arXiv subjects

Hossein Bagheri

Publications and source records attributed to Hossein Bagheri.

At least 19 recordsLinked to original sources

arXiv2025

LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction

Three-dimensional reconstruction of buildings, particularly at Level of Detail 1 (LOD1), plays a crucial role in various applications such as urban planning, urban environmental studies, and designing optimized transportation networks. This study focuses on assessing the potential of LiDAR data for accurate 3D building reconstruction at LOD1 and extracting morphological features from these models. Four deep semantic segmentation models, U-Net, Attention U-Net, U-Net3+, and DeepLabV3+, were used, applying transfer learning to extract building footprints from LiDAR data. The results showed that U-Net3+ and Attention U-Net outperformed the others, achieving IoU scores of 0.833 and 0.814, respectively. Various statistical measures, including maximum, range, mode, median, and the 90th percentile, were used to estimate building heights, resulting in the generation of 3D models at LOD1. As the main contribution of the research, the impact of segmentation accuracy on the quality of 3D building modeling and the accuracy of morphological features like building area and external wall surface area was investigated. The results showed that the accuracy of building identification (segmentation performance) significantly affects the 3D model quality and the estimation of morphological features, depending on the height calculation method. Overall, the UNet3+ method, utilizing the 90th percentile and median measures, leads to accurate height estimation of buildings and the extraction of morphological features.

eess.IV↗

arXiv2025

Assessing wildfire susceptibility in Iran: Leveraging machine learning for geospatial analysis of climatic and anthropogenic factors

This study investigates the multifaceted factors influencing wildfire risk in Iran, focusing on the interplay between climatic conditions and human activities. Utilizing advanced remote sensing, geospatial information system (GIS) processing techniques such as cloud computing, and machine learning algorithms, this research analyzed the impact of climatic parameters, topographic features, and human-related factors on wildfire susceptibility assessment and prediction in Iran. Multiple scenarios were developed for this purpose based on the data sampling strategy. The findings revealed that climatic elements such as soil moisture, temperature, and humidity significantly contribute to wildfire susceptibility, while human activities-particularly population density and proximity to powerlines-also played a crucial role. Furthermore, the seasonal impact of each parameter was separately assessed during warm and cold seasons. The results indicated that human-related factors, rather than climatic variables, had a more prominent influence during the seasonal analyses. This research provided new insights into wildfire dynamics in Iran by generating high-resolution wildfire susceptibility maps using advanced machine learning classifiers. The generated maps identified high risk areas, particularly in the central Zagros region, the northeastern Hyrcanian Forest, and the northern Arasbaran forest, highlighting the urgent need for effective fire management strategies.

cs.LG↗

arXiv2025

Optimizing Urban Critical Green Space Development Using Machine Learning

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{\deg}C and 0.92{\deg}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{\deg}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.

cs.LG↗

arXiv2024

Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features

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.

physics.ao-ph↗

arXiv2024

Using Deep Ensemble Forest for High Resolution Mapping of PM2.5 from MODIS MAIAC AOD in Tehran, Iran

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 the 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.

cs.LG↗

arXiv2024

Enhancing crop classification accuracy by synthetic SAR-Optical data generation using deep learning

Crop classification using remote sensing data has emerged as a prominent research area in recent decades. Studies have demonstrated that fusing 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 traditional data generation methods. These methods have been employed to tackle the imbalanced nature of the training data. Nevertheless, they still face limitations in effectively handling the minority classes. Overall, the issue of inadequate training data, particularly for minority classes, remains a hurdle that traditional methods struggle to overcome. In this research, We explore the effectiveness of conditional tabular generative adversarial network (CTGAN) as a synthetic data generation method based on a deep learning network, in 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 higher quality that can significantly increase the number of samples for minority classes leading to better performance of crop classifiers.

cs.CV↗

arXiv2023

Data level and decision level fusion of satellite multi-sensor AOD retrievals for improving PM2.5 estimations, a study on Tehran

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 do not 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). 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)

cs.CV↗

arXiv2022

Segment-based fusion of multi-sensor multi-scale satellite soil moisture retrievals

