Surface Model Generation Research Articles

Digital Surface Model Generation from Satellite Images Based on Double-Penalty Bundle Adjustment Optimization

Digital Surface Model (DSM) generation from high-resolution optical satellite images is an important topic of research in the remote sensing field. In optical satellite imaging systems, the attitude information of the cameras recorded by satellite sensors is often biased, which leads to errors in the Rational Polynomial Camera (RPC) model of satellite imaging. These errors in the RPC model can mislead the DSM generation. To solve the above problems, we propose an automatic DSM generation method from satellite images based on the Double-Penalty bundle adjustment (DPBA) optimization algorithm. In the proposed method, two penalty functions representing the camera’s attitude and the spatial 3D points, respectively, are added to the reprojection error model of the traditional bundle adjustment optimization algorithm. Instead of acting on images directly, the penalty functions are used to adjust the reprojection error model and improve the RPC parameters. We evaluate the performance of the proposed method using high-resolution satellite image pairs and multi-date satellite images. Through some experiments, we compare the accuracy and completeness of the DSM generated by the proposed method, the Satellite Stereo Pipeline (S2P) method, and the traditional bundle adjustment (BA) method. Compared to the S2P method, the experiment results of the satellite image pair indicate that the proposed method can significantly improve the accuracy and the completeness of the generated DSM by about 1–5 m and 20%–60% in most cases. Compared to the traditional BA method, the proposed method improves the accuracy and completeness of the generated DSM by about 0.01–0.05 m and 1%–3% in most cases. The experiment results can be a testament to the feasibility and effectiveness of the proposed method.

LOD2-Level+ Low-Rise Building Model Extraction Method for Oblique Photography Data Using U-NET and a Multi-Decision RANSAC Segmentation Algorithm

Oblique photography is a regional digital surface model generation technique that can be widely used for building 3D model construction. However, due to the lack of geometric and semantic information about the building, these models make it difficult to differentiate more detailed components in the building, such as roofs and balconies. This paper proposes a deep learning-based method (U-NET) for constructing 3D models of low-rise buildings that address the issues. The method ensures complete geometric and semantic information and conforms to the LOD2 level. First, digital orthophotos are used to perform building extraction based on U-NET, and then a contour optimization method based on the main direction of the building and the center of gravity of the contour is used to obtain the regular building contour. Second, the pure building point cloud model representing a single building is extracted from the whole point cloud scene based on the acquired building contour. Finally, the multi-decision RANSAC algorithm is used to segment the building detail point cloud and construct a triangular mesh of building components, followed by a triangular mesh fusion and splicing method to achieve monolithic building components. The paper presents experimental evidence that the building contour extraction algorithm can achieve a 90.3% success rate and that the resulting single building 3D model contains LOD2 building components, which contain detailed geometric and semantic information.

Evaluating Learning-based Tie Point Matching for Geometric Processing of Off-Track Satellite Stereo

Abstract. Tie-point matching of off-track stereo images is a very challenging task, which can impact bias compensation and digital surface model (DSM) generation. Compared to in-track stereo images, off-track stereo images are more complex primarily due to the radiometric differences caused by sun illumination, sensor responses, atmospheric conditions, and seasonal land cover variations, and secondly due to the longer baseline and larger intersection angle. These challenges significantly limit the use of the vast number of images in satellite archives for automated geometric processing and mapping. Recent advances in deep learning (DL) based matching show promising results against images with diverse illuminations, viewing angles and scales through learning examples. This paper evaluates the potentials of addressing the tie point matching problems in off-track satellite stereo images. Specifically, we focus on stereo pairs that failed or underperformed in classic matching algorithms (i.e., SIFT (scale invariant feature transform)), and evaluate the DL-based tie points matchers by its resulting geometric accuracy in relative orientation, and the generated DSM. The experiments are carried out using 40 off-track satellite stereo pairs from four different regions around the world. We conclude that DL-based methods provide a significant higher success rate in matching challenging multi-temporal stereo pairs, even if their matching accuracy is slightly lower than classic algorithms.

