Digital mapping of soil organic carbon stocks in the forest lands of Dominican Republic by Efraín Duarte, Erick Zagal, Juan A. Barrera, Francis Dube, Fabio Casco, Alexander J. Hernández

“…Model A reported the lowest prediction error and uncertainty with an R2 of 0.83, an RMSE of 35.02 Mg C ha−1. …”
Get full text

Implications of Climate Change for Bird Conservation in the Southwestern U.S. under Three Alternative Futures. by Megan M Friggens, Deborah M Finch

“…Using Maximum Entropy (MaxEnt3.3.3) modeling, we characterized habitat relationships and generated spatial predictions of habitat suitability for the Lucy's warbler (Oreothlypis luciae), the Southwestern willow flycatcher (Empidonax traillii extimus) and the Western yellow-billed cuckoo (Coccyzus americanus). …”
Get full text

The fatigue life estimation of the porous AlSi9Cu3 alloy based on the classification of pore geometry using multivariate probability distribution density by Dejan Tomažinčič, Branislav Panić, Marko Nagode, Jernej Klemenc

“…The proposed method offers a significant improvement in the accuracy of modeling fatigue life curves with respect to the spatial topology of porosity because it is leveraging μ-CT imaging for quantitative macrostructural characterization with statistical analysis. …”
Get full text

A GNN-Based False Data Detection Scheme for Smart Grids by Junhong Qiu, Xinxin Zhang, Tao Wang, Huiying Hou, Siyuan Wang, Tiejun Yang

“…However, since topological changes of power networks in smart grids often already predict the occurrence of anomalies, traditional models based on STGNNs to portray network evolution cannot be directly utilized in smart grids. …”
Get full text

The influence of climate change on the potential distribution of Ageratum conyzoides in China by Yuan Wang, Yonggang Yang, Minggang Zhang

“…Our results demonstrate that the ensemble model, constructed from the top seven single models, outperforms the individual models in predicting the suitable habitat of A. conyzoides. …”
Get full text

An edge sensitivity based gradient attack on graph isomorphic networks for graph classification problems by Srinitish Srinivasan, Chandraumakantham OmKumar

“…We experimentally validate this model on 4 benchmark datasets in the molecular property prediction literature where our model outperformed over 75% of all LLM-based architectures. …”
Get full text

Measurement of Suspended Sediment Concentration at the Outlet of the Yellow River Canyon: Using Sentinel-2 Images and Machine Learning by Genxin Song, Youjing Jiang, Xinyu Lei, Shiyan Zhai

“…Overall, the random forest model outperformed traditional methods in SSC prediction for sediment-laden rivers.…”
Get full text

Urbanization and forecast possibilities of land use changes by 2050: New evidence in Ho Chi Minh city, Vietnam by Tuan Nguyen Tran, Hegedűs Gábor, Phuong Nguyen Thi Tung

“…With an accuracy of 91%, the study predicts that by 2030, agricultural land will still account for more than half of HCM city’s area, but by 2050, this land group will only account for less than 40%. …”
Get full text

Integrated geophysical prospecting for deep ore detection in the Yongxin gold mining area, Heilongjiang, China by Yechang Yin, Jun Chen, Zhonghai Zhao, Yuanjiang Yang, Chenglu Li, Haina Li, Xiang Zhao

“…Abstract Geophysical exploration techniques play a pivotal role in enhancing the accuracy of mineral prospecting predictions. However, relying solely on individual methods often introduces uncertainties. …”
Get full text

Urban pertussis epidemiological patterns in a highly vaccinated megacity: Policy impacts and control strategies in Chongqing, China, 2005-2024 by Rui Shen, Jiawei Xu, Yugang Li, Jianxing Yu, Na Sun, Zilu Xu, Xueying Xu, Xiao Liu, Yang Liu, Bosong Li, Li Qi, Luzhao Feng

“…Methods: Using population-based surveillance data (2005-2024) from Chongqing (population 32.1 million; DTP3 coverage >97%), we conducted hierarchical Bayesian spatial modeling and age-structured Susceptible-Infected-Recovered-Vaccinated transmission analysis. …”
Get full text

A Regionalization of Downscaled GCM Data Considering Geographical Features in a Mountainous Area by Soojun Kim, Jaewon Kwak, Hung Soo Kim, Yonsoo Kim, Narae Kang, Seung Jin Hong, Jongso Lee

“…Future rainfall levels have been predicted by downscaling the data from CNRM-CM3 climate model, which was simulated under the A1B scenario. …”
Get full text

