Ganjirad, M.,
Delavar m.r., M.R.,
Bagheri, H.,
Azizi, M.M. Sustainable Cities and Society (22106715)120
This paper presents a novel framework for prioritizing urban green space development in Tehran using diverse socio-economic, environmental, and sensitivity indices. The indices were derived from various sources including Google Earth Engine, air pollution measurements, municipal reports and the Weather Research & Forecasting (WRF) model. The WRF model was used to estimate the air temperature at a 1 km resolution due to insufficient meteorological stations, yielding RMSE and MAE values of 0.96 °C and 0.92 °C, respectively. After data preparation, several machine learning models were used for binary vegetation cover classification including XGBoost, LightGBM, Random Forest (RF) and Extra Trees. RF achieved the highest performance, exceeding 94 % in Overall Accuracy, Recall, and F1-score. Then, the probability of areas lacking vegetation cover was assessed using socio-economic, environmental and sensitivity indices. This resulted in the RF generating an urban green space development prioritization map. Feature Importance Analysis revealed that the most significant indices were nightly land surface temperature (LST) and sensitive population. Finally, the framework performance was validated through microclimate simulation to assess the critical areas after and before the green space development by green roofs. The simulation demonstrated reducing air temperature by up to 0.67 °C after utilizing the green roof technology in critical areas. As a result, this framework provides a valuable tool for urban planners to develop green spaces. © 2025
Okolie, C.,
Adeleke, A.,
Mills, J.,
Smit, J.,
Maduako, I.,
Bagheri, H.,
Komar, T.,
Wang, S. International Journal of Image and Data Fusion (19479832)15(4)pp. 430-460
There has been a rapid evolution of tree-based ensemble algorithms which have outperformed deep learning in several studies, thus emerging as a competitive solution for many applications. In this study, ten tree-based ensemble algorithms (random forest, bagging meta-estimator, adaptive boosting (AdaBoost), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), light gradient boosting (LightGBM), histogram-based GBM, categorical boosting (CatBoost), natural gradient boosting (NGBoost), and the regularised greedy forest (RGF)) were comparatively evaluated for the enhancement of Copernicus digital elevation model (DEM) in an agricultural landscape. The enhancement methodology combines elevation and terrain parameters alignment, with feature-level fusion into a DEM enhancement workflow. The training dataset is comprised of eight DEM-derived predictor variables, and the target variable (elevation error). In terms of root mean square error (RMSE) reduction, the best enhancements were achieved by GBM, random forest and the regularised greedy forest at the first, second and third implementation sites respectively. The computational time for training LightGBM was nearly five-hundred times faster than NGBoost, and the speed of LightGBM was closely matched by the histogram-based GBM. Our results provide a knowledge base for other researchers to focus their optimisation strategies on the most promising algorithms. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Ecological Informatics (15749541)80
Land Use and Land Cover (LULC) maps are vital prerequisites for weather prediction models. This study proposes a framework to generate LULC maps based on the U.S. Geological Survey (USGS) 24-category scheme using Google Earth Engine. To realize a precise LULC map, a fusion of pixel-based and object-based classification strategies was implemented using various machine learning techniques across different seasons. For this purpose, feature importance analysis was conducted on the top classifiers considering the dynamic (seasonal) behavior of LULC. The results showed that ensemble approaches such as Random Forest and Gradient Tree Boosting outperformed other algorithms. The results also demonstrated that the object-based approach had better performance due to the consideration of contextual features. Finally, the proposed fusion framework produced a LULC map with higher accuracy (overall accuracy = 94.92% and kappa coefficient = 94.19%). Furthermore, the performance of the generated LULC map was assessed by applying it to the Weather Research and Forecasting (WRF) model for downscaling wind speed and 2-m air temperature (T2). The assessment indicated that the generated LULC map effectively reflected real-world conditions, thereby impacting the estimation of wind speed and T2 fields by WRF. Statistical assessments demonstrated enhancements in RMSE by 0.02 °C, MAE by 1 °C, and Bias by 0.03 °C for T2. Additionally, there was an improvement of 0.06 m/s in MAE for wind speed. Consequently, the framework can be implemented to produce accurate and up-to-date high-resolution LULC maps in various geographical areas worldwide. The source codes corresponding to this research paper are available on GitHub via https://github.com/Mganjirad/GEE-LULC-WRF. © 2023
Urban Climate (22120955)57
Climate models lack the necessary resolution for urban climate studies, requiring computationally intensive processes to estimate high resolution air temperatures. In contrast, Data-driven approaches offer faster and more accurate air temperature downscaling. This study presents a data-driven framework for downscaling air temperature using publicly available outputs from urban climate models, specifically datasets generated by UrbClim. The proposed framework utilized morphological features extracted from LiDAR data. To extract urban morphological features, first a three-dimensional building model was created using LiDAR data and deep learning models. Then, these features were integrated with meteorological parameters such as wind, humidity, etc., to downscale air temperature using machine learning algorithms. The results demonstrated that the developed framework effectively extracted urban morphological features from LiDAR data. Deep learning algorithms played a crucial role in generating three-dimensional models for extracting the aforementioned features. Also, the evaluation of air temperature downscaling results using various machine learning models indicated that the LightGBM model had the best performance with an RMSE of 0.352 °K and MAE of 0.215 °K. Furthermore, the examination of final air temperature maps derived from downscaling showed that the developed framework successfully estimated air temperatures at higher resolutions, enabling the identification of local air temperature patterns at street level. The corresponding source codes are available on GitHub: https://github.com/FatemehCh97/Air-Temperature-Downscaling. © 2024 Elsevier B.V.
