Pan-European forest maps produced with a combination of earth observation data and national forest inventory plotsZenodo by Jukka Miettinen, Johannes Breidenbach, Patricia Adame, Radim Adolt, Iciar Alberdi, Oleg Antropov, Ólafur Arnarsson, Rasmus Astrup, Ambros Berger, Jón Bogason, Gherardo Chirici, Piermaria Corona, Giovanni D'Amico, Jiří Fejfar, Christoph Fischer, Florence Gohon, Thomas Gschwantner, Johannes Hertzler, Zsofia Koma, Kari T. Korhonen, Luka Krajnc, Nicolas Latte, Philippe Lejeune, Andrew McCullagh, Marcin Mionskowski, Daniel Moreno-Fernández, Mari Myllymäki, Mats Nilsson, Jérôme Perin, Juho Pitkänen, John Redmond, Thomas Riedel, Johannes Schumacher, Lauri Seitsonen, Laura Sirro, Mitja Skudnik, Arnór Snorrason, Radosław Sroga, Berthold Traub, Björn Traustason, Bertil Westerlund, Stephanie Wurpillot

“…Maps were created independently for 13 multi-country processing areas. Root-mean-squared-errors (RMSEs) for AGB ranged from 53 % in the Nordic processing area to 73 % in the South-Eastern area. …”
Get full text

P-Band PolInSAR Sub-Canopy Terrain Retrieval in Tropical Forests Using Forest Height-to-Unpenetrated Depth Mapping by Chuanjun Wu, Jiali Hou, Peng Shen, Sai Wang, Gang Chen, Lu Zhang

“…A nonlinear iterative optimization algorithm is then employed to estimate forest height, from which a fundamental mapping between forest height and unpenetrated depth is established. …”
Get full text

An explicit forest carbon stock model and applications by Ningning Zhu, Bisheng Yang, Weishu Gong, Shen Ying, Wenxia Dai, Zhen Dong

“…First, the pixel size, forest canopy density, terrain slope, and forest height were used in the construction of EFM; Second, the EFM parameters were solved by simulated forest scene; Third, the EFM was used in simulated and real forest scenes to verify the accuracy, robustness, and applicability, the experiments show that the relative error is about 15%; Finally, the first time mapping forest carbon stock over 200,000 km2 area at 2 m scale was completed by the EFM. …”
Get full text

Groundwater fluoride modeling using an artificial neural network: a review by Neeta Kumari, Gaurav Kumar, Saahil Hembrom

“…The prediction accuracy of the network can be assessed using root mean square error (RMSE) analysis and the coefficient of determination (R2). …”
Get full text

Mitigating Algorithmic Bias Through Probability Calibration: A Case Study on Lead Generation Data by Miroslav Nikolić, Danilo Nikolić, Miroslav Stefanović, Sara Koprivica, Darko Stefanović

Get full text

Predicting the Multiphotonic Absorption in Graphene by Machine Learning by José Zahid García-Córdova, Jose Alberto Arano-Martinez, Cecilia Mercado-Zúñiga, Claudia Lizbeth Martínez-González, Carlos Torres-Torres

“…Decision tree-based models, such as random forests and gradient boosting regression, demonstrated superior performance compared to linear regression, especially in terms of mean squared error. …”
Get full text

Mapping forest types along ecological gradient in Pakistan by Naveed Ahmad, Syed Ghias Ali

“…DT showed that annual precipitation was the most important predictor for forest type classification with risk estimate of 0.412 (std error 0.31) and 0.478 (std error 0.52) for training and validation respectively. …”
Get full text

Estimation of Forest Aboveground Biomass Using Multitemporal Quad-Polarimetric PALSAR-2 SAR Data by Model-Free Decomposition Approach in Planted Forest by Cong Peng, Chao Fang, Jiangping Long, Tingchen Zhang, Huanna Zheng, Zilin Ye

“…Moreover, given the model-based or model-free decomposition methods, using the combined datasets from multitemporal SAR images led to a substantial increase in determination coefficient (R2) and a great decrease of relative root mean square error (rRMSE) of mapping forest AGB for each regression method than using the individual images. …”
Get full text

Complexity control method of random forest based HEVC by Peng WEN, Zongju PENG, Fen CHEN, Gangyi JIANG, Mei YU

“…High efficiency video coding (HEVC) has high computational complexity,and fast algorithm cannot perform video coding under restricted coding time.Therefore,a complexity control method of HEVC based on random forest was proposed.Firstly,three random forest classifiers with different prediction accuracy were trained to provide various coding configurations for coding tree unit (CTU).Then,an average depth-complexity model was built to allocate CTU complexity.Finally,the CTU coding configuration,determined by the smoothness,average depth,bit,and CTU-level accumulated coding error,was used to complete complexity control.The experimental results show that the proposed method has better complexity control precision,and outperforms the state-of-the-art method in terms of video quality.…”
Get full text

