate accuracy of 96.98% compared to the winning articles presented in the 2018 competition, which achieved accuracies of 64.95% and 76.54%, respectively. This improvement in accuracy can be attributed to the effective extraction and combination of high and low-level urban land cover/land use features within our proposed architecture. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Applied Soft Computing (15684946) 148
Although the high number of bands in hyperspectral remote sensing images increases their usefulness, it also causes some processing difficulty. In supervised classification, one problem is decreasing classification accuracy due to the insufficient training samples against the bands. A way to deal with this problem is the selection of appropriate bands by the metaheuristic methods. Because of the stochastic search, the selected bands differ in any implementation of a metaheuristic method. So, the results obtained from the classification of these different band subsets will also have some differences. In this study, a fusion-based approach has been proposed to improve the classification of hyperspectral remote sensing images by multiple implementations of a metaheuristic method for band selection. We have tested the proposed method using ten metaheuristic methods with different objective functions on four well-known datasets. The results show the proposed fusion-based approach successfully improves the classification accuracy in all experiments. The accuracy improvement varies depending on the metaheuristic method, the objective function, and the dataset and ranges from 0.4% to 15.7%. The proposed method improves the classification of complex datasets more and affects weaker objective functions considerably. The results also show the proposed method brings the accuracy of different metaheuristic methods close to each other and reduces the sensitivity of selecting the proper ones. Thus, an automated classification system can be obtained using a parameter-less method. © 2023 Elsevier B.V.
Geocarto International (17520762) 37(12)pp. 3565-3576
Building recognition is a core task for urban image classification (mapping), especially in optical high-resolution imagery. Convolutional Neural Networks (CNNs) have recently achieved unprecedented performance in the automatic recognition of objects (e.g. buildings, roads, or trees) in high-resolution imagery. Although these results are promising, questions remain about generalizability. This is a great challenge, as there is a wide variability in the visual characteristics of the building image scene across different geographic locations. CNNs are overfitted with limited and low diversity samples and are tested on the same or nearby geographic locations. In this work, we propose two scenarios with regard to transfer learning CNN features for building scene classification. We also investigate the generalizability of CNNs for building recognition across different geographic locations. The results of the two scenarios show that the final model, generalizable in different geographic locations, unseen areas. © 2021 Informa UK Limited, trading as Taylor & Francis Group.
Water Resources Management (09204741) 36(6)pp. 1813-1832
Accurate soil moisture (SM) data with continuous spatiotemporal distribution has greatly contributed to various analyses in the fields of agricultural dryness and irrigation, regional water cycle, soil erosion, and energy exchange. While, spatial and temporal resolutions are practically in conflict with each other, data fusion is considered to be efficient for accessing spatiotemporally high resolution data. In the present research to obtain daily surface SM at a spatial resolution of 100 m, an Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) was used by combining Landsat8 and Moderate resolution Imaging Spectroradiometer (MODIS) data. Furthermore, to improve the accuracy of SM retrieval, a novel scheme land surface temperature (LST)-vegetation index (VI) universal triangle was introduced to increase the LST retrieval accuracy using the TOPSIS method. This algorithm was also examined within two regions in Fars province in Iran. Simultaneously with the satellite passing through the study areas, SM of several points was measured by time-domain reflectometry (TDR). To evaluate the performance of the proposed method, the error metrics including the coefficient of determination (R2) and Root Mean Square Error (RMSE) were calculated between the in-situ SM measurements and those estimated. The resulted fusion SM was compared with the Landsat-derived and in-situ SM which reported lower (R2 = 0.73 and RMSE = 0.005cm3/cm3) and higher (R2 = 0.38 and RMSE = 0.048cm3/cm3) error values, respectively. The outcomes of the study indicated the high ability of the proposed fusion approach for achieving accurate and consistent SM monitoring by using the specified ESTARFM model, especially when the LST was obtained using the weighted average of several LST determination methods with TOPSIS method. © 2022, The Author(s), under exclusive licence to Springer Nature B.V.
IEEE Geoscience and Remote Sensing Letters (1545598X) 19
Getting the advantages of hyperspectral remote sensing images depends on overcoming the challenges posed by their large number of bands. One approach is selecting appropriate bands by the metaheuristic methods. Initial versions of these methods usually suffer from trapping into local optima, so they do not work optimally in selecting the best band subset. The number of training samples is also important in the band selection. With insufficient training samples, even improved metaheuristic methods do not yield the desired result. However, providing sufficient ground data as training samples is costly. In this letter, an improved Levy flight (LF)-based version of the genetic algorithm (GA) is developed and used to select bands in a semisupervised manner. The number of training samples in the proposed semisupervised method is increased based on spatial adjacency and spectral similarity simultaneously. Our results show that in cases where the initial version of the GA fails to select appropriate bands, our improved LF-based version introduces a band subset that yields the desirable classification result. Also, the classification accuracies have been improved considerably using our proposed semisupervised method. In some of our experiments using a small number of training samples, the accuracy improvement is near 17%. The proposed method has been effective in the case of sufficient training samples too. In this case, the accuracy improvement is near 11% in some experiments. © 2004-2012 IEEE.
