Article
Engineering, Civil
Jie Yang, Saffet Yagiz, Ying-Jing Liu, Farid Laouafa
Summary: This study develops two novel prediction models for tunnel boring machine (TBM) performance using evolutionary polynomial regression (EPR) and random forest (RF) methods. Both models can accurately predict the TBM penetration rate and field penetration index based on four input parameters. The results show that the RF-based model has higher prediction accuracy and better outlier identification, while the EPR-based model is more convenient for field engineers to use.
Article
Environmental Sciences
Komal Shukla, Nikhil Dadheech, Prashant Kumar, Mukesh Khare
Summary: The study utilized linear regression and random forest regression models to predict photochemical pollutants levels in urban areas. The site-specific models performed well when considering meteorological conditions, while city-level linear regression models performed poorly. Random forest regression models performed satisfactorily in predicting NO, NO2, and O-3 at the indicative city level.
Article
Physics, Applied
Nguyen Thanh Son, Nguyen Hoang Tung, Nguyen Thanh Tung
Summary: In the past decade, there has been a growing interest in metamaterial absorbers (MMAs) due to their versatility in various applications. Machine learning (ML) has recently emerged as a powerful tool for predicting absorption behavior with less effort and cost. In this study, two ML algorithms, Polynomial Regression (PR) and Random Forest Regression (RFR), were utilized to forecast the absorption strength and frequency of a specific metamaterial structure. The models were trained on simulation-generated samples, and the results showed that PR outperformed RFR in predicting absorption strength while both algorithms had similar accuracy in predicting absorption frequency.
MODERN PHYSICS LETTERS B
(2023)
Article
Multidisciplinary Sciences
W. K. V. J. B. Kulasooriya, R. S. S. Ranasinghe, Udara Sachinthana Perera, P. Thisovithan, I. U. Ekanayake, D. P. P. Meddage
Summary: This study investigates the importance of utilizing explainable artificial intelligence (XAI) on various machine learning (ML) models to predict the strength characteristics of basalt-fiber reinforced concrete (BFRC). It introduces three tree-based ML models and two explanation methods to provide interpretable explanations for the predictions. The findings highlight the need for further XAI-based research in concrete strength prediction and involvement of domain experts to evaluate XAI results.
SCIENTIFIC REPORTS
(2023)
Article
Biodiversity Conservation
Robson Borges de Lima, Eric Bastos Gorgens, Anderson Pedro Bernardina Batista, Diego Armando Silva da Silva, Cinthia Pereira de Oliveira, Carla Samara Campelo de Sousa
Summary: The increasing availability of field data provides an opportunity to understand the ecological relationships and functions of large trees in tropical forests. The average wood density and diversity of genera and families are the most important attributes to discriminate biogeographic regions.
Article
Chemistry, Multidisciplinary
Akhilesh Vyas, Fotis Aisopos, Maria-Esther Vidal, Peter Garrard, George Paliouras
Summary: The study examines various clinical attributes of dementia patients, using machine learning models to calibrate MMSE scores accurately determining cognitive status and provides an effective classification mechanism to identify inaccurate MMSE values.
APPLIED SCIENCES-BASEL
(2021)
Article
Materials Science, Multidisciplinary
Jiahao Xi, Xiangdong Xing, Zhaoying Zheng, Yuxing Wang, Shuai Wang, Ming Lv
Summary: This study explores the impacts of three feature selection methods on the predictive model for FeO content in sinter. The results show that random forest feature selection is more suitable for this prediction model and exhibits good predictive performance and generalization capability.
Article
Forestry
Zhentian Ding, Biyong Ji, Hongwen Yao, Xuekun Cheng, Shuhong Yu, Xiaobo Sun, Shuhan Liu, Lin Xu, Yufeng Zhou, Yongjun Shi
Summary: This study utilized data from 773 permanent plots in Zhejiang Province, China, to identify key variables influencing forest mortality and construct mortality prediction models. The findings revealed that soil and stand-related factors had significant effects on mortality rate, while terrain and climate factors were not statistically significant. The Random Forest model showed the best fitting and prediction effect for mortality, using variables such as stand age, tree height, ADBH, crown cover, humus layer thickness, and the biodiversity index.
