Exploration of slope-type geological hazard susceptibility evaluation based on dynamic correction of SBAS-InSAR technology: A case study of Kang County in Gansu Province by Rongwei Li, Pengwei Wang, Shucheng Tan, Yangbiao Zhou, Lifeng Liu, Chaodong Gou, Yalan Yu

“…This correction framework corrects the susceptibility results of the Random Forest (RF) model, which is based on 12 static factors and historical hazard data, using surface deformation data measured by the SBAS-InSAR technique. …”
Get full text

Decoding methane concentration in Alberta oil sands: A machine learning exploration by Liubov Sysoeva, Ilhem Bouderbala, Miles H. Kent, Esha Saha, B.A. Zambrano-Luna, Russell Milne, Hao Wang

“…We introduce a multi-step framework for finding the primary factors associated with higher methane concentrations, powered by machine learning models (such as random forest) trained on high dimensional datasets sourced from multiple weather monitoring stations located in the Lower Athabasca region. …”
Get full text

Spatiotemporal Variations in Compound Extreme Events and Their Cumulative and Lagged Effects on Vegetation in the Northern Permafrost Regions from 1982 to 2022 by Yunxia Dong, Guimin Liu, Xiaodong Wu, Lin Wang, Haiyan Xu, Sizhong Yang, Tonghua Wu, Evgeny Abakumov, Jun Zhao, Xingyuan Cui, Meiqi Shao

“…The temporal effects of compound extreme events on kNDVI vary with vegetation type; they produce more cumulative and lagged effects compared with single extreme high-temperature events and fewer effects compared with single extreme precipitation events, with compound events significantly affecting forest and grassland ecosystems. Notably, extreme high temperature–precipitation compound events exhibit the strongest cumulative and lagged effects on vegetation, while extreme low temperature–drought compound events influence wetland and shrubland areas within the same month. …”
Get full text

Global surface eddy mixing ellipses: spatio-temporal variability and machine learning prediction by Tian Jing, Ru Chen, Chuanyu Liu, Chunhua Qiu, Chunhua Qiu, Cuicui Zhang, Mei Hong

“…We also assessed the predictability of global mixing ellipses using machine learning algorithms, including Spatial Transformer Networks (STN), Convolutional Neural Network (CNN) and Random Forest (RF), with mean-flow and eddy- properties as features. …”
Get full text

Identification of serum tRNA-derived small RNAs biosignature for diagnosis of tuberculosis by Zikun Huang, Qing Luo, Cuifen Xiong, Haiyan Zhu, Chao Yu, Jianqing Xu, Yiping Peng, Junming Li, Aiping Le

“…By utilizing cross-validation with a random forest algorithm approach, the training cohort achieved a sensitivity of 100% and specificity of 100%. …”
Get full text

Long-Term Predictive Modelling of the Craniofacial Complex Using Machine Learning on 2D Cephalometric Radiographs by Michael Myers, Michael D. Brown, Sarkhan Badirli, George J. Eckert, Diane Helen-Marie Johnson, Hakan Turkkahraman

“…Three ML models—Lasso regression, Random Forest, and Support Vector Regression (SVR)—were trained on a subset of 240 subjects, while 61 subjects were used for testing. …”
Get full text

Health system responsiveness: comparison of different levels of medical institutions in Kunshan City, China by Zhuang Hong, Jing Lu, Gang Chen, Qi Tang, Heqi Sun, Ting Wei, Sitang Zhao, Jun Lu

“…Linear regression and ordinal logistics were applied to explore the relationship between different hospital levels and HSR. Forest plots were used to illustrate the relationship between each domain and the hospital level.Results The relationship between hospital level and HSR remained significant (p < 0.05). …”
Get full text

Production-living-ecological functions measurement and spatio-temporal evolution of the coastal zone under the perspective of land-sea coordination: a case study of Liaoning Coasta... by Lina Ke, Lei Wang, Quanming Wang, Zhiyu Ren, Yao Lu, Shusheng Yin, Yu Zhao, Qin Tan, Yibo Li

“…The results show that: (1) The production and living spaces on land are concentrated near the coastline, and the ecological space is mainly distributed in the mountainous forest area. The sea is dominated by the production space, and the living and ecological spaces occupy a relatively small proportion. (2) While the land has significant multifunctionality, the sea has a single PLEF, with the production function dominating and accounting for more than 90%. (3) In the period 2005–2010, the frequency of mutual transformation of the different PLES was the highest. …”
Get full text

Post‐Fire Sediment Yield From a Western Sierra Nevada Watershed Burned by the 2021 Caldor Fire by Amy E. East, Joshua B. Logan, Peter Dartnell, Helen W. Dow, Donald N. Lindsay, David B. Cavagnaro

“…We measured sediment yield from a forested, heavily managed 25.4‐km2 watershed in the western Sierra Nevada, California, over 2 years following the 2021 Caldor Fire, by repeat mapping of a reservoir where sediment accumulated from terrain with moderate to high soil burn severity. …”
Get full text

Estimation of minimum miscible pressure in carbon dioxide gas injection using machine learning methods by Ali Akbari, Ali Ranjbar, Yousef Kazemzadeh, Fatemeh Mohammadinia, Amirjavad Borhani

“…Furthermore, ML algorithms such as Artificial Neural Networks (ANN), Bayesian networks, Random Forest (RF), Support Vector Machine (SVM), LSBoost, and Linear Regression (LR) were employed to estimate MMP. …”
Get full text