Earth Science Informatics (18650473)16(1)pp. 753-771
One of the techniques for estimating the surface particle concentration with a diameter of fewer than 2.5 micrometers (PM2.5) is using aerosol optical depth (AOD) products. Different AOD products are retrieved from various satellite sensors, like MODIS and VIIRS, by various algorithms, such as Deep Blue and Dark Target. Therefore, they don’t have the same accuracy and spatial resolution. Additionally, the weakness of algorithms in AOD retrieval reduces the spatial coverage of products, particularly in cloudy or snowy areas. Consequently, for the first time, the present study investigated the possibility of fusing AOD products from observations of MODIS and VIIRS sensors retrieved by Deep Blue and Dark Target algorithms to estimate PM2.5 more accurately. For this purpose, AOD products were fused by machine learning algorithms using different fusion strategies at two levels: the data level and the decision level. First, the performance of various machine learning algorithms for estimating PM2.5 using AOD data was evaluated. After that, the XGBoost algorithm was selected as the base model for the proposed fusion strategies. Then, AOD products were fused. The fusion results showed that the estimated PM2.5 accuracy at the data level in all three metrics, RMSE, MAE, and R2, was improved (R2= 0.64, MAE= 9.71μgm3, RMSE= 13.51μgm3). Despite the simplicity and lower computational cost of the data level fusion method, the spatial coverage did not improve considerably due to eliminating poor quality data through the fusion process. Afterward, the fusion of products at the decision level was followed in eleven scenarios. In this way, the best result was obtained by fusing Deep Blue products of MODIS and VIIRS sensors (R2= 0.81, MAE= 7.38μgm3, RMSE= 10.08μgm3). Moreover, in this scenario, the spatial coverage was improved from 77% to 84%. In addition, the results indicated the significance of the optimal selection of AOD products for fusion to obtain highly accurate PM2.5 estimations. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
ISPRS International Journal of Geo-Information (22209964)12(11)
Crop classification using remote sensing data has emerged as a prominent research area in recent decades. Studies have demonstrated that fusing synthetic aperture radar (SAR) and optical images can significantly enhance the accuracy of classification. However, a major challenge in this field is the limited availability of training data, which adversely affects the performance of classifiers. In agricultural regions, the dominant crops typically consist of one or two specific types, while other crops are scarce. Consequently, when collecting training samples to create a map of agricultural products, there is an abundance of samples from the dominant crops, forming the majority classes. Conversely, samples from other crops are scarce, representing the minority classes. Addressing this issue requires overcoming several challenges and weaknesses associated with the traditional data generation methods. These methods have been employed to tackle the imbalanced nature of training data. Nevertheless, they still face limitations in effectively handling minority classes. Overall, the issue of inadequate training data, particularly for minority classes, remains a hurdle that the traditional methods struggle to overcome. In this research, we explore the effectiveness of a conditional tabular generative adversarial network (CTGAN) as a synthetic data generation method based on a deep learning network, for addressing the challenge of limited training data for minority classes in crop classification using the fusion of SAR-optical data. Our findings demonstrate that the proposed method generates synthetic data with a higher quality, which can significantly increase the number of samples for minority classes, leading to a better performance of crop classifiers. For instance, according to the G-mean metric, we observed notable improvements in the performance of the XGBoost classifier of up to 5% for minority classes. Furthermore, the statistical characteristics of the synthetic data were similar to real data, demonstrating the fidelity of the generated samples. Thus, CTGAN can be employed as a solution for addressing the scarcity of training data for minority classes in crop classification using SAR–optical data. © 2023 by the authors.
