HPO-empowered machine learning with multiple environment variables enables spatial prediction of soil heavy metals in coastal delta farmland of China

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 213, P. 108254 - 108254

Published: Sept. 25, 2023

Language: Английский

---

Supporting early-stage design decisions with building performance optimisation: Findings from a design experiment

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 82, P. 108298 - 108298

Published: Dec. 15, 2023

Language: Английский

---

Research on Optimized Design of Rural Housing in Cold Regions Based on Parametrization and Machine Learning

Sustainability, Journal Year: 2024, Volume and Issue: 16(2), P. 667 - 667

Published: Jan. 12, 2024

With the rapid development of urbanization, emergence more self-built buildings in countryside has brought about energy waste problems and decreased comfort. Achieving low-carbon goal improving quality human living environment through architectural planning means have become vital issues. In this study, from a parametric perspective, model building performance simulation are carried out using Rhino Grasshopper, multi-objective optimization method neural network used as theoretical basis to train prediction after data collection processing. The validation R2 = 0.988 MSE 0.0148 indicates that can accurately reflect program’s performance. By establishing for rural residential buildings, decision-makers perform predictions under various parameter combinations at early design stage, facilitating screening types with high consumption costs. improve efficiency decision-making stage design, help save costs by high-energy-consuming types, conditions residents, reduce carbon emissions, contribute sustainable renewal areas.

Language: Английский

---

Research on the Design Strategy of Double–Skin Facade in Cold and Frigid Regions—Using Xinjiang Public Buildings as an Example

Sustainability, Journal Year: 2024, Volume and Issue: 16(11), P. 4766 - 4766

Published: June 3, 2024

In the context of global warming, focus on applying and researching double–skin facade (DSF) systems to reduce energy consumption in buildings has significantly increased. However, researchers have not thoroughly examined performance applicability DSFs severe cold regions with high winter heating demands. This study aims evaluate potential application harsh cities Northwest China investigate their role enhancing efficiency large public buildings. Through simulation a comprehensive evaluation using TOPSIS entropy weight method, effects 20 DSF schemes four Xinjiang (Kashgar, Urumqi, Altay, Turpan) were analyzed. The experimental results indicate that average EUI energy–saving rates Kashgar, Turpan are 64.75%, 63.19%, 56.70%, 49.41%, respectively. South–facing orientation is deemed optimal for cities, highest rate reaching 15.19%. benefits west–facing surpass those north–facing DSF. Conversely, order other south, north, west, east. An analysis heating, cooling, lighting reveals Box Windows exhibit superior efficiency, while Corridors more effective cooling. characteristic also evident installation various types curtain walls. Given relatively higher demand compared cooling urban areas, yields significant when facing or north; conversely, if there should be considered these three directions. Multistorey suitable east–facing cities. Selecting based specific conditions requirements can building consumption. research findings offer theoretical guidance designing implementing diverse regions.

Language: Английский

---

A hybrid ensemble learning framework for zero-energy potential prediction of photovoltaic direct-driven air conditioners

Journal of Building Engineering, Journal Year: 2022, Volume and Issue: 64, P. 105602 - 105602

Published: Nov. 24, 2022

Language: Английский

---