Sanjay Somanath

Mr. Sanjay Somanath

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 May 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SSSanjay Somanath
Sanjay Somanath
VNVasilis Naserentin
Vasilis Naserentin
OEOrfeas Eleftheriou
Orfeas Eleftheriou
DSDaniel Sjölie
Daniel Sjölie
BWBeata Stahre Wästberg
Beata Stahre Wästberg
ALAnders Logg
Anders Logg
A key feature for urban digital twins (DTs) is an automatically generated detailed 3D representation of the built and unbuilt environment from aerial imagery, footprints, LiDAR, or a fusion of these. Such 3D models have applications in architecture, civil engineering, urban planning, construction, real estate, Geographical Information Systems (GIS), and many other areas. While the visualization of large-scale data in conjunction with the generated 3D models is often a recurring and resource-intensive task, an automated workflow is complex, requiring many steps to achieve a high-quality visualization. Methods for building reconstruction approaches have come a long way, from previously manual approaches to semi-automatic or automatic approaches. This paper aims to complement existing methods of 3D building generation. First, we present a literature review covering different options for procedural context generation and visualization methods, focusing on workflows and data pipelines. Next, we present a semi-automated workflow that extends the building reconstruction pipeline to include procedural context generation using Python and Unreal Engine. Finally, we propose a workflow for integrating various types of large-scale urban analysis data for visualization. We conclude with a series of challenges faced in achieving such pipelines and the limitations of the current approach. However, the steps for a complete, end-to-end solution involve further developing robust systems for building detection, rooftop recognition, and geometry generation and importing and visualizing data in the same 3D environment, highlighting a need for further research and development in this field.

6 June 2024 in iScience
Verified
Journal Article
Open access
EHEmily Ho
Emily Ho
MSMichelle Schneider
Michelle Schneider
SSSanjay Somanath
Sanjay Somanath
YYYinan Yu
Yinan Yu
LTLiane Thuvander
Liane Thuvander
Sustainable urban transformation requires comprehensive knowledge about the built environment, including people’s perceptions, use of sites, and wishes. Qualitative interviews are conducted to understand better people’s opinions about a specific topic or location. This study explores the automatization of the interview coding process by investigating how state-of-the-art natural language processing techniques classify sentiment and semantic orientation from interviews transcribed in Swedish. For the sentiment analysis, the Swedish bidirectional encoder representations from transformers (BERT) model KB-BERT was used to perform a multi-class classification task on a text sentence level into three different classes: positive, negative, and neutral. Named entity recognition (NER) and string search were used for the semantic analysis to perform multi-label classification to match domain-related topics to the sentence. The models were trained and evaluated on partially annotated datasets. The results demonstrate that the implemented deep learning techniques are a possible and promising solution to achieve the stated goal.

5 May 2021 in Local Environment
Verified
Journal Article
Open access
SSSanjay Somanath
Sanjay Somanath
Alexander HollbergAlexander Hollberg
Alexander Hollberg
Liane ThuvanderLiane Thuvander
Liane Thuvander
Digital tools for performance-assessment are commonly used to shorten the feedback loop in testing designs for buildings and neighbourhoods. However, these tools do not extend to the social dimension in the same way as the economic and environmental dimensions. This paper aims to contribute to the development of digital tools to design socially sustainable neighbourhoods. We analyse 115 academic articles to establish a theoretical understanding of Social Sustainability (SoSu). Based on these results, we propose a digital user-interaction model to operationalise SoSu in the digital design process of buildings. In the literature, we observe a lack of consensus on the theoretical discussion on SoSu. Several extrinsic and intrinsic factors are identified contributing to this fuzziness; the dependency on stakeholder value systems, the qualitative nature of social indicators, and comparison to environmental sustainability being the most common. Still, we distinguish two overarching categories, social equity and social capital, that are further divided into sub-themes. Having mapped the categories and hierarchies of social themes, we propose a user-interaction model that incorporates these findings into a digital environment. The user-interaction model creates a guided decision-making framework for architects and urban planners by enabling stakeholders to make conscious and informed decisions grounded in theory.

15 August 2025 in Automation in Construction
Verified
Journal Article
Open access
YYYinan Yu
Yinan Yu
AGAlex Gonzalez-Caceres
Alex Gonzalez-Caceres
SSSamuel Scheidegger
Samuel Scheidegger
SSSanjay Somanath
Sanjay Somanath
AHAlexander Hollberg
Alexander Hollberg

14 September 2024 in Data in Brief
Verified
Journal Article
Open access
SSSanjay Somanath
Sanjay Somanath
Liane ThuvanderLiane Thuvander
Liane Thuvander
Alexander HollbergAlexander Hollberg
Alexander Hollberg
A synthetic population is a distribution of synthetic agents that replicates the demographic distribution of a real-world population based on census records. This paper presents an end-to-end model to generate a synthetic population of residents in Gothenburg, Sweden, along with activity schedules and mobility patterns for present and past populations. Using a stochastic modelling approach, we describe the model and present its corresponding dataset. The model is designed for applications in neighbourhood planning and includes detailed replicas of people in different neighbourhoods of Gothenburg organised as persons, households, houses, buildings, and daily activity chains. While the persons, households, and houses are synthetic replicas, they are connected to existing buildings. The model considers the allocation of primary and secondary locations based on a gravity model, realistic routing for active, public, and private motorised modes of transportation and allows users to introduce new buildings and amenities if needed. The model aims to impute national-level mobility patterns from a household travel survey and apply them locally to capture the nuances of a neighbourhood's built environment and demographic composition.

5 June 2026 in Urban Research & Practice
Verified
Journal Article
Open access
SSSanjay Somanath
Sanjay Somanath
LTLiane Thuvander
Liane Thuvander
MAMarco Adelfio
Marco Adelfio
AHAlexander Hollberg
Alexander Hollberg
1. Sustainable development (SD) is a key concept in contemporary urban planning. It is described as the ‘meeting point of three major dimensions: ecology, economy and society’, with the social dime...