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.

eess.IV↗

arXiv2022

A machine learning-based framework for high resolution mapping of PM2.5 in Tehran, Iran, using MAIAC AOD data

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 mg/m3. Keywords: MAIAC; MODIS; AOD; Machine learning; Deep learning; PM2.5; Regression

cs.LG↗

arXiv2019

So2Sat LCZ42: A Benchmark Dataset for Global Local Climate Zones Classification

Access to labeled reference data is one of the grand 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 dataset named "So2Sat LCZ42," which consists of local climate zone (LCZ) labels of about half a million Sentinel-1 and Sentinel-2 image patches in 42 urban agglomerations (plus 10 additional smaller areas) across the globe. This dataset was labeled by 15 domain experts following a carefully designed labeling work flow and evaluation process over a period of six months. As rarely done in other labeled remote sensing dataset, we conducted rigorous quality assessment by domain experts. The dataset achieved an overall confidence of 85%. We believe this LCZ dataset is a first step towards an unbiased globallydistributed dataset for urban growth monitoring using machine learning methods, because LCZ provide a rather objective measure other than many other semantic land use and land cover classifications. It provides measures of the morphology, compactness, and height of urban areas, which are less dependent on human and culture. This dataset can be accessed from http://doi.org/10.14459/2018mp1483140.

cs.CV↗

arXiv2018

Fusion of Urban TanDEM-X raw DEMs using variational models

Recently, a new global Digital Elevation Model (DEM) with pixel spacing of 0.4 arcseconds and relative height accuracy finer than 2m for flat areas (slopes < 20%) and better than 4m 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 Interferometric 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-L1 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 2m particularly in inner-city subsets.

eess.IV↗

arXiv2018

A Framework for SAR-Optical Stereogrammetry over Urban Areas

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 2m is demonstrated and confirms the potential of 3D reconstruction from SAR-optical image pairs over urban areas.

eess.IV↗

arXiv2018

Fusion of TanDEM-X and Cartosat-1 Elevation Data Supported by NeuralNetwork-Predicted Weight Maps

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) ofDEMs is improved by up to 50% in urban areas and 22% in non-urban areas while the improvement by them-based method does not exceed 20% and 10% in urban and non-urban areas respectively.

eess.IV↗

arXiv2015

Network Coding Applications for 5G Millimeter-Wave Communications

The millimeter-wave bands have been attracting significant interest as a means to achieve major improvements in data rates and network efficiencies. One significant limitation for use of the millimeter-wave bands for cellular communication is that the communication suffers from much higher path-loss compared to the microwave bands. Millimeter-wave links have also been shown to change rapidly, causing links between devices and access points to switch among line-of-sight, non-line-of-sight and outage states. We propose using Random Linear Network Coding to overcome the unreliability of individual communication links in such millimeter-wave systems. Our system consists of devices transmitting and receiving network-coded packets through several access points. For downlink communication, network-coded packets are transmitted to a device via multiple access points. For uplink communication, the access points perform network coding of packets of several devices, and then send the network-coded packets to the core network. We compare our approach against a naive approach in which non-network coded packets are transmitted via multiple access points ("Forwarding" approach). We find that the network coding approach significantly outperforms the forwarding approach. In particular, network coding greatly improves the efficiency of the air-interface transmissions and the efficiency of the backhaul transmissions for the downlink and uplink communication, respectively.

cs.NI↗

arXiv2013

Low-Latency Data Sharing in Erasure Multi-Way Relay Channels

We consider an erasure multi-way relay channel (EMWRC) in which several users share their data through a relay over erasure links. Assuming no feedback channel between the users and the relay, we first identify the challenges for designing a data sharing scheme over an EMWRC. Then, to overcome these challenges, we propose practical low-latency and low-complexity data sharing schemes based on fountain coding. Later, we introduce the notion of end-to-end erasure rate (EEER) and analytically derive it for the proposed schemes. EEER is then used to calculate the achievable rate and transmission overhead of the proposed schemes. Using EEER and computer simulations, the achievable rates and transmission overhead of our proposed schemes are compared with the ones of one-way relaying. This comparison implies that when the number of users and the channel erasure rates are not large, our proposed schemes outperform one-way relaying. We also find an upper bound on the achievable rates of EMWRC and observe that depending on the number of users and channel erasure rates, our proposed solutions can perform very close to this bound.

