Machine learning predicts improvement of functional outcomes in spinal cord injury patients after inpatient rehabilitation by Mohammad Rasoolinejad, Irene Say, Peter B. Wu, Xinran Liu, Yan Zhou, Yan Zhou, Nathan Zhang, Emily R. Rosario, Daniel C. Lu, Daniel C. Lu, Daniel C. Lu

“…The RF model exhibited the highest predictive accuracy, with an R-squared value of 0.90 and a Mean Squared Error (MSE) of 0.29 on the training dataset, while achieving 0.52 R-squared and 1.37 MSE on the test dataset. …”
Get full text

Estimation of Near-Surface Ozone Concentration Across China and Its Spatiotemporal Variations During the COVID-19 Pandemic by Shikang Guan, Xiaotong Zhang, Wenbo Zhao, Yanjun Duan, Xinpei Han, Lingfeng Lv, Mengyao Li, Bo Jiang, Yunjun Yao, Shunlin Liang

“…The validation results against the ground measurements indicate that the developed SDSTRF model effectively captures O₃ variations, achieving a coefficient of determination of 0.83 and a root mean square error of 20.37 μg/m³. The spatiotemporal variations of O₃ concentrations were investigated using the generated dataset. …”
Get full text

Weaning performance prediction in lactating sows using machine learning, for precision nutrition and intelligent feeding by Jiayi Su, Xiangfeng Kong, Wenliang Wang, Qian Xie, Chengming Wang, Bie Tan, Jing Wang

“…The findings demonstrated that the ensemble learning models, specifically random forest and gradient boosting decision tree regression, delivered the best overall performance, with a coefficient of determination (R2) ranging from 0.40 to 0.80 and a mean absolute error (MAE) between 0.11 and 4.36. …”
Get full text

Self SOC Estimation for Second-Life Lithium-Ion Batteries by Joelton Deonei Gotz, Emilson Ribeiro Viana, Jose Rodolfo Galvao, Fernanda Cristina Correa, Milton Borsato, Alceu Andre Badin

“…The results indicated a root square mean error (RSME) below 45 mAh for the capacity estimation (phase 1), and an RSME below 0.87% was found in the second phase for the SOC estimation. …”
Get full text

WetCH₄: a machine-learning-based upscaling of methane fluxes of northern wetlands during 2016–2022 by Q. Ying, Q. Ying, B. Poulter, J. D. Watts, K. A. Arndt, A.-M. Virkkala, L. Bruhwiler, Y. Oh, Y. Oh, B. M. Rogers, S. M. Natali, H. Sullivan, A. Armstrong, A. Armstrong, E. J. Ward, E. J. Ward, L. D. Schiferl, C. D. Elder, C. D. Elder, O. Peltola, A. Bartsch, A. R. Desai, E. Euskirchen, M. Göckede, B. Lehner, M. B. Nilsson, M. Peichl, O. Sonnentag, E.-S. Tuittila, T. Sachs, T. Sachs, A. Kalhori, M. Ueyama, Z. Zhang, Z. Zhang

Get full text

Modelación de estructuras diamétricas con la función Log-Logistic en bosques naturales de Durango, México by Sacramento Corral-Rivas, Omar Martínez-Ruíz, Juan Abel Nájera-Luna, Friday Nwabueze Ogana, José Javier Corral-Rivas

“…Para la modelización de la distribución diamétrica se evaluó el comportamiento gráfico y numérico de los métodos de predicción (PPM) y recuperación de parámetros (PRM) con el sesgo medio (SM) y error medio absoluto (EMA). El mejor estimador de parámetros resultó del diámetro que acumula los percentiles 25 y 79%, considerando el porcentaje de rodales donde fue más preciso en términos de KS, AD y W2, así como su rendimiento respecto a máxima verosimilitud. …”
Get full text