Global Evaluation of Simulated High and Low Flows from 23 Macroscale Models

Abstract Macroscale hydrological/land surface models are important tools for assessing historical and predicting future characteristics of extreme hydrological events, yet quantitative understandings of how these large-scale models perform in simulating extreme hydrological characteristics remain limited. Here we evaluate simulated high and low flows from 23 macroscale models within three modeling experiments (i.e., 14 climate models from CMIP6, 6 global hydrological models from ISIMIP2a, and 3 land surface models from GLDAS) against observation in 633 unimpaired catchments globally over 1971–2010. Our findings reveal limitations in simulating extreme flow characteristics by these models. Specifically, we find that (i) most models overestimate high-flow magnitudes (bias range: from +15% to +70%) and underestimate low-flow magnitudes (bias range: from −80% to −20%); (ii) interannual variability in high and low flows is reasonably reproduced by ISIMIP2a and GLDAS models but poorly reproduced by CMIP6 models; (iii) no model consistently replicates the observed trend direction in high and low flows in over two-thirds of the catchments, and most models overestimate high-flow trends and underestimate low-flow trends; and (iv) CMIP6 and GLDAS models show timing biases, with early high flows and late low flows, while ISIMIP2a models exhibit the opposite pattern. Furthermore, all models performed better in more humid environments and noncold regions, with model structure and parameterization contributing more to uncertainties than climatic forcings. Overall, our results demonstrate that extreme flow characteristics simulated from current state-of-the-art macroscale models still contain large uncertainties and provide important guidance regarding the robustness of assessing extreme hydrometeorological events based on these modeling outputs. Significance Statement Macroscale hydrological and land surface models represent crucial tools for assessing historical trends and making predictions about future hydrological changes. Nevertheless, our current understanding of the quantitative performance of these large-scale models in simulating extreme hydrological characteristics remains limited. Here, we evaluate simulated high and low flows from 23 state-of-the-art macroscale models against observation in 633 unimpaired catchments globally over 1971–2010. Our results reveal important limitations in the extreme flow characteristics simulated from these models and provide important guidance regarding the robustness of assessing extreme hydrometeorological events based on these modeling outputs. The model evaluation performed herein serves as a pivotal, offering valuable insights to inform the development of the next generation of macroscale hydrological and land surface models.

Completing the picture of field-grown cereal crops: a new method for detailed leaf surface models in wheat.

The leaf angle distribution (LAD) is an important structural parameter of agricultural crops that influences light interception, radiation fluxes and consequently plant performance. Therefore, LAD and its parametrized form, the Beta distribution, is used in many photosynthesis models. However, in field cultivations, these parameters are difficult to assess and cereal crops in particular pose challenges since their leaves are thin, flexible, and often bent and twisted around their own axis. To our knowledge, there is only a very limited set of methods currently available to calculate LADs of field-grown cereal crops that explicitly takes these special morphological properties into account. In this study, a new processing pipeline is introduced that allows for the generation of realistic leaf surface models and the analysis of LADs of field-grown cereal crops from 3D point clouds. The data acquisition is based on a convenient stereo imaging setup. The approach was validated with different artificial targets and results on the accuracy of the 3D reconstruction, leaf surface modeling and calculated LAD are given. The mean error of the 3D reconstruction was below 1mm for an inclination angle range between 0° and 75° and the leaf surface could be quantified with an average accuracy of 90%. The concordance correlation coefficient (CCC) of 99.6% (p-value = [Formula: see text]) indicated a high correlation between the reconstructed inclination angle and the identity line. The LADs for bent leaves were reconstructed with a mean error of 0.21° and a standard deviation of 1.55°. As an additional parameter, the insertion angle was reconstructed for the artificial leaf model with an average error < 5°. Finally, the method was tested with images of field-grown cereal crops and Beta functions were approximated from the calculated LADs. The mean CCC between reconstructed LAD and calculated Beta function was 0.66. According to Cohen, this indicates a high correlation. This study shows that our image processing pipeline can reconstruct the complex leaf shape of cereal crops from stereo images. The high accuracy of the approach was demonstrated with several validation experiments including artificial leaf targets. The derived leaf models were used to calculate LADs for artificial leaves and naturally grown cereal crops. This helps to better understand the influence of the canopy structure on light absorption and plant performance and allows for a more precise parametrization of photosynthesis models via the derived Beta distributions.