Jalali, S. ,
Karbakhsh, M. ,
Momeni shahraki, M. ,
Taheri, M. ,
Amini, S. ,
Mansourian, M. ,
Sarrafzadegan, N. Environmental Health: A Global Access Science Source (1476069X) 20(1)
Background: Evidence concerning the impact of long-term exposure to fine Particulate Matter ≤2.5 μm (PM2.5) on Cardio-Vascular Diseases (CVDs) for those people subject to ambient air pollution in developing countries remains relatively scant. This study assessed the relationship of 15-year PM2.5 exposure with cardiovascular incidence and mortality rate in Isfahan province, Iran. Methods: The cohort comprised 3081 participants over 35 years old who were free of CVDs. They were selected through multi-stage cluster sampling in Isfahan, Iran. PM2.5 exposure was determined separately for each individual via satellite-based spatiotemporal estimates according to their residential addresses. In this context, CVD is defined as either fatal and non-fatal Acute Myocardial Infarctions (AMI) or stroke and sudden cardiac death. The incidence risk for CVD and the ensuing mortality was calculated based on the average PM2.5 exposure within a study period of 15 years using the Cox proportional hazards frailty model upon adjusting individual risk factors. The mean annual rate of PM2.5 and the follow-up data of each residential area were combined. Results: Mean three-year PM2·5 exposure for the cohort was measured at 45.28 μg/m3, ranging from 20.01 to 69.80 μg/m3. The median time period for conducting necessary follow-ups was 12.3 years for the whole population. Notably, 105 cardiovascular and 241 all-cause deaths occurred among 393,786 person-months (27 and 61 per 100,000 person-months, respectively). In well-adjusted models, 10 μg/m3 increase in PM2.5 corresponded to a 3% increase in the incidence rate of CVDs [0.95 CI = 1.016, 1.036] (in case of p = 0.000001 per 10 μg/m3 increase in PM2.5, the Hazard Ratio (HR) for AMI and Ischemic Heart Disease (IHD) was 1.031 [0.95 CI = 1.005, 1.057] and 1.028 [0.95 CI = 1.017, 1.039]), respectively. No consistent association was observed between PM2.5 concentration and fatal CVD (fatal AMI, fatal stroke, SCD (Sudden Cardiac Death)) and all-cause mortality. Conclusions: Results from analyses suggest that the effect of PM2.5 on cardiovascular disease occurrence was stronger in the case of older people, smokers, and those with high blood pressure and diabetes. The final results revealed that long-term exposure to ambient PM2.5 with high concentrations positively correlated with IHD incidence and its major subtypes, except for mortality. The outcome accentuates the need for better air quality in many countries. © 2021, The Author(s).
Journal of Aerosol Science (18791964) 158
Due to the high variation of aerosol in space and time, remote sensing has become an effective tool in aerosol optical depth (AOD) retrieval. Most of the satellite-based AOD retrieval methods using the radiative transfer model (RTM). RTMs help to establish a relation between AOD and the observed top-of-atmosphere (TOA) reflectance. Using look-up table-based approaches is among the commonly used methods for reducing the computational complexity in RTMs. Tuning steps for parameters in the LUTs influences computational cost and accuracy of retrieved satellite-based AOD. However, a comprehensive and quantitative assessment for the construction of LUT based on sensitivity analysis does not exist. In this paper, we present a sensitivity analysis approach called Morris one-at-a-time (MOAT) for identifying parameters that dominate model behaviour in the AOD retrieval process. We also use 8 cases to tune steps for each parameter in the look-up table. We investigate the influence of geometrical and physical parameters in the 6S RT code on radiance and reflectance. The result indicated that ground reflectance, aerosol model, and single scattering albedo are dominant parameters in LUT construction. Other geometrical and physical parameters have less impact on the simulated radiance and reflectance. Finally, we tuned proper steps for LUT construction based on the trend and behaviour of each parameter. The proposed method in this study can improve the accuracy of satellite-based AOD by constructing a LUT with a short processing time. © 2021 Elsevier Ltd
Infrared Physics and Technology (13504495) 109
One of the controversial issues in hyperspectral remote sensing methods for target detection is whether the feature selection will be useful. Generally, feature selection methods are divided into variance based and wavelength based methods. Variance based feature selection methods like information-theory-based methods may eliminate the distinctive features because the distinctive features probably are not statistical principal components. Distinctive features are crucial to distinguish target from background and are maintained in wavelength based methods which concentrate on wavelength information. However, beside to wavelength-based information, target spectrum fluctuations are also critical for target detection. In addition, the wavelength based methods are often time consuming iterative methods with high computational cost. This paper introduces a new feature selection method considering hyperspectral target spectrum. The proposed algorithm has been developed based on Chain coding idea. We proposed Chain Filtering, Chain Encoding, and Chain Statistics as filter, embedded, and wrapper feature selection methods. In this paper, Chain filtering, Chain statistics, and Chain encoding approaches have been compared with different types of feature selection methods such as Principle Component Analysis (PCA) and Minimum Noise Fraction (MNF). Numerical tests have been executed using 4 datasets including Cuprite Nevada and Jasper Ridge datasets from AVIRIS, Botswana, and local datasets of Isfahan province from Hyperion sensor and using Constrained Energy Minimization (CEM) target detection. The results show the accuracy of target detection applying the proposed feature selection method increases from 85% to about 92% for Kaolinite and from 77% to 96% for Buddingtonite in comparison with PCA for Cuprite dataset. Furthermore, the increments more than 5% and 17.5% will be achieved in comparison with MNF, respectively. The results have shown that not only the proposed method overcomes the accuracy decrement issue of feature selection in target detection, but also it improves target detection accuracy by eliminating non-informative features for target detection applications. So feature selection will be an efficient tool for target detection if the applied feature selection method picks out the distinctive features well. © 2020 Elsevier B.V.
