Tina Ziarati

Ms. Tina Ziarati


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
1 October 2025 in Energies
Verified
Journal Article
Open access
PDF file
EFEkaterina Filippova
Ekaterina Filippova
SHSattar Hedayat
Sattar Hedayat
TZTina Ziarati
Tina Ziarati
Matteo ManganelliMatteo Manganelli
Matteo Manganelli
The integration of artificial intelligence (AI) into bioclimatic building design is reshaping the architecture, engineering, and construction (AEC) industry by addressing critical challenges in sustainability and efficiency. By aligning structures with local climates, bioclimatic design addresses global challenges such as energy consumption, urbanization, and climate change. Complementing these principles, AI technologies—including machine learning, digital twins, and generative algorithms—are revolutionizing the sector by optimizing processes across the entire building lifecycle, from design and construction to operation and maintenance. Amid the diverse array of AI-driven innovations, this research highlights digital twin (DT) technologies as a key to AI-driven transformation, enabling real-time monitoring, simulation, and optimization for sustainable design. Applications like façade optimization, energy flow analysis, and predictive maintenance showcase their role in adaptive architecture, while frameworks like Construction 4.0 and 5.0 promote human-centric, data-driven sustainability. By bridging AI with bioclimatic design, the findings contribute to a vision of a built environment that seamlessly aligns environmental sustainability with technological advancement and societal well-being, setting new standards for adaptive and resilient architecture. Despite the immense potential, AI and DTs face challenges like high computational demands, regulatory barriers, interoperability and skill gaps. Overcoming these challenges will be crucial for maximizing the impact on sustainable building, requiring ongoing research to ensure scalability, ethics, and accessibility.

4 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
EFEkaterina Filippova
Ekaterina Filippova
SHSattar Hedayat
Sattar Hedayat
TZTina Ziarati
Tina Ziarati
Matteo ManganelliMatteo Manganelli
Matteo Manganelli
The integration of Artificial Intelligence (AI) into bioclimatic building design is reshaping the Architecture, Engineering, and Construction (AEC) industry by addressing critical challenges in sustainability and efficiency. By aligning structures with local climates, bioclimatic design addresses global challenges such as energy consumption, urbanization, and climate change. Complementing these principles, AI technologies - including machine learning, digital twins, and generative algorithms - are revolutionizing the sector by optimizing processes across the entire building lifecycle, from design and construction to operation and maintenance. Amid the diverse array of AI-driven innovations, this research highlights Digital Twin (DT) technologies as a key to AI-driven transformation, enabling real-time monitoring, simulation, and optimization for sustainable design. Applications like façade optimization, energy flow analysis, and predictive maintenance showcase their role in adaptive architecture, while frameworks like Construction 4.0 and 5.0 promote human-centric, data-driven sustainability. By bridging AI with bioclimatic design, the findings contribute to a vision of a built environment that seamlessly aligns environmental sustainability with technological advancement and societal well-being, setting new standards for adaptive and resilient architecture. Despite the immense potential, AI and DTs face challenges like high computational demands, regulatory barriers, interoperability and skill gaps. Overcoming these challenges will be crucial for maximizing the impact on sustainable building, requiring ongoing research to ensure scalability, ethics, and accessibility.

30 November 2025 in Energies
Verified
Journal Article
Open access
PDF file
SHSattar Hedayat
Sattar Hedayat
TZTina Ziarati
Tina Ziarati
Matteo ManganelliMatteo Manganelli
Matteo Manganelli
This paper presents a physics-informed reinforcement learning framework that embeds thermodynamic constraints directly into the policy network of a continuous control agent for HVAC optimization. We introduce a Thermodynamically-Constrained Deep Deterministic Policy Gradient (TC-DDPG) algorithm that operates on continuous actions and enforces physical feasibility through a differentiable constraint layer coupled with physics-regularized loss functions. In a simulation-based evaluation using a custom Python multi-zone resistance-capacitance (RC) thermal model, the proposed method achieves a 34.7% reduction in annual HVAC electricity consumption relative to a rule-based baseline (95% CI: 31.2–38.1%, n = 50 runs) and outperforms standard DDPG by 16.1 percentage points. Thermal comfort during occupied hours maintains PMV ∈ [−0.5, 0.5] for 98.3% of operational time, peak demand decreases by 35.8%, and simulated coefficient of performance (COP) improves from 2.87 ± 0.08 to 4.12 ± 0.10. Physics constraint violations are reduced by approximately 98.6% compared to unconstrained DDPG, demonstrating the effectiveness of architectural enforcement mechanisms within the simulation environment. We present a reference prototype and commit to a future public release of the code, configurations, and hyperparameters sufficient to reproduce the reported results. The paper explicitly addresses the limitations of simulation-based studies and presents a staged roadmap toward hardware-in-the-loop testing and pilot deployments in real buildings.

3 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
SHSattar Hedayat
Sattar Hedayat
TZTina Ziarati
Tina Ziarati
Matteo ManganelliMatteo Manganelli
Matteo Manganelli
This paper presents a physics-informed reinforcement learning framework that em-beds thermodynamic constraints directly into the policy network of a continu-ous-control agent for HVAC optimization. We introduce a Thermodynamical-ly-Constrained Deep Deterministic Policy Gradient (TC-DDPG) algorithm that oper-ates on continuous actions and enforces physical feasibility through a differentiable constraint layer coupled with physics-regularized loss functions. In simulation-based evaluation using a custom Python multi-zone resistance-capacitance (RC) thermal model, the proposed method achieves 34.7% reduction in annual HVAC electricity consumption relative to a rule-based baseline (95% CI: 31.2–38.1%, n=50 runs) and outperforms standard DDPG by 16.1 percentage points. Thermal comfort during oc-cupied hours maintains PMV ∈ [−0.5, 0.5] for 98.3% of operational time, peak demand decreases by 35.8%, and simulated coefficient of performance (COP) improves from 2.87 ± 0.08 to 4.12 ± 0.10. Physics constraint violations are reduced by approximately 98.6% compared to unconstrained DDPG, demonstrating the effectiveness of archi-tectural enforcement mechanisms within the simulation environment. We provide complete code, model configurations, and hyperparameters to enable reproduction. The paper explicitly addresses the limitations of simulation-based studies and presents a staged roadmap toward hardware-in-the-loop testing and pilot deployments in real buildings.