Digital surface model generation from high‐resolution satellite stereos based on hybrid feature fusion network

AbstractRecent studies have demonstrated that deep learning‐based stereo matching methods (DLSMs) can far exceed conventional ones on most benchmark datasets by both improving visual performance and decreasing the mismatching rate. However, applying DLSMs on high‐resolution satellite stereos with broad image coverage and wide terrain variety is still challenging. First, the broad coverage of satellite stereos brings a wide disparity range, while DLSMs are limited to a narrow disparity range in most cases, resulting in incorrect disparity estimation in areas with contradictory disparity ranges. Second, high‐resolution satellite stereos always comprise various terrain types, which is more complicated than carefully prepared datasets. Thus, the performance of DLSMs on satellite stereos is unstable, especially for intractable regions such as texture‐less and occluded regions. Third, generating DSMs requires occlusion‐aware disparity maps, while traditional occlusion detection methods are not always applicable for DLSMs with continuous disparity. To tackle these problems, this paper proposes a novel DLSM‐based DSM generation workflow. The workflow comprises three steps: pre‐processing, disparity estimation and post‐processing. The pre‐processing step introduces low‐resolution terrain to shift unmatched disparity ranges into a fixed scope and crops satellite stereos to regular patches. The disparity estimation step proposes a hybrid feature fusion network (HF2Net) to improve the matching performance. In detail, HF2Net designs a cross‐scale feature extractor (CSF) and a multi‐scale cost filter. The feature extractor differentiates structural‐context features in complex scenes and thus enhances HF2Net's robustness to satellite stereos, especially on intractable regions. The cost filter filters out most matching errors to ensure accurate disparity estimation. The post‐processing step generates initial DSM patches with estimated disparity maps and then refines them for the final large‐scale DSMs. Primary experiments on the public US3D dataset showed better accuracy than state‐of‐the‐art methods, indicating HF2Net's superiority. We then created a self‐made Gaofen‐7 dataset to train HF2Net and conducted DSM generation experiments on two Gaofen‐7 stereos to further demonstrate the effectiveness and practical capability of the proposed workflow.

SPARSESAT-NERF: DENSE DEPTH SUPERVISED NEURAL RADIANCE FIELDS FOR SPARSE SATELLITE IMAGES

Abstract. Digital surface model generation using traditional multi-view stereo matching (MVS) performs poorly over non-Lambertian surfaces, with asynchronous acquisitions, or at discontinuities. Neural radiance fields (NeRF) offer a new paradigm for reconstructing surface geometries using continuous volumetric representation. NeRF is self-supervised, does not require ground truth geometry for training, and provides an elegant way to include in its representation physical parameters about the scene, thus potentially remedying the challenging scenarios where MVS fails. However, NeRF and its variants require many views to produce convincing scene’s geometries which in earth observation satellite imaging is rare. In this paper we present SparseSat-NeRF (SpS-NeRF) – an extension of Sat-NeRF adapted to sparse satellite views. SpS-NeRF employs dense depth supervision guided by crosscorrelation similarity metric provided by traditional semi-global MVS matching. We demonstrate the effectiveness of our approach on stereo and tri-stereo Pléiades 1B/WorldView-3 images, and compare against NeRF and Sat-NeRF. The code is available at https://github.com/LulinZhang/SpS-NeRF

Solving photogrammetric cold cases using AI-based image matching: New potential for monitoring the past with historical aerial images

With the ongoing digitization in archives, an increasing number of historical data becomes available for research. This includes historical aerial images which provide detailed information about the depicted area. Among the applications enabled by these images are change detection of land use, land cover, glaciers, and coastal environments as well as the observation of land degradation, and natural hazards. Studying the depicted areas and occurring 3D deformations requires the generation of a digital surface model (DSM) which is usually obtained via photogrammetric Structure-from-Motion (SfM). However, conventional SfM workflows often fail in registering historical aerial images due to their radiometric characteristics introduced by digitization, original image quality, or vast temporal changes between epochs. We demonstrate that the feature matching step in the Structure from Motion (SfM) pipeline is particularly crucial. To address this issue, we apply the two synergetic neural network methods SuperGlue and DISK, improving feature matching for historical aerial images. This requires several modifications to enable rotational invariance and leveraging the high resolution of aerial images. In contrast to other studies our workflow does not require any prior information such as DSMs, flight height, focal lengths, or scan resolution which are often no more extent in archives. It is shown that our methods using adapted parameter settings are even able to deal with quasi texture-less images. This enables the simultaneous processing of various kind of mono-temporal and multi-temporal data handled in a single workflow from data preparation over feature matching through to camera parameter estimation and the generation of a sparse point cloud. It outperforms conventional strategies in the number of correct feature matches, number of registered images and calculated 3D points and allows the generation of multi-temporal DSMs with high quality.With the flexibility of the method, it enables the automatic processing of formerly unusable or only to be interactively processed data, e.g. aerial images where the flight route is unknown, or with difficult radiometric properties. This makes it possible to go back even further in time, where the data quality usually decreases, and enables a holistic monitoring and comparison of environments of high interest. The code is made publicly available at https://github.com/tudipffmgt/HAI-SFM.