Multi-Index Assessment and Machine Learning Integration for Drought Monitoring Using Google Earth Engine by Xulong Duan, Rana Waqar Aslam, Syed Ali Asad Naqvi, Dmitry E. Kucher, Zohaib Afzal, Danish Raza, Rana Muhammad Zulqarnain, Yahia Said

“…The framework’s AI-driven error correction and multisensor synergy provide a scalable model for drought applications, such as ecosystem resilience monitoring (integrating thermal and optical analysis) and hydrological modelling (fusing soil moisture, precipitation, and vegetation datasets). …”
Get full text

Identification of Earthquake Precursors Origin and AI Framework for Automatic Classification for One of These Precursors by Ghada Ali, Lotfy Samy, Omar M. Saad, Ali G. Hafez, El-Sayed Hasaneen, Kamal AbdElrahman, Ibrahim Salah, Mohammed S. Fnais, Hamed Nofel, Ahmed M. Mohamed

“…By automating the classification of these patterns, the true P-wave arrival can be determined in real-time processing, reducing the error in P-wave arrival timing. The current study also introduces this automatic classification by developing various machine learning (ML) and Convolutional Neural Network (CNN) models to highlight the features characterizing each pattern. …”
Get full text

Interpreting machine learning models based on SHAP values in predicting suspended sediment concentration by Houda Lamane, Latifa Mouhir, Rachid Moussadek, Bouamar Baghdad, Ozgur Kisi, Ali El Bilali

“…Three metrics (coefficient of correlation (r), root mean square error (RMSE), and Nash–Sutcliffe model-fit efficiency (NSE)) and a more advanced interpretation system SHapley Additive exPlanations (SHAP) are used to assess the performance of these models applied to hydro-climatic datasets for prediction of SSC. …”
Get full text

Prediction of carbon dioxide emissions from Atlantic Canadian potato fields using advanced hybridized machine learning algorithms – Nexus of field data and modelling by Muhammad Hassan, Khabat Khosravi, Aitazaz A. Farooque, Travis J. Esau, Alaba Boluwade, Rehan Sadiq

“…In this study, three novel machine learning algorithms of additive regression-random forest (AR-RF), Iterative Classifier Optimizer (ICO-AR-RF), and multi-scheme (MS-RF) were explored for carbon dioxide (CO2) flux rate prediction from three agricultural fields. …”
Get full text

Alterations in tidal volume over recording time during pulmonary function testing by barometric whole-body plethysmography in client-owned cats: a multicenter retrospective investi... by Wei-Tao Chang, Laín García-Guasch, Hannah Gareis, Bianka Schulz, Yoshiki Yamaya, Pei-Ying Lo, Chin-Hao Chang, Hui-Wen Chen, Chung-Hui Lin

“…The trend of alterations in TV was not affected by site, emotional status, health status, age, or gender. Forest plots with 95% confidence intervals of TV generated from short sections, alongside conventional data averaging breaths over a 5-minute period (TV-All), showed acceptable margins of error at all sites. …”
Get full text

Effectiveness of a transfluthrin emanator and insecticide-treated barrier screen in reducing Anopheles biting in a temporary shelter in Sumatra, Indonesia by Timothy A. Burton, Lepa Syahrani, Dendi Hadi Permana, Ismail Ekoprayitno Rozi, Rifqi Risandi, Siti Zubaidah, Syarifah Zulfah, Ma’as M. Maloha, Rusli Efendi, Maria Kristiana, Puji B. S. Asih, Din Syafruddin, Neil F. Lobo

“…Collections occurred near Bukit Duabelas National Park in central Sumatra, Indonesia, an area characterized by secondary forest undergoing widespread conversion to palm and rubber plantations. …”
Get full text

A novel approach for downscaling land surface temperature from 30 m to 10 m using land features multi-interaction by Alfred Homère Ngandam Mfondoum, Sofia Hakdaoui, Ali Mihi, Ibrahima Diba, Mesmin Tchindjang, Luc Beni Moutila, Frederic Chamberlain Lounang Tchatchouang

