Periodic Reporting for period 2 - GECKO (building GrEener and more sustainable soCieties by filling the Knowledge gap in social science and engineering to enable responsible artificial intelligence co-creatiOn)
Okres sprawozdawczy: 2023-01-01 do 2025-06-30
A gap existed in responsible AI research for sustainability across social and information sciences. Current connected home technologies (CHTs) lacked actionable, commercially valuable low-energy outcomes because AI systems failed to embed users’ values or reflect the complexity of domestic life. Responsible AI remained nascent due to disciplinary divides: AI sought to replace human reasoning, while social science aimed to inform it.
GECKO addressed this gap by training future researchers and challenging conventional approaches, recognising that socio-technical solutions must reflect interrelations between people and technology to meet urgent sustainability needs. Effective responsible AI must integrate social science insights into human behaviour and technology interaction.
GECKO’s key objectives were to:
- develop conceptual information science and responsible AI methods for technology design;
- examine how everyday life understanding can inform AI-driven, low-carbon home technologies; and
- guide new human-centred information sciences for responsible, application-relevant AI.
GECKO achieved these goals. It produced explainable, trustworthy AI for connected homes and energy management, delivering measurable savings—25–38% energy cost and up to 31% carbon footprint reductions on dairy farms, plus up to 30% electricity and 12% gas savings via the Hugo Pro App. Its social science research advanced intersectional, participatory AI, shaping local energy transitions from the Aran Islands to Dutch communities, where coaching lifted three-quarters of households out of energy poverty.
Training 15 early-stage researchers now active across Europe, GECKO laid the groundwork for future responsible, human-centred AI that promotes sustainability and social equity.
GECKO addressed this gap by training future researchers and challenging conventional approaches, recognising that socio-technical solutions must reflect interrelations between people and technology to meet urgent sustainability needs. Effective responsible AI must integrate social science insights into human behaviour and technology interaction.
GECKO’s key objectives were to:
- develop conceptual information science and responsible AI methods for technology design;
- examine how everyday life understanding can inform AI-driven, low-carbon home technologies; and
- guide new human-centred information sciences for responsible, application-relevant AI.
GECKO achieved these goals. It produced explainable, trustworthy AI for connected homes and energy management, delivering measurable savings—25–38% energy cost and up to 31% carbon footprint reductions on dairy farms, plus up to 30% electricity and 12% gas savings via the Hugo Pro App. Its social science research advanced intersectional, participatory AI, shaping local energy transitions from the Aran Islands to Dutch communities, where coaching lifted three-quarters of households out of energy poverty.
Training 15 early-stage researchers now active across Europe, GECKO laid the groundwork for future responsible, human-centred AI that promotes sustainability and social equity.
The Information Sciences & Engineering Team focused on developing AI models that enhance trust and explainability. Research explored evaluating explanations of deep learning models for time series prediction, ensuring algorithmic trust through assessment of generalisability and transferability, incorporating human-in-the-loop via active learning to manage data uncertainty, developing adaptable deep learning structures responsive to environmental and living conditions, and detecting anomalies in data streams. These were demonstrated in residential buildings and farms to support global NetZero Energy targets, considering renewables and electric vehicle integration.
The Social Science Team examined literature on CHTs, social practices, social justice, and human-centred AI design. Data collection and fieldwork—including two living labs in eco-conscious residential buildings in Norway and a remote Aran Islands community—comprised household interviews; a mixed-method study on energy impacts of smart new-builds; a qualitative study on smart home designers’ user imaginaries; desk-based mapping of CHT errors and resistances; interviews with energy professionals on CHT and vulnerability; co-design workshops with smart energy professionals; and piloting ‘walk with video’ methods in sustainable communities.
The Data Interpretation Team investigated how algorithms can involve humans in the loop for explainability via intelligent personal assistants influencing energy behaviour, generating new design concepts for AI assistants. A living lab (13 households) enables users to monitor and receive feedback on energy use. A scalable, decentralised big data energy disaggregation scheme is being implemented to overcome central processing drawbacks and encourage adoption. Optimisation methods under Demand Response schemes have been reviewed as a foundation for identifying optimal residential consumption patterns.
The Social Science Team examined literature on CHTs, social practices, social justice, and human-centred AI design. Data collection and fieldwork—including two living labs in eco-conscious residential buildings in Norway and a remote Aran Islands community—comprised household interviews; a mixed-method study on energy impacts of smart new-builds; a qualitative study on smart home designers’ user imaginaries; desk-based mapping of CHT errors and resistances; interviews with energy professionals on CHT and vulnerability; co-design workshops with smart energy professionals; and piloting ‘walk with video’ methods in sustainable communities.
The Data Interpretation Team investigated how algorithms can involve humans in the loop for explainability via intelligent personal assistants influencing energy behaviour, generating new design concepts for AI assistants. A living lab (13 households) enables users to monitor and receive feedback on energy use. A scalable, decentralised big data energy disaggregation scheme is being implemented to overcome central processing drawbacks and encourage adoption. Optimisation methods under Demand Response schemes have been reviewed as a foundation for identifying optimal residential consumption patterns.