Digital terrain, surface, and canopy height model generation with dual-baseline low-frequency InSAR over forest areas

Digital terrain, surface, and canopy height model generation with dual-baseline low-frequency InSAR over forest areas

BIM-supported drone path planning for building exterior surface inspection

Digitalization in the architectural, engineering, and construction (AEC) industry highlights the interdisciplinary collaboration between complex systems to provide fast and efficient services. This paper incorporates Building Information Modeling (BIM) and drone, and generates feasible paths for exterior building surface inspections. A systematic approach was proposed, focusing on the overall automatic procedure from the BIM model to the actual flight of the drone in a real-world building environment. The proposed method comprises five main steps: BIM to point cloud represented surface model generation, viewpoint determination, path planning, virtual simulation, and actual flight. In particular, the basic function could generate an inspection path for the whole building that guarantees high coverage rates, obstacle avoidance, and collision-free operation. The advanced function provides four types of building-specific decomposition strategies capable of overcoming the complex building structure shape, enabling reasonable inspection ranges, and enhancing computation efficiency. To simulate a drone’s inspection procedure and evaluate its performance in various contexts, an integrated platform based on a game engine and Airsim was developed. In addition, a case study was conducted to demonstrate the effectiveness of the method. The results demonstrate that the proposed BIM-enabled path planning can assist drones in conducting building inspection tasks with considerable applicability and flexibility.

Impact of tessellation surface model generation process on acoustical tire features

Due to the electrification of vehicles, the focus of vehicle noise is shifting to the tires. Since tire noise is dependent of the tread pattern, methods to characterize tread patterns are required. This research investigates the effects of different processes of tire digitization on the identification of tread pattern features. An open source digitization pipeline is built to extract a tessellation surface model. This model is compared to one, generated with a commercial photogrammetric system. The comparison is based on three acoustically relevant tire features. Fully automated algorithms are introduced to extract these features from any 3D tire tessellation model. The research finds that although the resolution of the mesh surface of the proposed model is lower, feature recognition is not affected by this change. This paves the way for more accessible models that accelerate the statistical coupling of tire tread characteristics and their acoustic, handling or braking behavior.

Application of Finite Element Method to Create a Digital Elevation Model

The generation of a topographical surface or digital elevation model for a given set of points in space is a known problem in civil engineering and topography. In this article, we propose a simple and efficient way to obtain the terrain surface by using a structural shell finite element model, giving advice on how to implement it. The proposed methodology does not need a large number of points to define the terrain, so it is especially suitable to be used with data provided by manual topographical tools. Several examples are developed to demonstrate the easiness and accuracy of the methodology. The digital terrain model of a real landscape is modeled by using different numbers of points (from 49 to 400) using a regular mesh or a randomly generated cloud of points. The results are compared, showing how the proposed methodology creates a sufficiently accurate model, even with a low number of points (compared with the thousands of points handled in a LiDAR representation). A real case application is also shown. As an appendix, the sample code to generate the examples is provided.

Deep Neural Network Regression for Normalized Digital Surface Model Generation With Sentinel-2 Imagery

Deep Neural Network Regression for Normalized Digital Surface Model Generation With Sentinel-2 Imagery

Digital surface model generation from aerial imagery using bridge probability relaxation matching

Optical image dense matching is a crucial step in the process of generating digital surface models (DSMs). Many existing dense matching methods have adopted pixelwise matching strategy and have achieved precise matching results; however, the methods are time consuming and have limited efficiency in high surveying and mapping production. We introduce a bridge probability relaxation matching method for automatic DSM generation. The method adopts a coarse-to-fine hierarchical strategy and achieves high matching accuracy and fast processing speed simultaneously. This method builds a self-adaptive disparity surface model in a local area and constrains the disparity surface using the spatial relationship between feature points and adjacent pixels. Finally, the disparity is optimized by calculating the increment of the relaxation iteration probability. Experiments are based on different areas with different textures and terrain types. Compared with the DSMs derived from semi-global matching, our proposed approach achieves high levels of accuracy and efficiency in automatic DSM generation.