Multi-omics analysis reveals the sensitivity of immunotherapy for unresectable non-small cell lung cancer by Rui Wu, Kunchen Wei, Xingshuai Huang, Yinge Zhou, Xiao Feng, Xin Dong, Hao Tang

“…Finally, potential biomarkers were picked out by applying machine learning methods including random forest and stepwise regression and prediction models were constructed by logistic regression.ResultsThe presence of metabolites and proteins in peripheral blood plasma was causally associated with both non-small cell lung cancer and PD-L1/PD-1 expression levels. …”
Get full text

Effects of ground bamboo application on weed suppression and rice production: a 3-year paddy field experiment by Masfiro Lailati, Yichen Shang, Thien Quang Huynh, Koji Ito, Naoya Katsumi, Yumiko Mizuuchi, Masaya Ino, Tadao Takashima, Nisikawa Usio

“…Abstract Background In light of the dramatic expansion of Japan’s bamboo forests, it is necessary to develop a strategy for the effective use of bamboo biomass resources. …”
Get full text

SMR-guided molecular subtyping and machine learning model reveals novel prognostic biomarkers and therapeutic targets in non-small cell lung adenocarcinoma by Baozhen Wang, Yichen Yin, Anqi Wang, Weidi Liu, Jing Chen, Tao Li

“…By performing correlation analysis and Cox regression analysis, we identified 26 prognostic genes and classified LUAD samples into two molecular subtypes with significantly distinct survival outcomes. The Random Survival Forest (RSF) model exhibited robust prognostic predictive capabilities across multiple independent cohorts (AUC > 0.75). …”
Get full text

Radiomic prediction for durable response to high‐dose methotrexate‐based chemotherapy in primary central nervous system lymphoma by Haoyi Li, Mingming Xiong, Ming Li, Caixia Sun, Dao Zheng, Leilei Yuan, Qian Chen, Song Lin, Zhenyu Liu, Xiaohui Ren

“…The radiomic‐clinical integrated models were developed using the random forest method. Model performance was externally validated to verify its clinical utility. …”
Get full text

3D highly isolated 6-port tri-band MIMO antenna system with 360° coverage for 5G IoT applications based machine learning verification by Md Afzalur Rahman, Samir Salem Al-Bawri, Sultan S. Alharbi, Wazie M. Abdulkawi, Noorlindawaty Md Jizat, Mohammad Tariqul Islam, Abdel-Fattah A. Sheta

“…In addition, the machine learning prediction is used to verify the single element realized gain, and the results demonstrate that it performs admirably with an accuracy of more than 89% using the random forest regression model throughout the entire frequency spectrum. …”
Get full text

Machine learning model and nomogram to predict the risk of heart failure hospitalization in peritoneal dialysis patients by Liping Xu, Fang Cao, Lian Wang, Weihua Liu, Meizhu Gao, Li Zhang, Fuyuan Hong, Miao Lin

“…Introduction The study presented here aimed to establish a predictive model for heart failure (HF) and all-cause mortality in peritoneal dialysis (PD) patients with machine learning (ML) algorithm.Methods We retrospectively included 1006 patients who initiated PD from 2010 to 2016. XGBoost, random forest (RF), and AdaBoost were used to train models for assessing risk for 1-year and 5-year HF hospitalization and mortality. …”
Get full text

Multiple Dimensions Define Thresholds for Population Resilience of the Eastern Oyster, Crassostrea virginica by Megan K. La Peyre, Hongqing Wang, Shaye E. Sable, Wei Wu, Bin Li, Devin Comba, Carlos Perez, Melanie Bates, Lauren M. Swam

“…Two statistical approaches were applied, with each model highlighting a different operational definition of a threshold: random forest models identified a threshold as an abrupt change in the oyster abundance‐ salinity relationship, while Bayesian models identified an increased probability of oyster abundance dropping below a critical threshold, defined here as less than 50% of the 5‐year mean. …”
Get full text

Spatiotemporal Variability of Channel Roughness and its Substantial Impacts on Flood Modeling Errors by Md Abdullah Al Mehedi, Shah Saki, Krutikkumar Patel, Chaopeng Shen, Sagy Cohen, Virginia Smith, Adnan Rajib, Emmanouil Anagnostou, Tadd Bindas, Kathryn Lawson

“…These large, diverse observations allowed training of a Random Forest (RF) model capable of predicting n (or alternative parameters) at high accuracy (Nash Sutcliffe model efficiency >0.7) in space and time. …”
Get full text

Integrative machine learning frameworks to uncover specific protein signature in neuroendocrine cervical carcinoma by Tao Shen, Tingting Dong, Haiyang Wang, Yi Ding, Jianuo Zhang, Xinyi Zhu, Yeping Ding, Wen Cai, Yalan Wei, Qiao Wang, Sufen Wang, Feiyun Jiang, Bin Tang

“…Eleven machine-learning algorithms were packaged into 66 combinations, of which we selected the optimal algorithm, including randomForest, SVM-RFE, and LASSO, to select key NECC specific dysregulated proteins (kNsDEPs). …”
Get full text

iMESc – an interactive machine learning app for environmental sciences by Danilo Cândido Vieira, Danilo Cândido Vieira, Fabiana S. Paula, Luciana Erika Yaginuma, Gustavo Fonseca

“…Finally, a hybrid model combining an unsupervised SOM and followed by the supervised Random Forest model returned an accuracy of 83.47% for the training and 80.77% for the test, with Bathymetry, Chlorophyll, and Coarse Sand as key predictive variables. …”
Get full text