“…Finally, the machine learning algorithm of random forest based on different seeds achieved overall accuracy between [0.92–1]. …”
Get full text

Standardized conversion model for retinal thickness measurements between spectral-domain and swept-source optical coherence tomography based on machine learning by Zhongping Tian, Yinning Guo, Xi Chen, Qifeng Zhou, Yuan Liu, Zhizhu Yi, Li Zhang, Li Zhang

“…Model efficacy was assessed using coefficient of determination (R2) and root mean square error (RMSE).ResultsStatistically significant inter-device discrepancies (P < 0.001) were identified in 9 macular sectors, all GCIPL parameters (average and six-sector measurements), and RNFL measurements (average thickness and three quadrants, excluding nasal sector). …”
Get full text

Development of hybrid stacking machine learning for evaluating parameters affecting refrigerated shrimp coated with chitosan-loaded Salvia officinalis nanoemulsions by Mehran Sayadi, Elahe Abedi, Najmeh Oliyaei, Maryam Mousavifard

“…The hybrid model consistently achieved high R² values, such as R2-train=0.986 and R2-test=0.986 for pH and R2-train=0.958 and R2-test=0.997 for overall acceptability, while maintaining low mean absolute error (MAE) values, notably 0.105 for pH and 0.138 for overall acceptability. …”
Get full text

Ten simple rules for working with high resolution remote sensing data by Mahood, Adam L., Joseph, Maxwell B., Spiers, Anna I., Koontz, Michael J., Ilangakoon, Nayani, Solvik, Kylen K., Quarderer, Nathan, McGlinchy, Joe, Scholl, Victoria M., St. Denis, Lise A., Nagy, Chelsea, Braswell, Anna, Rossi, Matthew W., Herwehe, Lauren, Wasser, Leah, Cattau, Megan E., Iglesias, Virginia, Yao, Fangfang, Leyk, Stefan, Balch, Jennifer K.

Get full text

Spatial Prediction of Soil Total Phosphorus in a Karst Area: Comparing GWR and Residual-Centered Kriging by Laimou Lu, Penghui Li, Liang Zhong, Mingbao Luo, Liyuan Xing, Chunlai Zhang

“…The GWRK model exhibited superior accuracy (80.6%), with predicted concentration of TP closely aligning with observed TP values, effectively capturing fine spatial variations, and showing the lowest mean standardized error, average standard error, and mean absolute error. …”
Get full text

Regression models for the prediction of the influence of magnesium ions on primary endothelial cell (HUVEC) proliferation and migration by Heike Helmholz, Redon Resuli, Marius Tacke, Jalil Nourisa, Sven Tomforde, Roland Aydin, Regine Willumeit-Römer, Berit Zeller-Plumhoff

“…Using these machine learning methods, we were able to predict the proliferation of HUVECs for missing Mg concentrations and for missing passages with mean absolute errors below 10 % and as low as 8.5 %, respectively. …”
Get full text

Machine learning assisted estimation of total solids content of drilling fluids by B.T. Gunel, Y.D. Pak, A.Ö. Herekeli, S. Gül, B. Kulga, E. Artun

“…Further optimization of the random forests model resulted in a mean absolute percentage error (MAPE) of 3.9% and 9.6% and R2 of 0.99 and 0.93 for the training and testing sets, respectively. …”
Get full text

Landscape fragmentation reduces but shape complexity enhances soil loss: Evidence from the plain grain-producing area along the Yangtze River in China by Shunqian Gao, Wenyi Yang, Xingyu Tan, Shumi Liu, Yangbiao Li, Xingzi Yu, Zhen Wang, Zhanhang Zhou, Chen Zeng

“…By prioritizing the conversion of approximately 5,400 ha of cropland with slopes greater than 15° in these areas into forest, soil loss was expected to be reduced by about 2,606 t. …”
Get full text