Impacts of surface model generation approaches on raytracing-based solar potential estimation in urban areas

Raytracing-based methods are widely used for quantifying irradiation on building surfaces. Urban 3D surface models are necessary input for raytracing simulations, which can be generated from open-source point cloud data with the help of surface reconstruction algorithms. In research and engineering practice, various algorithms are being used for this purpose; each leading to different mesh topologies and corresponding performance. This paper compares the impacts of four different reconstruction algorithms by investigating their performance using DAYSIM raytracing simulations. The analysis is carried out for five configurations with various urban morphologies. Results show that the reconstructed models consistently underestimate the shading influence due to geometrical shrinkages that emerge from the various model generation procedures. The explicit algorithms, with Generic Delaunay a notable example, have better performance with less embedded error than the implicit algorithms in both daily and annual simulations. Results also show that diffuse irradiance is responsible for larger contributions to the overall error than direct components. This effect becomes more prominent when modeling reflected irradiation in urban environments. Additionally, the work shows that solar elevation and shading geometry types also affect the error magnitude. The paper concludes by providing reconstruction algorithm selection criteria for photovoltaic practitioners and urban energy planners.

Mineral nutrition and tolerance to Colletotrichum spp. of Andean blackberry (Rubus glaucus Benth.) in nursery

Introduction. Several diseases affect the Andean blackberry cultivation in Colombia, where anthracnose (Colletotrichum spp.) stands out for generating total losses. Objective. To estimate the doses of N, P, K, and Ca that allow greater tolerance to C. gloeosporioides strain 52 in Andean blackberry seedlings. Materials and methods. The experiment was carried out in 2017, in a greenhouse located in Mosquera in the department of Cundinamarca (Colombia), with seedlings sown in a substrate based on a 3: 1 mixture of peat and rice husks. A randomized complete block design with a central composite arrangement of 25 treatments and 15 seedlings were used per experimental unit. The inoculation of plant material was carried out 53 days after had begun the application of the treatments, with mycelial discs at a concentration of 9.53×104 conidia. The severity percentage (Sev), incubation period (IP), disease development rate (r), plant height (PLH), stem diameter (StD), leaf area (LA), chlorophyll content index (CCI), dry weight of the aerial part, and concentration of nutrients were measured. The analysis of variance with Tukey’s test (p&lt;0.05), correlation analysis, generation of response surface models, and principal component analysis with the t-test (p&lt;0.05) was carried out. Results. The severity percentage showed significant differences in the plants that received the fertilization treatments, the allometric variables, and chlorophyll content index were negatively and significantly related with the severity percentage. Simple linear effects models and interaction between elements and four components were obtained, which explained 63 % of the observed variability. Conclusions. The doses of 55, 3, 14, and 9 g plant of N, P2O5, K2O, and CaO, respectively, allowed a higher tolerance of plants against strain 52, as well as higher values in growth variables.

A linear pushbroom satellite image epipolar resampling method for digital surface model generation

Epipolar resampling, also known as stereo rectification, is a prerequisite for optical satellite image stereo matching in digital surface model (DSM) generation. In epipolar resampling, image pairs are warped and thus can be matched pixel-to-pixel along the epipolar line. Different from the pinhole imaging model of frame cameras, the multi-center projection model of linear pushbroom sensors does not obey the epipolar geometric constraint, making it impossible to conjugate epipolar lines from stereo images. The epipolar resampling methods can resolve some of the inherent epipolar error, but not completely. The topographic relief brings high disparity values between epipolar image pairs, posing a challenge to the subsequent stereo matching to recover disparity map. In this paper, we introduce a novel epipolar resampling method for satellite imagery based on ortho rectification. This method takes full advantage of a rational function model to establish a connection between image space and object space coordinates, and thereby transform the two-dimensional disparity in ortho rectification products into one dimension. We propose a coarse-to-fine DSM generation pipeline to overcome the high-disparity-problem without additional time costs or precision decrement. We conducted experiments on various satellite stereo images, and validated both the extreme suppression on epipolar error as well as the feasibility of the proposed coarse-to-fine DSM generation pipeline. The experimental results show that the generated epipolar image pairs from our proposed method effectively solved the high disparity problem. Furthermore, the novel DSM generation method obtained an internal error below one pixel for a rectified stereo image pair in mountain area, and the lowest vertical error in the IARPA MVS dataset when compared with the common open-source programs and commercial software.