Infrared Physics and Technology (13504495) 99pp. 222-230
In this paper, a novel adaptive algorithm for target detection in hyperspectral images (HSIs) is proposed. In a general classification, the proposed method belongs to the category of those methods which are not based on the statistical moments of the observed HSI (e.g. correlation or covariance matrix). The main processing burden of the proposed method is over a known set of spectral signatures. Assuming a linear spectral mixing model, the proposed method takes a set of spectral signatures which one of them relates to the target material and the others relate to the background materials. Based on an adaptive approach, the normalized least mean square (NLMS) adaptive algorithm is engaged to estimate a weight vector which is almost orthogonal to the background materials spectral signature whereas it makes an absolutely non-orthogonal pair with the target material spectral signature. The estimated weight vector is multiplied by the observed HSI to make the final decision. One synthetic and two real hyperspectral images are considered to evaluate the performance of the proposed method. The evaluation results show that the proposed method outperforms its counterparts. © 2019
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (21511535) 12(8)pp. 2627-2635
Automated building extraction from single, very-high-resolution (VHR) images is still one of the most challenging tasks for urban planning, estimating population, understanding urban dynamics, and many other applications. The complexities of building objects have caused the images of buildings to be oversegmented into multiple segments in the object-based image analysis (OBIA) method. Selecting the appropriate segmentation scale parameter is a major challenge in OBIA that influences the discriminative features extraction, especially for building objects. Furthermore, transferability of OBIA method is another challenge. Presently, convolutional neural networks (CNNs) are a well-understood tool for images scene classification. However, scene classification based on CNNs is still difficult due to the scale variation of the objects in VHR images. To meet these challenges, we propose a novel object-based deep CNN (OCNN) framework for VHR images. The datasets used for testing were Vaihingen (Germany) aerial images and a Tunis Worldview-2 (WV2) satellite imagery. Experimental results prove that our framework is extensible to different types of the image with the same sensor or another sensor (for example WV2) with once-fine-tuning. In addition, our framework extracts the different types of building with respect to size, color, material, spectral similarity to roads, and complex backgrounds. Quantitative evaluation at the object level demonstrated that the proposed framework could yield promising results (average precision 0.88, recall 0.92, quality 0.82, F-score 0.90, overall accuracy 0.95, and Kappa coefficient 0.90). Comparative experimental results indicate that our proposed OCNN significantly outperforms the traditional method for building extraction. © 2008-2012 IEEE.
Signal Processing (01651684) 155pp. 108-129
Kalman filter (KF) as a linear estimator which is used in super-resolution (SR) problems, suffers from high computational costs and storage requirements. To gain appreciable success in the elimination of these two challenges, this paper advances a SR framework employing KF in the frequency domain, while no resort is made to any approximations or extra assumptions in the dynamic system modeling and statistical matrices. Generally, previous KF-based SR methods organized the system with huge-sized matrices in the spatial domain, following which they tried to reduce the system dimension using approximation and/or limitation on point spread function (PSF). In this study, first, several small-dimension dynamic systems are separately made in the frequency domain supporting space-invariant PSFs of an arbitrary form and size. Then, the acquired small-dimension KF estimators are applied rather than the traditional huge-dimension one. These will greatly reduce computational complexity, decrease storage requirements allowing parallel implementation as well. Furthermore, our proposed SR framework can be used to produce high resolution image of an expedient size, that is, a scalable SR. Experimental results with both simulated and real world sequences indicate that our proposed framework works more effectively than the other compared methods, especially in fine details restoration. © 2018 Elsevier B.V.
