Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls
The objective of this study was to explore the potential of a machine learning algorithm, the Support Vector Machine Regression (SVR), to forecast long-term hygrothermal responses and the moisture performance of light wood frame and massive timber walls. Hygrothermal simulations were performed using...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/11/5/188 |
| _version_ | 1827693699934453760 |
|---|---|
| author | Naman Bansal Maurice Defo Michael A. Lacasse |
| author_facet | Naman Bansal Maurice Defo Michael A. Lacasse |
| author_sort | Naman Bansal |
| collection | DOAJ |
| description | The objective of this study was to explore the potential of a machine learning algorithm, the Support Vector Machine Regression (SVR), to forecast long-term hygrothermal responses and the moisture performance of light wood frame and massive timber walls. Hygrothermal simulations were performed using a 31-year long series of climate data in three cities across Canada. Then, the first 5 years of the series were used in each case to train the model, which was then used to forecast the hygrothermal responses (temperature and relative humidity) and moisture performance indicator (mold growth index) for the remaining years of the series. The location of interest was the exterior layer of the OSB and cross-laminated timber in the case of the wood frame wall and massive timber wall, respectively. A sliding window approach was used to incorporate the dependence of the hygrothermal response on the past climatic conditions, which allowed SVR to capture time, implicitly. The variable selection was performed using the Least Absolute Shrinkage and Selection Operator, which revealed wind-driven rain, relative humidity, temperature, and direct radiation as the most contributing climate variables. The results show that SVR can be effectively used to forecast hygrothermal responses and moisture performance on a long climate data series for most of the cases studied. In some cases, discrepancies were observed due to the lack of capturing the full range of variability of climate variables during the first 5 years. |
| first_indexed | 2024-03-10T11:50:07Z |
| format | Article |
| id | doaj.art-6169f7eb3ee74f05b0ae7787209fbea6 |
| institution | Directory Open Access Journal |
| issn | 2075-5309 |
| language | English |
| last_indexed | 2024-03-10T11:50:07Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj.art-6169f7eb3ee74f05b0ae7787209fbea62023-11-21T17:48:11ZengMDPI AGBuildings2075-53092021-04-0111518810.3390/buildings11050188Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber WallsNaman Bansal0Maurice Defo1Michael A. Lacasse2National Research Council Canada, Construction Research Centre, Ottawa, ON K1A 0R6, CanadaNational Research Council Canada, Construction Research Centre, Ottawa, ON K1A 0R6, CanadaNational Research Council Canada, Construction Research Centre, Ottawa, ON K1A 0R6, CanadaThe objective of this study was to explore the potential of a machine learning algorithm, the Support Vector Machine Regression (SVR), to forecast long-term hygrothermal responses and the moisture performance of light wood frame and massive timber walls. Hygrothermal simulations were performed using a 31-year long series of climate data in three cities across Canada. Then, the first 5 years of the series were used in each case to train the model, which was then used to forecast the hygrothermal responses (temperature and relative humidity) and moisture performance indicator (mold growth index) for the remaining years of the series. The location of interest was the exterior layer of the OSB and cross-laminated timber in the case of the wood frame wall and massive timber wall, respectively. A sliding window approach was used to incorporate the dependence of the hygrothermal response on the past climatic conditions, which allowed SVR to capture time, implicitly. The variable selection was performed using the Least Absolute Shrinkage and Selection Operator, which revealed wind-driven rain, relative humidity, temperature, and direct radiation as the most contributing climate variables. The results show that SVR can be effectively used to forecast hygrothermal responses and moisture performance on a long climate data series for most of the cases studied. In some cases, discrepancies were observed due to the lack of capturing the full range of variability of climate variables during the first 5 years.https://www.mdpi.com/2075-5309/11/5/188support vector regressionmoisture performance predictionmassive timber wallwood frame wall |
| spellingShingle | Naman Bansal Maurice Defo Michael A. Lacasse Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls Buildings support vector regression moisture performance prediction massive timber wall wood frame wall |
| title | Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls |
| title_full | Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls |
| title_fullStr | Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls |
| title_full_unstemmed | Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls |
| title_short | Application of Support Vector Regression to the Prediction of the Long-Term Impacts of Climate Change on the Moisture Performance of Wood Frame and Massive Timber Walls |
| title_sort | application of support vector regression to the prediction of the long term impacts of climate change on the moisture performance of wood frame and massive timber walls |
| topic | support vector regression moisture performance prediction massive timber wall wood frame wall |
| url | https://www.mdpi.com/2075-5309/11/5/188 |
| work_keys_str_mv | AT namanbansal applicationofsupportvectorregressiontothepredictionofthelongtermimpactsofclimatechangeonthemoistureperformanceofwoodframeandmassivetimberwalls AT mauricedefo applicationofsupportvectorregressiontothepredictionofthelongtermimpactsofclimatechangeonthemoistureperformanceofwoodframeandmassivetimberwalls AT michaelalacasse applicationofsupportvectorregressiontothepredictionofthelongtermimpactsofclimatechangeonthemoistureperformanceofwoodframeandmassivetimberwalls |