Environmental Monitoring And Assessment (01676369)195(3)
High-resolution mapping of PM2.5 concentration over Tehran city is challenging because of the complicated behavior of numerous sources of pollution and the insufficient number of ground air quality monitoring stations. Alternatively, high-resolution satellite Aerosol Optical Depth (AOD) data can be employed for high-resolution mapping of PM2.5. For this purpose, different data-driven methods have been used in the literature. Recently, deep learning methods have demonstrated their ability to estimate PM2.5 from AOD data. However, these methods have several weaknesses in solving the problem of estimating PM2.5 from satellite AOD data. In this paper, the potential of the deep ensemble forest method for estimating the PM2.5 concentration from AOD data was evaluated. The results showed that the deep ensemble forest method with R2= 0.74 gives a higher accuracy of PM2.5 estimation than deep learning methods (R2= 0.67) as well as classic data-driven methods such as random forest (R2= 0.68). Additionally, the estimated values of PM2.5 using the deep ensemble forest algorithm were used along with ground data to generate a high-resolution map of PM2.5. Evaluation of produced PM2.5 map revealed the good performance of the deep ensemble forest for modeling the variation of PM2.5 in the city of Tehran. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
Advances in Space Research (02731177)69(9)pp. 3333-3349
This paper investigates the possibility of high resolution mapping of PM2.5 concentration over Tehran city using high resolution satellite AOD (MAIAC) retrievals. For this purpose, a framework including three main stages, data preprocessing; regression modeling; and model deployment was proposed. The output of the framework was a machine learning model trained to predict PM2.5 from MAIAC AOD retrievals and meteorological data. The results of model testing revealed the efficiency and capability of the developed framework for high resolution mapping of PM2.5, which was not realized in former investigations performed over the city. Thus, this study, for the first time, realized daily, 1 km resolution mapping of PM2.5 in Tehran with R2 around 0.74 and RMSE better than 9.0 [Formula presented]. © 2022 COSPAR
Remote Sensing Letters (2150704X)13(12)pp. 1260-1270
Synergetic use of sensors for soil moisture retrieval is attracting considerable interest due to the different advantages of different sensors. Active, passive, and optic data integration could be a comprehensive solution for exploiting the advantages of different sensors aimed at preparing soil moisture maps. Typically, pixel-based methods are used for multi-sensor fusion. Since, different applications need different scales of soil moisture maps, pixel-based approaches are limited for this purpose. Object-based image analysis employing an image object instead of a pixel could help us to meet this need. This paper proposes a segment-based image fusion framework to evaluate the possibility of preparing a multi-scale soil moisture map through integrated Sentinel-1, Sentinel-2, and Soil Moisture Active Passive (SMAP) data. The results confirmed that the proposed methodology was able to improve soil moisture estimation in different scales up to 20% better compared to pixel-based fusion approach. © 2022 Informa UK Limited, trading as Taylor & Francis Group.
Zhu, X.X.,
Hu, J.,
Qiu, C.,
Shi, Y.,
Kang, J.,
Mou, L.,
Bagheri, H.,
Haberle, M.,
Hua, Y.,
Huang, R. IEEE Geoscience and Remote Sensing Magazine (24732397)8(3)pp. 76-89
Gaining access to labeled reference data is one of the great challenges in supervised machine-learning endeavors. This is especially true for an automated analysis of remote sensing images on a global scale, which enables us to address global challenges, such as urbanization and climate change, using state-of-the-art machine-learning techniques. To meet these pressing needs, especially in urban research, we provide open access to a valuable benchmark data set, So2Sat LCZ42, which consists of local-climate-zone (LCZ) labels of approximately half a million Sentinel-1 and Sentinel-2 image patches in 42 urban agglomerations (plus 10 additional smaller areas) across the globe. © 2013 IEEE.