International Journal of Remote Sensing (13665901) 39(3)pp. 684-703
Multiresolution segmentation (MRS) is one of the most commonly used image segmentation algorithms in the remote-sensing community. This algorithm has three user-defined parameters: scale, shape, and compactness. The scale parameter (SP) is the most crucial one in determining the average size of the image segments generated. Since setting this parameter typically requires a trialand- error process, automatically estimating it can expedite the segmentation process. However, most of automatic approaches are still iterative and can lead to a time-consuming process. In this article, we propose a new, non-iterative framework for estimating the SP with an emphasis on extracting individual urban buildings. The basis of the proposed method is to investigate the feasibility of associating the size of urban buildings with a corresponding ‘optimal’ (or at least reasonable) SP using an explicit mathematical equation. Using the proposed method, these two variables are related to each other by constructing a mathematical (regression) model. In this framework, the independent variables were chosen to be the typical size of buildings in a given urban area and the spatial resolution of the image under consideration; and the dependent variable was chosen to be the corresponding optimal SP. To assess the potential of the proposed approach, two regression models that yielded explicit equations (i.e. degree-2 polynomial (DP), and regression tree (RT)) were employed. In addition, as a sophisticated and versatile nonlinear model, support vector regression (SVR) was utilized to further measure the performances of DP and RT models compared with it. According to the comparisons, the DP model was selected as a representative of the proposed approach. In the end, to evaluate the proposed methodology, we also compared the results derived from the DP model with those derived from the Estimation of Scale Parameter (ESP) tool. Based on our experiments, not only did the DP model produce acceptable results, but also it outperformed ESP tool in this study for extracting individual urban buildings. © 2017 Informa UK Limited, trading as Taylor and Francis Group. All rights reserved.
Environmental Monitoring And Assessment (01676369) 190(4)
Urban expansion can cause extensive changes in land use and land cover (LULC), leading to changes in temperature conditions. Land surface temperature (LST) is one of the key parameters that should be considered in the study of urban temperature conditions. The purpose of this study was, therefore, to investigate the effects of changes in LULC due to the expansion of the city of Isfahan on LST using landscape metrics. To this aim, two Landsat 5 and Landsat 8 images, which had been acquired, respectively, on August 2, 1985, and July 4, 2015, were used. The support vector machine method was then used to classify the images. The results showed that Isfahan city had been encountered with an increase of impervious surfaces; in fact, this class covered 15% of the total area in 1985, while this value had been increased to 30% in 2015. Then LST zoning maps were created, indicating that the bare land and impervious surfaces categories were dominant in high temperature zones, while in the zones where water was present or NDVI was high, LST was low. Then, the landscape metrics in each of the LST zones were analyzed in relation to the LULC changes, showing that LULC changes due to urban expansion changed such landscape properties as the percentage of landscape, patch density, large patch index, and aggregation index. This information could be beneficial for urban planners to monitor and manage changes in the LULC patterns. © 2018, Springer International Publishing AG, part of Springer Nature.
Journal of the Indian Society of Remote Sensing (09743006) 46(2)pp. 169-178
With the advent of high spatial resolution satellite imagery, automatic and semiautomatic building extractions have turned into one of the outstanding research topics in the field of remote sensing and machine vision. To this date, various algorithms have been presented for extracting the buildings from satellite images. Such methods lend their bases to diverse criteria such as radiometric, geometric, edge detection, and shadow. In this paper, a novel object based approach has been proposed for automatic and robust detections as well as extraction of the building in high spatial resolution images. To fulfill this, we simultaneously made use of both stable and variable features. While the former can be derived from inherent characteristics of the buildings, the latter is extracted using a feature analysis tool. In addition, a novel perspective has been recommended to boost the automation degree of the segmentation part in the object based analysis of remote sensing imagery. The proposed method was applied to a QuickBird imagery of an urban area in Isfahan city and the results of the quantitative evaluation demonstrated that the proposed method could yield promising results. Moreover, in another section of this study, for assessing the algorithm transferability, the rule set was implemented to a part of the WorldView image of Yazd city, proving that the proposed approach is capable of transferability in different types of case studies. © 2017, Indian Society of Remote Sensing.
Iranian Journal of Science and Technology - Transactions of Electrical Engineering (23641827) 42(1)pp. 95-105
Although various building detection algorithms from high spatial resolution satellite (HSRS) images have been presented in recent years, there are yet some difficulties to detect building boundaries for mapping purposes. The present study aims to propose a new approach to detect building boundaries from HSRS images by focusing on higher detection rates. The approach utilizes the idea of object-based image processing. However, it has an innovative vision using image edges instead of traditional image segments as objects. To evaluate the efficiency of the proposed approach, two datasets which have different contrast between building and non-building areas, are used: the first dataset has a high contrast between building and non-building areas (HC) and second has a low contrast (LC). The results are compared with the results of two segmentation-based algorithms, i.e., classification based on edge-based segmentation (CBES) and classification based on multi-resolution segmentation (CBMS). The comparisons indicate higher efficiency of the proposed approach for the HC dataset with 6–14% higher detection rate (lower omission error) than the two segmentation-based algorithms. For the LC dataset, the proposed approach is already more efficient than CBMS with 10–25% higher detection rate. However, it has lower efficiency than CBES with 15–36% higher omission errors. Though, the proposed approach is generally more robust than CBES and CBMS algorithms based on standard deviation values of evaluation metrics. © 2018, Shiraz University.