Application of Forest Integrity Assessment to Determine Community Diversity in Plantation Forests Managed Under Carbon Sequestration Projects in the Western Qinba Mountains, China by Chun-Jing Wang, Dong-Zhou Deng, Wu-Xian Yan, Zhi-Wen Gao, Shan-Feng Huang, Ji-Zhong Wan

“…FIA scores were closely associated with Pielou’s evenness index of plant communities in plantation forests managed under carbon sequestration projects (R² = 0.104; mean square error = 0.014; standard error = 0.104; <i>p</i> = 0.012). …”
Get full text

Predicting Diameter Distributions in Mixed Forests in Southern Mexico by Juan Carlos Guzmán-Santiago, Héctor Manuel de los Santos-Posadas, Benedicto Vargas-Larreta, Martín Gómez-Cárdenas, Wenceslao Santiago-García, Adan Nava-Nava

“…Understanding the diameter structure of a stand is crucial for making informed decisions regarding silviculture and forest management. This is achieved by collecting forest inventory data and applying them to probability density functions. …”
Get full text

Forecasting Delivery Time of Goods in Supply Chains Using Machine Learning Methods by V. K. Rezvanov, O. M. Romakina, E. V. Zaytseva

“…Low values of the mean square error (0.0367) and mean absolute error (0.0324) were recorded. …”
Get full text

Estimation of Solar Diffuse Radiation in Chongqing Based on Random Forest by Peihan Wan, Yongjian He, Chaoyu Zheng, Jiaxiong Wen, Zhuting Gu

“…The model was validated using 8179 measured data points, demonstrating good predictive capability with a correlation coefficient (R²) of 0.72, a mean absolute error (MAE) of 35.99 W/m², and a root mean square error (RMSE) of 50.46 W/m². …”
Get full text

New Possibilities of Field Data Survey in Forest Road Design by Mihael Lovrinčević, Ivica Papa, David Janeš, Luka Hodak, Tibor Pentek, Andreja Đuka

“…Field data, as the basis for planning and designing forest roads, must have high spatial accuracy. Classical (using a theodolite and a level) and modern (based on total stations and GNSSs) surveying methods are used in current field data survey for forest road design. …”
Get full text

ANALYSIS OF MULTITEMPORAL AERIAL IMAGES FOR FENYŐFŐ FOREST CHANGE DETECTION by SHUKHRAT SHOKIROV, GÉZA KIRÁLY

“…Overall accuracy of classification was 77.2%, analysis showed that coniferous tree type classification was very accurate, but deciduous tree classification had a lot of omission errors. Based on the results and analysis, general information about forest health conditions has been presented. …”

Anomaly detection research using Isolation Forest in Machine Learning by A. S. Kechedzhiev, O. L. Tsvetkova

“…The study includes data preprocessing, training the model on the training set, and evaluating the model's performance on the test set using accuracy metrics, error matrix, and classification report. To implement this research, the Python programming language and the scikit-learn library were chosen to implement the Isolation Forest, as well as Pandas for working with data.Result. …”
Get full text

An Approach to Predicting Urban Carbon Stock Using a Self-Attention Convolutional Long Short-Term Memory Network Model: A Case Study in Wuhan Urban Circle by Zhi Zhou, Xueling Wu, Bo Peng

“…For forests, grasslands, and water bodies, the future spatial error model (SEM) indicated that for each unit increase in carbon stock change, the SLUDD would increase by 55, 7, and −305 units, respectively. …”
Get full text

Assessment and improvement of GEDI canopy height estimation in tropical and temperate forests by Myung-Sik Cho, David P. Roy, Herve B. Kashongwe, Lin Yan, Meicheng Shen

“…The approach is demonstrated at a tropical evergreen lowland forest site in the Democratic Republic of Congo (MNDP), a temperate pine and hardwood forest site in Alabama (TALL), and a temperate mix-species forest site in Maryland (SERC). …”
Get full text

Random Forest–Based Coal Mine Roof Displacement Prediction and Application by Hongxia Li, Rong Wu, Jianan Gao

“…R2, mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE) are selected to evaluate the performance of the models. …”
Get full text

Improving prediction of solar radiation using Cheetah Optimizer and Random Forest. by Ibrahim Al-Shourbaji, Pramod H Kachare, Abdoh Jabbari, Raimund Kirner, Digambar Puri, Mostafa Mehanawi, Abdalla Alameen

“…Evaluation metrics encompassing Mean Absolute Error (MAE), Mean Squared Error (MSE), and coefficient of determination (R2) are employed to validate its performance. …”
Get full text