In the year 2006, the energy performance directive 2002/91/EG was passed by the European Union, according to this directive the Swedish building code was supplemented by a key measure of energy use intensity (EUI). The implemented EUI equals some energy use within a building divided by its floor area and must be calculated in new housing estate and shown when renting or selling housing property. In order to improve the EUI, energy efficiency refurbishments could be implemented. Building energy simulation tools enables a virtual view a building model and can estimate the energy use before implementing any refurbishments. They are a powerful resource when determine the impact of the refurbishment measure. In order to obtain a correct model which corresponds to the actual energy use, some adjustments of the model are often needed. This process refers to as calibration. The used EUI has been criticized and thus, the first objective in this work was to suggest an alternative key measure of a buildings performance. The results showed that the currently used EUI is disfavoring some districts in Sweden. New housing estate in the far north must take more refined actions in order to fulfill the regulation demand, given that the users are behaving identical regardless where the house is located. Further, the suggested measure is less sensitive to the users’ behavior than the presently used EUI. It also has a significance meaning in building design as it relating the building shape and thermal properties and stating that extreme building shapes must undergo a stricter thermal construction rather than buildings that are more compact. Thus, the suggested key measure also creates a communication link between architects and the consultant constructors. The second objective of this thesis has been to investigate a concept of calibration using the data normally provided by energy bills, i.e. some monthly aggregated data. A case study serves to answer this objective, by using the building energy simulation tool IDA ICE 4.7 and a building located in Umeå, Sweden. The findings showed that the used calibration approach yielded a model considered as calibrated in eleven of twelve months. Furthermore, the method gives a closer agreement to the actual heat demand rather than using templates and standardized values. The major explanation of the deviation was influence of the users, but also that the case study building burden with large heat losses by domestic hot water circulation and thus, more buildings should be subjected to this calibration approach.

Building information extraction and reconstruction from satellite images is an essential task for many applications related to 3D city modeling, planning, disaster management, navigation, and decision-making. Building information can be obtained and interpreted from several data, like terrestrial measurements, airplane surveys, and space-borne imagery. However, the latter acquisition method outperforms the others in terms of cost and worldwide coverage: Space-borne platforms can provide imagery of remote places, which are inaccessible to other missions, at any time. Because the manual interpretation of high-resolution satellite image is tedious and time consuming, its automatic analysis continues to be an intense field of research. At times however, it is difficult to understand complex scenes with dense placement of buildings, where parts of buildings may be occluded by vegetation or other surrounding constructions, making their extraction or reconstruction even more difficult. Incorporation of several data sources representing different modalities may facilitate the problem. The goal of this dissertation is to integrate multiple high-resolution remote sensing data sources for automatic satellite imagery interpretation with emphasis on building information extraction and refinement, which challenges are addressed in the following: Building footprint extraction from Very High-Resolution (VHR) satellite images is an important but highly challenging task, due to the large diversity of building appearances and relatively low spatial resolution of satellite data compared to airborne data. Many algorithms are built on spectral-based or appearance-based criteria from single or fused data sources, to perform the building footprint extraction. The input features for these algorithms are usually manually extracted, which limits their accuracy. Based on the advantages of recently developed Fully Convolutional Networks (FCNs), i.e., the automatic extraction of relevant features and dense classification of images, an end-to-end framework is proposed which effectively combines the spectral and height information from red, green, and blue (RGB), pan-chromatic (PAN), and normalized Digital Surface Model (nDSM) image data and automatically generates a full resolution binary building mask. The proposed architecture consists of three parallel networks merged at a late stage, which helps in propagating fine detailed information from earlier layers to higher levels, in order to produce an output with high-quality building outlines. The performance of the model is examined on new unseen data to demonstrate its generalization capacity. The availability of detailed Digital Surface Models (DSMs) generated by dense matching and representing the elevation surface of the Earth can improve the analysis and interpretation of complex urban scenarios. The generation of DSMs from VHR optical stereo satellite imagery leads to high-resolution DSMs which often suffer from mismatches, missing values, or blunders, resulting in coarse building shape representation. To overcome these problems, a methodology based on conditional Generative Adversarial Network (cGAN) is developed for generating a good-quality Level of Detail (LoD) 2 like DSM with enhanced 3D object shapes directly from the low-quality photogrammetric half-meter resolution satellite DSM input. Various deep learning applications benefit from multi-task learning with multiple regression and classification objectives by taking advantage of the similarities between individual tasks. Therefore, an observation of such influences for important remote sensing applications such as realistic elevation model generation and roof type classification from stereo half-meter resolution satellite DSMs, is demonstrated in this work. Recently published deep learning architectures for both tasks are investigated and a new end-to-end cGAN-based network is developed, which combines different models that provide the best results for their individual tasks. To benefit from information provided by multiple data sources, a different cGAN-based work-flow is proposed where the generative part consists of two encoders and a common decoder which blends the intensity and height information within one network for the DSM refinement task. The inputs to the introduced network are single-channel photogrammetric DSMs with continuous values and pan-chromatic half-meter resolution satellite images. Information fusion from different modalities helps in propagating fine details, completes inaccurate or missing 3D information about building forms, and improves the building boundaries, making them more rectilinear. Lastly, additional comparison between the proposed methodologies for DSM enhancements is made to discuss and verify the most beneficial work-flow and applicability of the resulting DSMs for different remote sensing approaches.