Digital Signal Processing: A Review Journal (10954333) 72pp. 19-43
As there are data redundancies in successive frames in a multi-frame super resolution (SR) algorithm, one can expect that discarding some of these superfluous frames would have no impact on the quality of the high resolution (HR) output image. The present paper presents an efficient algorithm for selecting the proper combination of the minimum frames required for multi-frame SR algorithms so as to not only preserve the quality of the obtained HR output, but also reduce the SR procedure complexity and memory. To achieve this, the present study first seeks to prove that minimizing the spectral interference between the selected frames for SR procedure will result in maximizing the HR output power. Then, the criterion for measuring the Upper Bound on Spectral Interferences (UBSI) among the selected frames for SR procedure is presented; the formulation is expressed in such a way that it can be extended to global sub-pixel translations between frames. Our proposed frame selection algorithm evaluates all candidate combinations from input frames so that the best option capable of minimizing the UBSI can be selected. In order to evaluate our proposed frame selection algorithm, five well-known SR image reconstruction methods are applied both in four standard simulated images and in three well known real video sequences, employing two different procedures: Using our proposed frame selection algorithm and otherwise. The obtained results indicate that when our proposed frame selection algorithm is applied, the quality of the HR output images is preserved tantamount to considering all available frames. Besides, the computational complexity of the SR algorithms is dramatically reduced adopting the proposed frame selection algorithm, for the number of frames engaged in the SR is diminished. Also compared with the SR algorithms presented in the literature, our proposed frame selection method takes relatively negligible time to execute. © 2017 Elsevier Inc.
Sustainable Cities and Society (22106715) 39pp. 650-661
Urban development and consequently, the growth of construction can result in changing the climatic parameters, such as land surface temperature (LST). This study was conducted in the central part of Isfahan province to investigate changes in thermal patterns during 1985–2015 time period. To generate land-use/land-cover maps and LST, Landsat-TM, ETM+ and OLI/TIRS data were utilized. The results demonstrated that impervious surfaces had been increased by 2.8 times from 1985 to 2015. The results also indicated a negative correlation between LST and the Normalized Difference Vegetation Index (NDVI) in hot months. This research also focused on exploring the occurrence of surface urban heat island (SUHI) in hot and cold months in the city of Isfahan. Buffer zones in various widths were created to measure SUHI. In August 1985, in buffers of 1 km–3 km and in July 1992, in all buffers, SUHI was observed. In contrast, in July 2001, in buffers of 3 km–10 km and in July 2015, in all buffers, LST of Isfahan rural area was higher than that of city, showing surface urban cool island (SUCI). The results also demonstrated that the urban area was cooler than the surrounding rural area in the cold months. © 2018 Elsevier Ltd
CTIT workshop proceedings series (16821750) 42(4W4)pp. 111-116
This paper presents an automatic method to extract road centerline networks from high and very high resolution satellite images. The present paper addresses the automated extraction roads covered with multiple natural and artificial objects such as trees, vehicles and either shadows of buildings or trees. In order to have a precise road extraction, this method implements three stages including: classification of images based on maximum likelihood algorithm to categorize images into interested classes, modification process on classified images by connected component and morphological operators to extract pixels of desired objects by removing undesirable pixels of each class, and finally line extraction based on RANSAC algorithm. In order to evaluate performance of the proposed method, the generated results are compared with ground truth road map as a reference. The evaluation performance of the proposed method using representative test images show completeness values ranging between 77% and 93%.
Chemical Engineering and Technology (09307516) 40(6)pp. 1149-1157
An experimental study on NO removal via UV/H2O2 process was conducted in a semi-continuous bubble-column reactor and the effect of some operation parameters including NO initial concentration and gas flow rates on removal efficiency was investigated. Applying UV light increased the efficiency significantly. The steady-state removal efficiency was found to be higher at the lower gas flow rates. The bubble size as an important factor in mass transfer calculations and modeling procedure was determined at different gas flow rates using bubble photographs and image processing technique. In the ranges of flow rates studied here, the gas flow rate had no significant effect on the bubble diameter. A mathematical model was developed to describe the NO removal process. The model predictions were compared with existing experimental data, confirming a good agreement of the data. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
International Journal of Remote Sensing (13665901) 37(21)pp. 5234-5248
Building extraction from high-resolution satellite images (HRSI) in urban areas is an intricate problem. Recent studies proposed different methods during 2005–2015. However, in HRSI, they have not investigated the effects of challenges altogether. This paper studies the effects of non-building features which are the main drawbacks in building extraction. To overcome each challenge, it reviews recent strategies between 2005 and 2015. The pros and cons of each strategy are discussed, and proper strategies are combined to generate hybrid methods. Lower cost and fewer strategies are efficient attributes to recognize the best hybrid methods. Hybrid methods can be useful for different case studies in the future. © 2016 Informa UK Limited, trading as Taylor & Francis Group.