ISPRS International Journal of Geo-Information (22209964)8(4)
So-called prismatic 3D building models, following the level-of-detail (LOD) 1 of the OGC City Geography Markup Language (CityGML) standard, are usually generated automatically by combining building footprints with height values. Typically, high-resolution digital elevation models (DEMs) or dense LiDAR point clouds are used to generate these building models. However, high-resolution LiDAR data are usually not available with extensive coverage, whereas globally available DEM data are often not detailed and accurate enough to provide sufficient input to the modeling of individual buildings. Therefore, this paper investigates the possibility of generating LOD1 building models from both volunteered geographic information (VGI) in the form of OpenStreetMap data and remote sensing-derived geodata improved by multi-sensor and multi-modal DEM fusion techniques or produced by synthetic aperture radar (SAR)-optical stereogrammetry. The results of this study show several things: First, it can be seen that the height information resulting from data fusion is of higher quality than the original data sources. Secondly, the study confirms that simple, prismatic building models can be reconstructed by combining OpenStreetMap building footprints and easily accessible, remote sensing-derived geodata, indicating the potential of application on extensive areas. The building models were created under the assumption of flat terrain at a constant height, which is valid in the selected study area. c 2019 by the authors.
A huge archive of very high-resolution SAR and optical satellite imagery acquired by different remote sensing satellites provides the opportunity to explore the possibility of 3D-reconstruction by multi-sensor stereogrammetry. This paper investigates the potential of SAR-optical stereogrammetry over urban areas using very-high-resolution imagery acquired by TerraSAR-X and Worldview-2. Furthermore, the potentials and challenges of deriving simple prismatic building models by combining the stereogrammetry results and OpenStreetMap building footprints are discussed. The results of this data fusion research demonstrate the possibility of using SAR-optical stereogrammetry for urban 3D reconstruction at level-of-detail 1. © 2019 IEEE.
ISPRS Journal of Photogrammetry and Remote Sensing (09242716)146pp. 389-408
Currently, numerous remote sensing satellites provide a huge volume of diverse earth observation data. As these data show different features regarding resolution, accuracy, coverage, and spectral imaging ability, fusion techniques are required to integrate the different properties of each sensor and produce useful information. For example, synthetic aperture radar (SAR) data can be fused with optical imagery to produce 3D information using stereogrammetric methods. The main focus of this study is to investigate the possibility of applying a stereogrammetry pipeline to very-high-resolution (VHR) SAR-optical image pairs. For this purpose, the applicability of semi-global matching is investigated in this unconventional multi-sensor setting. To support the image matching by reducing the search space and accelerating the identification of correct, reliable matches, the possibility of establishing an epipolarity constraint for VHR SAR-optical image pairs is investigated as well. In addition, it is shown that the absolute geolocation accuracy of VHR optical imagery with respect to VHR SAR imagery such as provided by TerraSAR-X can be improved by a multi-sensor block adjustment formulation based on rational polynomial coefficients. Finally, the feasibility of generating point clouds with a median accuracy of about 2 m is demonstrated and confirms the potential of 3D reconstruction from SAR-optical image pairs over urban areas. © 2018 The Authors
CTIT workshop proceedings series (16821750)42(2)pp. 43-48
Nowadays, a huge archive of data from different satellite sensors is available for diverse objectives. While every new sensor provides data with ever higher resolution and more sophisticated special properties, using the data acquired by only one sensor might sometimes still not be enough. As a result, data fusion techniques can be applied with the aim of jointly exploiting data from multiple sensors. One example is to produce 3D information from optical and SAR imagery by employing stereogrammetric methods. This paper investigates the application of the semi-global matching (SGM) framework for 3D reconstruction from SAR-optical image pairs. For this objective, first a multi-sensor block adjustment is carried out to align the optical image with a corresponding SAR image using an RPC-based formulation of the imaging models. Then, a dense image matching, SGM is implemented to investigate its potential for multi-sensor 3D reconstruction. While the results achieved with Worldview-2 and TerraSAR-X images demonstrate the general feasibility of SAR-optical stereogrammetry, they also show the limited applicability of SGM for this task in its out-of-the-box formulation. © Authors 2018.