Article
Environmental Sciences
Saeid Shabani, Saeid Varamesh, Hossein Moayedi, Bao Le Van
Summary: This study modeled and spatially visualized the susceptibility of a forest stand in northern Iran to snowstorm damage using the random forest (RF) and logistic regression (LR) methods. The RF model outperformed the LR model in both training and validation phases, identifying slope, aspect, and wind effect as the variables with the greatest impacts on forest stand sustainability to snowstorm damage. Approximately 30% of the study area was categorized as highly and very highly susceptible to snowstorms. The results can inform forest managers in developing adaptive forest management plans for snowstorm readiness and recovery.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Engineering, Environmental
Shaojian Wang, Zhitao Liu, Yongxin Chen, Chuanglin Fang
Summary: This study analyzed the varying importance and spatiotemporal differentiation of factors influencing ecosystem services in China's Pearl River Delta from 2000 to 2015 using the random forest model and a geographically and temporally weighted regression model. The results showed an increase in the importance of human factors, a decrease in natural factors, and significant spatiotemporal differentiation in the influencing factors. These findings can guide decision makers in ecological management and policy making.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Multidisciplinary Sciences
Soongu Kwak, Hyun-Jung Lee, Seungyeon Kim, Jun-Bean Park, Seung-Pyo Lee, Hyung-Kwan Kim, Yong-Jin Kim
Summary: This study aimed to explore the differences in the association between cardiovascular risk factors and atherosclerotic cardiovascular disease (ASCVD) risk in men and women using machine learning. A random forest model was developed to predict the 10-year ASCVD probabilities in each sex. The results showed that there were significant sex-specific associations between cardiovascular risk factors and ASCVD events, with higher total cholesterol or LDL cholesterol levels being more strongly associated with the risk of ASCVD in men, while older age and increased waist circumference were more strongly associated with the risk of ASCVD in women.
SCIENTIFIC REPORTS
(2023)
Article
Environmental Studies
Joseph Oduro Appiah, Dina Adei, Williams Agyemang-Duah
Summary: Land uses and terrain characteristics have significant impacts on forest fragmentation. This study explores the relationship between the spatial distribution of core forest patches and land uses, as well as terrain variables. The results indicate that elevation and slope gradient influence the likelihood of forest patches being core forests. Furthermore, the proximity to logging sites and access roads also affects the odds of forest patches being core forests. The findings suggest that forest conservation efforts should prioritize higher elevations, steeper slopes, and areas far from human activities, while forest restoration should focus on areas close to human activities and lower elevations and slopes.
Article
Computer Science, Interdisciplinary Applications
Leyre Torre-Tojal, Aitor Bastarrika, Ana Boyano, Jose Manuel Lopez-Guede, Manuel Grana
Summary: This article utilizes random forest models to estimate the biomass of Pinus radiata species in a region of the Basque Autonomous Community. By tuning the hyperparameters and conducting cross-validation, two models with high R-2 values were obtained. These models were then applied to the municipality of Orozko, predicting a biomass that is 16-18% higher than the predictions made by the Basque Government.
JOURNAL OF COMPUTATIONAL SCIENCE
(2022)
Article
Geosciences, Multidisciplinary
Melisa Diaz Resquin, Pablo Lichtig, Diego Alessandrello, Marcelo De Oto, Dario Gomez, Cristina Rossler, Paula Castesana, Laura Dawidowski
Summary: Having a low-cost prediction model for air quality is important for research, forecasting, regulatory, and monitoring purposes, especially in Latin America where urbanization has led to increased stress on air quality. Machine learning techniques, particularly random forest, have been found to be effective and computationally efficient for air quality forecasting, capturing the nonlinear relationships among emissions, chemical reactions, and meteorological effects.
EARTH SYSTEM SCIENCE DATA
(2023)
Article
Ecology
Robin Singh Bhadoria, Manish Kumar Pandey, Pradeep Kundu
Summary: Human intervention causing forest fires hinders nature's ability to recover, leading to climate change consequences that we must take responsibility for and minimize. Mitigating fires by predicting and controlling their spread can be enhanced through machine learning models, like the proposed RVFR model, which achieves higher accuracy in predicting forest fires based on past data.
ECOLOGICAL INFORMATICS
(2021)