Remote Sensing Letters (2150704X) 7(4)pp. 368-377
Soil evaporation transfer coefficient (ha) is an effective means of estimating surface soil moisture from moderate-resolution imaging spectroradiometer (MODIS) imagery. This coefficient is a function of three variables: air temperature, land surface temperature and dry soil temperature. The first two variables can easily be obtained from different sources, whereas dry soil temperature cannot be determined as easily as the other ones, particularly over partially vegetated areas. In this paper, to enhance the capability of ha in estimating soil moisture, we propose to use the combination of land surface temperature (LST) and normalized difference vegetation index (NDVI) to estimate dry soil temperature over partially vegetated areas as well as bare soil areas; this combination is known as LST-NDVI feature space in the literature. The underlying assumption of the proposed method is that at any given pixel over partially vegetated or bare soil areas, dry soil temperature is approximately equivalent to the maximum LST derived from LST-NDVI triangle space. The results showed that calculating hausing dry soil temperature derived from the triangle space can result in more reliable estimation of soil moisture over bare soil and partially vegetated areas. © 2016 Taylor & Francis.
CTIT workshop proceedings series (16821750) 41pp. 337-343
Airborne LiDAR (Light Detection and Ranging) data have a high potential to provide 3D information from trees. Most proposed methods to extract individual trees detect points of tree top or bottom firstly and then using them as starting points in a segmentation algorithm. Hence, in these methods, the number and the locations of detected peak points heavily effect on the process of detecting individual trees. In this study, a new method is presented to extract individual tree segments using LiDAR points with 10cm point density. In this method, a two-step strategy is performed for the extraction of individual tree LiDAR points: finding deterministic segments of individual trees points and allocation of other LiDAR points based on these segments. This research is performed on two study areas in Zeebrugge, Bruges, Belgium (51.33° N, 3.20° E). The accuracy assessment of this method showed that it could correctly classified 74.51% of trees with 21.57% and 3.92% under-and over-segmentation errors respectively.
International Association of Geodesy Symposia (21979359) 140pp. 127-130
In recent decades land subsidence and its associated fissures have been observed in many plain aquifers of Iran. Knowledge of the deformation field in groundwater basins is of basic interest for understanding the cause and mechanism of deformation phenomenon, and for mitigating hazard related to it. In this paper the result of Envisat InSAR time-series analysis for monitoring land subsidence in Mahyar Plain, Central Iran, is presented. Longterm extraction of groundwater, which started in 1970 with the development of agriculture in this area, has caused substantial subsidence and formation of many earth fissures in Mahyar. Our analysis indicates significant subsidence bowl south of Mahyar plain with an elliptical pattern directed northwest–southeast along the axis of the plain. The velocity map obtained by the time-series analysis of InSAR data shows a maximum subsidence velocity of _9 cm/year in the line of sight from the ground to the satellite in the year 2003–2006. © Springer International Publishing Switzerland 2015.
International Journal of Remote Sensing (13665901) 35(13)pp. 5094-5119
In studies of high-resolution satellite (HRS) imagery, the extraction of man-made features such as roads and buildings has become quite attractive to the photogrammetric and remote-sensing communities. The extraction of 2D images from buildings in a dense urban area is an intricate problem, due to the variety of shapes, sizes, colours, and textures. To overcome the problem, many case studies have been conducted; however, they have frequently contained isolated buildings with low variations of shapes and colours and/or high contrast with respect to adjacent features. As an alternative, this study uses continuous building blocks along with high variation in shape, colour, radiance, size, and height. In addition, some non-building features include either the same or similar materials to that of building rooftops. Thus, there is low contrast between building and non-building features. The core components of the algorithm are: (1) multispectral binary filtering, (2) sub-clustering and single binary filtering, (3) multi-conditional region growing, and (4) post-processing. This approach was applied to a dense urban area in Tehran, Iran, and a semi-urban area in Hongshan district, Wuhan city, central China. A quantitative comparison was carried out between the proposed and three other algorithms for the Wuhan case study. GeoEye multispectral imagery was used in both case studies. The results show that the proposed algorithm correctly extracted the majority of building and non-building features in both case studies. The short running time of this algorithm along with precise manual editing can generate accurate building maps for practical applications. © 2014 Taylor & Francis.