ISPRS Journal of Photogrammetry and Remote Sensing (09242716)144pp. 285-297
Recently, the bistatic SAR interferometry mission TanDEM-X provided a global terrain map with unprecedented accuracy. However, visual inspection and empirical assessment of TanDEM-X elevation data against high-resolution ground truth illustrates that the quality of the DEM decreases in urban areas because of SAR-inherent imaging properties. One possible solution for an enhancement of the TanDEM-X DEM quality is to fuse it with other elevation data derived from high-resolution optical stereoscopic imagery, such as that provided by the Cartosat-1 mission. This is usually done by Weighted Averaging (WA) of previously aligned DEM cells. The main contribution of this paper is to develop a method to efficiently predict weight maps in order to achieve optimized fusion results. The prediction is modeled using a fully connected Artificial Neural Network (ANN). The idea of this ANN is to extract suitable features from DEMs that relate to height residuals in training areas and then to automatically learn the pattern of the relationship between height errors and features. The results show the DEM fusion based on the ANN-predicted weights improves the qualities of the study DEMs. Apart from increasing the absolute accuracy of Cartosat-1 DEM by DEM fusion, the relative accuracy (respective to reference LiDAR data) of DEMs is improved by up to 50% in urban areas and 22% in non-urban areas while the improvement by the HEM-based method does not exceed 20% and 10% in urban and non-urban areas respectively. © 2018 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS)
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (21511535)11(12)pp. 4761-4774
Recently, a new global digital elevation model (DEM) with pixel spacing of 0.4 arcsec and relative height accuracy finer than 2 m for flat areas (slopes < 20%) and better than 4 m for rugged terrain (slopes > 20%) was created through the TanDEM-X mission. One important step of the chain of global DEM generation is to mosaic and fuse multiple raw DEM tiles to reach the target height accuracy. Currently, weighted averaging (WA) is applied as a fast and simple method for TanDEM-X raw DEM fusion, in which the weights are computed from height error maps delivered from the Integrated TanDEM-X Processor (ITP). However, evaluations show that WA is not the perfect DEM fusion method for urban areas, especially in confrontation with edges such as building outlines. The main focus of this paper is to investigate more advanced variational approaches such as TV-L 1 and Huber models. Furthermore, we also assess the performance of variational models for fusing raw DEMs produced from data takes with different baseline configurations and height of ambiguities. The results illustrate the high efficiency of variational models for TanDEM-X raw DEM fusion in comparison to WA. Using variational models could improve the DEM quality by up to 2 m, particularly in inner city subsets. © 2008-2012 IEEE.
Recently, the TanDEM-X DEM has been produced as a global DEM with unprecedented relative accuracy. One important step of the chain of global DEM generation is to mosaic multiple raw DEM tiles by DEM fusion methods to reach the best possible target accuracy. Currently, Weighted Averaging (WA) is used as a fast and simple method for TanDEM-X raw DEM fusion in which the weights are computed from height error maps delivered from the Interferometric TanDEM-X Processor (ITP). In this paper, we investigate the efficiency of variational models such as TV-L1 and Huber model for the TanDEM-X raw DEM fusion task in comparison to WA. The results illustrate that using variational models can improve the quality of DEM fusion outputs especially for areas with high-frequency contents and more complex morphological features like urban areas. Using variational models could improve the DEM quality by up to about 1m. © 2018 IEEE
This paper deals with TanDEM-X and Cartosat-1 DEM fusion over urban areas with support of weight maps predicted by an artificial neural network (ANN). Although the TanDEM-X DEM is a global elevation dataset of unprecedented accuracy (following HRTI-3 standard), its quality decreases over urban areas because of artifacts intrinsic to the SAR imaging geometry. DEM fusion techniques can be used to improve the TanDEM-X DEM in problematic areas. In this investigation, Cartosat-1 elevation data were fused with the TanDEM-X DEM by weighted averaging and total variation (TV)-based regularization, resorting to weight maps derived by a specifically trained ANN. The results show that the proposed fusion strategy can significantly improve the final DEM quality. © 2017 IEEE.
CTIT workshop proceedings series (16821750)42(1W1)pp. 433-439
Recently, with InSAR data provided by the German TanDEM-X mission, a new global, high-resolution Digital Elevation Model (DEM) has been produced by the German Aerospace Center (DLR) with unprecedented height accuracy. However, due to SAR-inherent sensor specifics, its quality decreases over urban areas, making additional improvement necessary. On the other hand, DEMs derived from optical remote sensing imagery, such as Cartosat-1 data, have an apparently greater resolution in urban areas, making their fusion with TanDEM-X elevation data a promising perspective. The objective of this paper is two-fold: First, the height accuracies of TanDEM-X and Cartosat-1 elevation data over different land types are empirically evaluated in order to analyze the potential of TanDEM-X-Cartosat-1 DEM data fusion. After the quality assessment, urban DEM fusion using weighted averaging is investigated. In this experiment, both weight maps derived from the height error maps delivered with the DEM data, as well as more sophisticated weight maps predicted by a procedure based on artificial neural networks (ANNs) are compared. The ANN framework employs several features that can describe the height residual performance to predict the weights used in the subsequent fusion step. The results demonstrate that especially the ANN-based framework is able to improve the quality of the final DEM through data fusion.
