Iskanje po katalogu digitalne knjižnice

Opis: In this paper, a novel method for estimating high-resolution isotropic broadband albedo is proposed, by downscaling satellite-derived albedo using an optimization approach. At first, broadband albedo is calculated from the lower-resolution multispectral satellite image using standard narrow-to-broadband (NTB) conversion, where the surfaces are considered Lambertian with isotropic reflectance. The high-resolution true orthophoto for the same location is segmented with the deep learning-based Segment Anything Model (SAM), and the resulting segments are refined with a classified digital surface model (cDSM) to exclude small transient objects. Afterwards, the remaining segments are grouped using K-means clustering, by considering orthophoto-visible (VIS) and near-infrared (NIR) bands. These segments present surfaces with similar materials and underlying reflectance properties. Next, the Differential Evolution (DE) optimization algorithm is applied to approximate albedo values to these segments so that their spatial aggregate matches the coarse-resolution satellite albedo, by proposing two novel objective functions. Extensive experiments considering different DE parameters over an 0.75 km2 large urban area in Maribor, Slovenia, have been carried out, where Sentinel-2 Level-2A NTB-derived albedo was downscaled to 1 m spatial resolution. Looking at the performed spatiospectral analysis, the proposed method achieved absolute differences of 0.09 per VIS band and below 0.18 per NIR band, in comparison to lower-resolution NTB-derived albedo. Moreover, the proposed method achieved a root mean square error (RMSE) of 0.0179 and a mean absolute percentage error (MAPE) of 4.0299% against ground truth broadband albedo annotations of characteristic materials in the given urban area. The proposed method outperformed the Enhanced Super-Resolution Generative Adversarial Networks (ESRGANs), which achieved an RMSE of 0.0285 and an MAPE of 9.2778%, and the Blind Super-Resolution Generative Adversarial Network (BSRGAN), which achieved an RMSE of 0.0341 and an MAPE of 12.3104%.
Ključne besede: isotropic broadband albedo, high-resolution albedo, Sentinel-2 albedo, true orthophoto, anything model, differential evolution
Objavljeno v DKUM: 23.04.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (20,47 MB)

Opis: In the past years various methods have been developed to estimate high-resolution solar potential in urban areas, by simulating solar irradiance over surface models that originate from remote sensing data. In general, this requires discretisation of solar irradiance models that estimate direct, reflective, and diffuse irradiances. The latter is most accurately estimated by an anisotropic model, where the hemispherical sky dome from arbitrary surface’s viewpoint consists of the horizon, the circumsolar and sky regions. Such model can be modified to incorporate the effects of shadowing from obstruction with a view factor for each sky region. However, state-of-the-art using such models for estimating solar potential in urban areas, only considers the sky view factor, and not circumsolar view factor, due to high computational load. In this paper, a novel parallelisation of solar potential estimation is proposed by using General Purpose computing on Graphics Processing Units (GPGPU). Modified anisotropic Perez model is used by considering diffuse shadowing with all three sky view factors. Moreover, we provide validation based on sensitivity analysis of the method’s accuracy with independent meteorological measurements, by changing circumsolar sky region’s half-angle and resolution of the hemispherical sky dome. Finally, the presented method using GPPGU was compared to multithreaded Central Processing Unit (CPU) approach, where on average a 70x computational speedup was achieved. Finally, the proposed method was applied over a urban area, obtained from Light Detection And Ranging (LiDAR) data, where the computation of solar potential was performed in a reasonable time.
Ključne besede: solar energy, solar potential, anisotropic diffuse irradiance, LiDAR, GPGPU
Objavljeno v DKUM: 17.12.2024; Ogledov: 0; Prenosov: 4
Celotno besedilo (8,06 MB)

Ključne besede: dynamic programming, suboptimal solution, feature selection, machine learning
Objavljeno v DKUM: 16.07.2024; Ogledov: 139; Prenosov: 27
Celotno besedilo (596,28 KB)

Ključne besede: multispectral, Sentinel-2, superpixel, node, EfficientNetV2, GraphSAGE
Objavljeno v DKUM: 23.05.2024; Ogledov: 158; Prenosov: 22
Celotno besedilo (34,47 MB)
Gradivo ima več datotek! Več...

Opis: V doktorski disertaciji opišemo nov postopek učenja razložljivih značilnic za klasifikacijske namene. Značilnice med vsako iteracijo rekombiniramo na osnovi vnaprej podanih aritmetičnih operacij, ocenimo pa jih glede na njihovo primernosti za klasifikacijo. Slednja temelji na prekrivanju porazdelitve verjetnosti med vrednostmi vzorcev, ki pripadajo različnim razredom. Za nadaljnji razvoj v naslednjo iteracijo izberemo podmnožico najbolj kakovostnih nekoreliranih značilnic z uporabo nove metode, ki temelji na rezu grafa. Pri tem se postopek opira na dva vhoda parametra, ki omogočata nadzor nad številom členov izhodnih značilnic. Prvi opisuje minimalno sprejemljivo kakovost značilnic, ki jih je treba vključiti v izhodni prostor značilnic, medtem ko drugi določa najvišjo dovoljeno stopnjo podobnosti med značilnicama. Rezultati pokažejo, da je metoda nizko občutljiva na oba vhodna parametra. Naučene značilnice pa statistično značilno izboljšajo klasifikacijsko točnost vseh testiranih klasifikatorjev, medtem ko najboljše točnosti dosežemo z uporabo klasifikatorja naključnih gozdov. Z rezultati primerjave pokažemo, da je predlagani postopek v vseh testnih primerih dosegal ali presegal klasifikacijske točnosti trenutnega stanje tehnike. Prav tako pokažemo tudi pravilnost razlage naučenih značilnic dobro preučene množice testnih podatkov.
Ključne besede: klasifikacija podatkov, razložljiva umetna inteligenca, učenje značilnic, odkrivanje znanja
Objavljeno v DKUM: 07.05.2024; Ogledov: 266; Prenosov: 96
Celotno besedilo (1,22 MB)