ICESAT-2 LASER ALTIMETRY DATA-GUIDED HIGH-ACCURACY POSITIONING OF SATELLITE STEREO IMAGES

Abstract. Positioning accuracy is a key indicator that restricts the accuracy of satellite image mapping. Laser altimetry acquires surface height in decimeters or higher accuracy, providing high-accuracy topographic information for satellite photogrammetry. This study proposes a four-step high-accuracy positioning method called laser altimetry data-guided stereo images positioning (LGSP): photon outlier removal, digital surface model (DSM) generation by a variant of the tube-shape semi-global matching (tSGM), fast point cloud alignment, and DSM and rational function model (RFM) refining. First, outliers of the laser altimetry data are filtered out via confidence selection and open access DSM constraints. Second, the DSM around high-accuracy photons is generated via the variant of tSGM. Third, fast point cloud alignment is performed to align the DSM with laser altimetry data. Finally, we propose a high-resolution stereo model refinement method based on alignment parameters. Experiments on two satellite stereo datasets with different loads, resolutions, and topographies show that LGSP improved the planimetry accuracy of satellite stereo images after adding laser altimetry data. What’s more, LGSP significantly improved the height accuracy of satellite images. Specifically, LGSP reduced the height errors from the original 5.99 m to 1.00 m for the Ziyuan-3 stereo dataset and from the original 20.39 m to 0.83 m for the Gaofen-7 stereo dataset, and slightly outperformed bundle adjustment in which four ground control points were deployed around the four corners of the stereo images. RFM refining based on alignment parameters has been made publicly available at https://mega.nz/file/EFQASJ6A#BKjoupHVshylQR4wCxGd9BDtg08bhy-_aY-c_rHnl-0.

Digital surface model generation from high-resolution satellite stereo imagery based on structural similarity

In this study, we proposed an automatic approach to extract DSMs from VHR satellite imagery. This study aims to apply the histogram of orientated phase congruency (HOPC) descriptor and SIFT-Flow algorithm to match multi-view VHR satellite images densely and extract detailed DSMs competitive with ones generated from Light Detection and Ranging (LiDAR) point clouds. The HOPC descriptor relies on detecting features by calculating the phase congruency model, which allows the image features to be highly robust against illumination changes. Moreover, we developed an automatic algorithm to extract precise and homogenously distributed tie-points and subsequently conduct bias correction of the Rational Polynomial Coefficients (RPC). We tested our proposed algorithm on four WorldViw-3 datasets captured from different viewpoints, and compared the results with the DSMs obtained by the Semi-Global Matching (SGM) algorithm. The experimental results indicated the proficiency of our proposed method in generating accurate and reliable DSMs using VHR satellite data.

EVALUATION OF THE POTENTIAL OF GREEN ROOFS APPLIED TO AN URBAN FABRIC USING GIS AND REMOTE SENSING DATA CASE OF THE NADOR CITY / MOROCCO

Abstract. Accelerated urban growth has affected many of the planet's natural processes. In cities, most of the surface is covered with asphalt and cement, which has changed the water and air cycles. To restore the balance of urban ecosystems, cities must find the means to create green spaces in an increasingly gray world. Green spaces provide the city and its inhabitants a better living environment. This article uses Nador city as a case study area, this project consists in studying the possibility for the roofs to receive vegetation. The first axis of this project is the quantification of the current vegetation cover at ground level by calculating the Normalized Difference Vegetation Index (NDVI) based on Satellite images Landsat 8, then the classification of the LiDAR point cloud, and the generation of a digital surface model (DSM) of the urban area. This type of derived data was used as the basis for the various stages of estimating the potential plant cover at the roof level. In order to study the different possible scenarios, a set of criteria was applied, such as the minimum roof area, the inclination and the duration of the sunshine on the roof, which is calculated using the linear model of angstrom Prescott based on solar radiation. The study shows that in the most conservative scenario, 21771 suitable buildings that had to be redeveloped into green roofs, with an appropriate surface area of 369.26Ha allowing a 63,40% increase in the city's green space by compared to the current state contributing to the improvement of the quality of life and urban comfort. The average budget for the installation of green roofs in a building with a surface area of 100 m2 varies between 60000dh and 170000dh depending on the type of green roofs used, extensive or intensive. These results would enable planners and researchers in green architecture sciences to carry out more detailed planning analyzes.