Arabian Journal of Geosciences (discontinued) (18667538) 7(5)pp. 1891-1897
Atmospheric water vapor validation needs simultaneous, well-defined, and independent information which are not easily available causing limitations in the development of remote sensing water vapor retrieval algorithms. This study is concerned with the retrieval of total atmospheric water vapor content and its validation. A band ratio method has been used to estimate the water vapor content based on Moderate Resolution Imaging Spectroradiometer (MODIS) Near InfraRed (NIR) data. The method uses MODIS bands 17, 18, and 19 as NIR bands and band 2 to remove the land cover reflectance. Furthermore, the Atmospheric Infrared Sounder (AIRS) has been used for both algorithm development and analysis of the results. The method has been modified to take into account the dry condition of the central parts of Iran. Using some various datasets, the method is implemented and evaluated quantitatively. The validation of the water vapor estimates has been undertaken by an analysis of AIRS data. The validation results shows error as low as 9 % for the estimated water vapor using the MODIS NIR band ratio method. © 2013 Saudi Society for Geosciences.
Photogrammetric Engineering and Remote Sensing (00991112) 80(6)pp. 519-528
This paper reviews and evaluates four building extraction algorithms including two pixel-based and two object-based methods using a diverse set of very high spatial resolution imagery. The applied images are chosen from different places (the cities of Isfahan, Tehran, and Ankara) and different sensors (QuickBird and GeoEye-1), which are diverse in terms of building shape, size, color, height, alignment, brightness, and density. The results indicate that the performance and the reliability of two object-based algorithms are better than pixel-based algorithms; about 10 percent to 15 percent better for the building detection rate and 6 percent to 10 percent better for the reliability rate. However, in some cases, the detection rate of pixel-based algorithms has been greater than 80 percent, which is a satisfactory result. On the other hand, segmentation errors can cause limitations and errors in the object-based algorithms, so that the commission error of object-based algorithms has been higher than pixel-based algorithms in some cases. © 2014 American Society for Photogrammetry and Remote Sensing.
Drying Technology (15322300) 32(14)pp. 1655-1663
An image processing technique was used to predict the size distribution of the high speed, fine droplets at downstream of an air blast atomizer. The spray visualization setup consisted of UV lamps as light source, a stroboscope for slowing down the droplet motion, and a digital camera to capture the droplet images. The experiments were carried out at different liquid flow rates with various nozzle diameters. Two key unknown parameters (spray half angle and dispersion angle) of the air blast atomizer model in Fluent were obtained from these experiments. Using the obtained parameters and other structural parameters, the spray modeling was performed, and the Rosin–Rammler distribution was obtained and compared with those obtained from image processing technique through a diagnostic matrix. Regarding the kappa value, the agreement between predictions of the Fluent model and the image processing technique was moderate. © 2014, Copyright Taylor & Francis Group, LLC.
CTIT workshop proceedings series (16821750) 40(1W3)pp. 453-458
Determination of the maximum ability for feature extraction from satellite imageries based on ontology procedure using cartographic feature determination is the main objective of this research. Therefore, a special ontology has been developed to extract maximum volume of information available in different high resolution satellite imageries and compare them to the map information layers required in each specific scale due to unified specification for surveying and mapping. ontology seeks to provide an explicit and comprehensive classification of entities in all sphere of being. This study proposes a new method for automatic maximum map feature extraction and reconstruction of high resolution satellite images. For example, in order to extract building blocks to produce 1:5000 scale and smaller maps, the road networks located around the building blocks should be determined. Thus, a new building index has been developed based on concepts obtained from ontology. Building blocks have been extracted with completeness about 83%. Then, road networks have been extracted and reconstructed to create a uniform network with less discontinuity on it. In this case, building blocks have been extracted with proper performance and the false positive value from confusion matrix was reduced by about 7%. Results showed that vegetation cover and water features have been extracted completely (100%) and about 71% of limits have been extracted. Also, the proposed method in this article had the ability to produce a map with largest scale possible from any multi spectral high resolution satellite imagery equal to or smaller than 1:5000.
CTIT workshop proceedings series (16821750) 39pp. 57-60
Automatic building extraction from high resolution satellite imagery is considered as an important field of research in remote sensing and machine vision. Many algorithms for extraction of buildings from satellite images have been presented so far. These algorithms mainly have considered radiometric, geometric, edge detection and shadow criteria approaches to perform the building extraction. In this paper, we propose a novel object based approach for automatic and robust detection and extraction of building in high spatial resolution images. To achieve this goal, we use stable and variable features together. Stable features are derived from inherent characteristics of building phenomenon and variable features are extracted using SEparability and THresholds analysis tool. The proposed method has been applied on a QuickBird imagery of an urban area in Isfahan city and visual validation demonstrates that the proposed method provides promising results. © 2012 ISPRS.