The GECKO Team, as evidenced by academic publications and released public datasets, enabled by various training events, have made the following contributions so far:
The Information Science and Engineering Team:
- developed a novel framework for evaluating mathematical interpretability of deep 'black box' ML models and demonstrated how these can be used to determine the mechanism by which knowledge from one ML model can be effectively passed to another via knowledge distillation
- performed rigorous evaluation of what information can be mined at different smart meter sampling rates and how meaningful and trustworthy deep learning and domain-specific metrics are in CHT applications in ensuring ‘responsible’ and ‘ethical’, ‘bias-free’ outcomes
- demonstrated the challenges of transferability of non-intrusive load disaggregation to achieve net zero in agriculture by quantifying electricity consumption of various farming automation tools
- released a transformer-based deep learning software for load disaggregation, by processing entire sequences of data, understanding the significance of each part of the input sequence and assigning importance weights accordingly, to learn global dependencies in the sequence
-improved feature selection techniques for personal thermal comfort modelling
- tackle time series anomaly detection in smart homes
Social Science Team:
-Empirically, results have been achieved through in-depth qualitative methods such as interviews, workshops and observation with diverse communities including prosumers, smart home occupants, industry professionals, and other stakeholders. Major empirical advances have focussed on engaging diverse and often marginalised groups (e.g. island communities or energy vulnerable groups), and focussing on diverse CHTs across spatial scales rather than solely in the home.
-Methodologically, innovation has been demonstrated through detailed case study research on situated practices (e.g. in specific organisations or communities), with a focus on how practices are connected across scales (e.g. how domestic life connects with design imaginaries). Novel methodologies such as co-design and ‘walk with video’ methods have also been developed to engage and empower diverse groups.
-Conceptually, progress has been demonstrated through developments of social practice-based approaches, such as tracing connections between expert imaginaries and domestic practices, and combining practice theories with learning theory and design approaches. Understandings of ART AI and CHT have also been advanced through the development of more systemic and anticipatory approaches to social justice based on intersectionality.
-Expected results for the rest of the research centre on deepening these advances, and translating them into recommendations for improved design of CHTs, as well as more inclusive approaches to design that engage and empower diverse user groups.
Data Interpretation team:
-Demonstrated the challenges and needs involving smart users in the loop and optimising the AI/ML-models performance by reviewing literature and interviewing smart home users
-Demonstrated explainability for individual decisions by ML methods in different domains including energy demand forecasting in CHT, e-commerce, and personal thermal comfort prediction towards generating user-centered explanations.
-Implemented Graph-based neural networks that demonstrated high performance for load disaggregation providing trustworthy decisions.
-Demonstrated Deep Reinforcement Learning and Particle Swarm Optimization methods in residential Distributed Energy Resources scheduling and control.
The Information Science and Engineering Team:
- developed a novel framework for evaluating mathematical interpretability of deep 'black box' ML models and demonstrated how these can be used to determine the mechanism by which knowledge from one ML model can be effectively passed to another via knowledge distillation
- performed rigorous evaluation of what information can be mined at different smart meter sampling rates and how meaningful and trustworthy deep learning and domain-specific metrics are in CHT applications in ensuring ‘responsible’ and ‘ethical’, ‘bias-free’ outcomes
- demonstrated the challenges of transferability of non-intrusive load disaggregation to achieve net zero in agriculture by quantifying electricity consumption of various farming automation tools
- released a transformer-based deep learning software for load disaggregation, by processing entire sequences of data, understanding the significance of each part of the input sequence and assigning importance weights accordingly, to learn global dependencies in the sequence
-improved feature selection techniques for personal thermal comfort modelling
- tackle time series anomaly detection in smart homes
Social Science Team:
-Empirically, results have been achieved through in-depth qualitative methods such as interviews, workshops and observation with diverse communities including prosumers, smart home occupants, industry professionals, and other stakeholders. Major empirical advances have focussed on engaging diverse and often marginalised groups (e.g. island communities or energy vulnerable groups), and focussing on diverse CHTs across spatial scales rather than solely in the home.
-Methodologically, innovation has been demonstrated through detailed case study research on situated practices (e.g. in specific organisations or communities), with a focus on how practices are connected across scales (e.g. how domestic life connects with design imaginaries). Novel methodologies such as co-design and ‘walk with video’ methods have also been developed to engage and empower diverse groups.
-Conceptually, progress has been demonstrated through developments of social practice-based approaches, such as tracing connections between expert imaginaries and domestic practices, and combining practice theories with learning theory and design approaches. Understandings of ART AI and CHT have also been advanced through the development of more systemic and anticipatory approaches to social justice based on intersectionality.
-Expected results for the rest of the research centre on deepening these advances, and translating them into recommendations for improved design of CHTs, as well as more inclusive approaches to design that engage and empower diverse user groups.
Data Interpretation team:
-Demonstrated the challenges and needs involving smart users in the loop and optimising the AI/ML-models performance by reviewing literature and interviewing smart home users
-Demonstrated explainability for individual decisions by ML methods in different domains including energy demand forecasting in CHT, e-commerce, and personal thermal comfort prediction towards generating user-centered explanations.
-Implemented Graph-based neural networks that demonstrated high performance for load disaggregation providing trustworthy decisions.
-Demonstrated Deep Reinforcement Learning and Particle Swarm Optimization methods in residential Distributed Energy Resources scheduling and control.