cs.IT↗

arXiv2010

The Approximate Capacity Region of the Gaussian Z-Interference Channel with Conferencing Encoders

A two-user Gaussian Z-Interference Channel (GZIC) is considered, in which encoders are connected through noiseless links with finite capacities. In this setting, prior to each transmission block the encoders communicate with each other over the cooperative links. The capacity region and the sum-capacity of the channel are characterized within 1.71 bits per user and 2 bits in total, respectively. It is also established that properly sharing the total limited cooperation capacity between the cooperative links may enhance the achievable region, even when compared to the case of unidirectional transmitter cooperation with infinite cooperation capacity. To obtain the results, genie-aided upper bounds on the sum-capacity and cut-set bounds on the individual rates are compared with the achievable rate region. In the interference-limited regime, the achievable scheme enjoys a simple type of Han-Kobayashi signaling, together with the zero-forcing, and basic relaying techniques. In the noise-limited regime, it is shown that treating interference as noise achieves the capacity region up to a single bit per user.

cs.IT↗

arXiv2009

On the Capacity of the Half-Duplex Diamond Channel

In this paper, a dual-hop communication system composed of a source S and a destination D connected through two non-interfering half-duplex relays, R1 and R2, is considered. In the literature of Information Theory, this configuration is known as the diamond channel. In this setup, four transmission modes are present, namely: 1) S transmits, and R1 and R2 listen (broadcast mode), 2) S transmits, R1 listens, and simultaneously, R2 transmits and D listens. 3) S transmits, R2 listens, and simultaneously, R1 transmits and D listens. 4) R1, R2 transmit, and D listens (multiple-access mode). Assuming a constant power constraint for all transmitters, a parameter $Δ$ is defined, which captures some important features of the channel. It is proven that for $Δ$=0 the capacity of the channel can be attained by successive relaying, i.e, using modes 2 and 3 defined above in a successive manner. This strategy may have an infinite gap from the capacity of the channel when $Δ\neq$0. To achieve rates as close as 0.71 bits to the capacity, it is shown that the cases of $Δ$>0 and $Δ$<0 should be treated differently. Using new upper bounds based on the dual problem of the linear program associated with the cut-set bounds, it is proven that the successive relaying strategy needs to be enhanced by an additional broadcast mode (mode 1), or multiple access mode (mode 4), for the cases of $Δ$<0 and $Δ$>0, respectively. Furthermore, it is established that under average power constraints the aforementioned strategies achieve rates as close as 3.6 bits to the capacity of the channel.

cs.IT↗

arXiv2009

On the Symmetric Gaussian Interference Channel with Partial Unidirectional Cooperation

A two-user symmetric Gaussian Interference Channel (IC) is considered in which a noiseless unidirectional link connects one encoder to the other. Having a constant capacity, the additional link provides partial cooperation between the encoders. It is shown that the available cooperation can dramatically increase the sum-capacity of the channel. This fact is proved based on comparison of proposed lower and upper bounds on the sum-capacity. Partitioning the data into three independent messages, namely private, common, and cooperative ones, the transmission strategy used to obtain the lower bound enjoys a simple type of Han-Kobayashi scheme together with a cooperative communication scheme. A Genie-aided upper bound is developed which incorporates the capacity of the cooperative link. Other upper bounds are based on the sum-capacity of the Cognitive Radio Channel and cut-set bounds. For the strong interference regime, the achievablity scheme is simplified to employ common and/or cooperative messages but not the private one. Through a careful analysis it is shown that the gap between these bounds is at most one and two bits per real dimension for strong and weak interference regimes, respectively. Moreover, the Generalized Degrees-of-Freedom of the channel is characterized.

cs.IT↗