Photogrammetric Engineering and Remote Sensing (00991112) 74(5)pp. 637-646
Estimation of land surface temperature and emissivity has taken on a great deal of importance in recent remote sensing studies. The estimation of temperature and emissivity from thermal radiation observations is involved with an under-determined equation set. In this study, an approach is proposed to overcome the problem based on statistical theory of observations and error propagation. First, the under-determined radiance equations have been completed using two NDVI-based equations for the mean and difference emissivities as constraint equations. The two added constraint equations provide the possibility of weighted least squares solution to estimate temperature and emissivity from the over-determined equation set simultaneously. The weights have been calculated based on the uncertainty of each of the equations. The weighting basis of the proposed approach allows statistical control on the uncertainties. The advantages of the weighted least squares solution which is contributed by this study are weighted observations used in the solution, the uncertainty considerations of the used observations, uncertainty propagation control, statistical standard deviation estimation for the unknowns, statistical quality control criteria, and the opportunity of systematic error detection. The numerical efficiency of the proposed approach is examined using a great number of simulated sample data. Then, the proposed approach is validated using the in situ measurements of land surface temperature. The validations accompanied by some statistical tests represent the acceptable performance and accuracy of the proposed approach (approximately 0.5°K for LST standard deviation and approximately 0.0075 for standard deviation of the bands 31 and 32 emissivities). In addition, the simplicity and robustness of the proposed approach may be regarded as a considerable achievement. © 2008 American Society for Photogrammetry and Remote Sensing.
CTIT workshop proceedings series (16821750) 37pp. 523-528
One of the most important parameters in all surface-atmosphere interactions (e.g. energy fluxes between the ground and the atmosphere) is atmospheric water vapor. It is also an indicator among others to modeling the energy balance at the Earth's surface. Total atmospheric water vapor content is an important parameter in some remote sensing applications especially land surface temperature (LST) estimation. As such, total atmospheric water vapor content and LST are used as key parameters for a variety of environmental studies and agricultural ecological applications. Estimation of an accurate LST requires the atmospheric water vapor content estimation. This study is concerned with retrieving total atmospheric water vapor content (W) using Moderate Resolution Imaging Spectrometer (MODIS). We have used a ratio technique to estimate the column water vapor based on MODIS data. However Atmospheric Infrared Sounder (AIRS) column water vapor and AIRS MMR near surface water vapor have been taken into account to calculate coefficients of the equation in the ratio technique. Then the accuracy of the results was examined using independent data set. It is concluded in this study that MODIS data is appropriate in mapping water vapor content as a suitable alternative to meteorological stations measurement data. © 2008 International Society for Photogrammetry and Remote Sensing. All rights reserved.
Remote Sensing of Environment (00344257) 106(2)pp. 190-198
Surface emissivity estimation is a significant factor for the land surface temperature estimation from remotely sensed data. For fully vegetated surfaces, the emissivity estimation is performed in a simple manner since the emissivity is relatively uniform. However, for arid land with sparse vegetation, the estimation is more complicated since the emissivity of the exposed soil and rock is highly variable. In this study, mean and difference emissivity for bands 31 and 32 of MODIS sensor have been derived based on NDVI values. First, the NDVI thresholds have been determined to separate bare soil, partially vegetated soil and fully vegetated land. Then regression relations have been derived to estimate mean and difference emissivity of the bare soil samples and partially vegetated surfaces. A constant emissivity is also used for fully vegetated area. Along with the correlations, standard deviations of the regression relations have been examined for a set of representative soil types. Standard deviations smaller than 0.003 in mean emissivity and smaller than 0.004 in difference emissivity are resulted in regression linear relations. Evaluation of the NDVI derived regression relations has been performed using the results of MODIS Day/Night Land Surface Temperature (LST) algorithm on a pair of MODIS images. Using around 45,500 pixels with different soil and land cover types, emissivity of each pixel in bands 31 and 32 have been estimated. The calculated emissivities have been compared with emissivities calculated by MODIS Day/Night LST algorithm. Biases and standard deviations of NDVI-based relations show relatively high agreement for mean and difference emissivity relations with Day/Night method results. It may be concluded that the proposed algorithm can be used as a rather simple alternative to complex emissivity estimation algorithms. © 2006 Elsevier Inc. All rights reserved.
Survey Review (17522706) 38(296)pp. 165-173
It is possible to use single frequency GPS receivers to estimate the Total Electron Content (TEC). In this research, we improved an algorithm presented by Giffard [2], that is based on a least squares solution. We investigated the effect of the use of different weights (elevation of satellites, signal to noise ratio, combination of elevation and signal to noise ratio) and different block sizes on TEC estimates. We found that these parameters had a significant impact on TEC estimates based on this algorithm. Our research is based on observations at the GPS site of the Esfahan University made with single frequency 12-channel Leica System 500 receivers.