Monitoring soil salinization in Arid cotton fields using Unmanned Aerial Vehicle hyperspectral imagery by Jinming Zhang, Jianli Ding, Jiao Tan, Jinjie Wang, Zihan Zhang, Zeyuan Wang, Xiangyu Ge

“…The results indicate: (1) SG smoothing and FOD technology effectively enhanced the spectral characteristics of cotton field soils and crop canopies. (2) The soil salinity prediction model constructed using 0.7-order FOD combined with the BOSS algorithm yields the best performance, with an R2 of 0.92, RMSE of 0.15 dS m−1, and RPD of 3.54 on the test set. (3) The soil salinity distribution map generated from the optimal model clearly revealed the spatial distribution characteristics of salinity in the 0–10 cm topsoil layer, with significant differences observed under different cover conditions. …”
Get full text

Deep Learning-Based Atmospheric Visibility Detection by Yawei Qu, Yuxin Fang, Shengxuan Ji, Cheng Yuan, Hao Wu, Shengbo Zhu, Haoran Qin, Fan Que

“…This paper systematically reviews the applications of various deep learning models—Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and Transformer networks—in visibility estimation, prediction, and enhancement. …”
Get full text

Study on the Shock Wave Characteristics of Spherical and Cylindrical Explosives in Near-field Underwater Explosion by J. Yu, X. P. Zhang, J. Wang, Y. Hao, H. B. Mao

“…Therefore, precise prediction of shockwave loading characteristics for various charge shapes during underwater explosions is critical. …”
Get full text

Surface Multi-Hazard Effects of Underground Coal Mining in Mountainous Regions by Xuwen Tian, Xin Yao, Zhenkai Zhou, Tao Tao

“…Additionally, the subsidence continued even after coal mining operations concluded. Predictions derived from the logistic model indicate that the duration of residual surface subsidence in the study area is approximately 1 to 2 years. …”
Get full text

Hyperspectral Reconstruction Method Based on Global Gradient Information and Local Low-Rank Priors by Chipeng Cao, Jie Li, Pan Wang, Weiqiang Jin, Runrun Zou, Chun Qi

“…First, to improve the prior model’s efficiency in utilizing information of different frequencies, we design a gradient sampling strategy and training framework based on decision trees, leveraging changes in the loss function gradient information to enhance the model’s predictive capability for data of varying frequencies. …”
Get full text

A Spatiotemporal Attention-Guided Graph Neural Network for Precise Hyperspectral Estimation of Corn Nitrogen Content by Feiyu Lu, Boming Zhang, Yifei Hou, Xiao Xiong, Chaoran Dong, Wenbo Lu, Liangxue Li, Chunli Lv

“…A hyperspectral maize nitrogen content prediction model is proposed, integrating a dynamic spectral–spatiotemporal attention mechanism with a graph neural network, with the aim of enhancing the accuracy and stability of nitrogen estimation. …”
Get full text

Automated Detection of Center-Pivot Irrigation Systems from Remote Sensing Imagery Using Deep Learning by Aliasghar Bazrafkan, James Kim, Rob Proulx, Zhulu Lin

“…YOLOv11, using Landsat 8 panchromatic data, achieved the highest detection accuracy (precision: 0.98; recall: 0.91; and F1-score: 0.94) among all tested datasets and models. Spatial autocorrelation and hotspot analysis revealed systematic prediction errors, suggesting a need to adjust training data regionally. …”
Get full text

Mapping soil organic carbon stocks of different land use types in the Southern Moscow region by applying machine learning to legacy data by Yury A. Dvornikov, Lukyan A. Mirniy, Ekaterina S. Mukvich, Kristina V. Ivashchenko

“…The root mean square error of cross-validation (RMSEcv = 0.67 kg/m2) was chosen to describe the uncertainty of soil organic carbon stock prediction. According to the model, the total soil organic carbon stocks in the upper 10 cm soil layer of the Podolsky District were 2.65 0.72 Tg, for the Serpukhovsky District 2.77 0.73 Tg.…”
Get full text

Snow drought to hydrologic drought progression using machine learning and probabilistic analysis by Pouya Moghaddasi, Keyhan Gavahi, Hamid Moradkhani

“…This study explores the relationship between Snow Water Equivalent (SWE) and streamflow in snow-dominated watersheds using the Long Short-Term Memory (LSTM) model and probabilistic analysis. While LSTM model is typically used for prediction, we employed it primarily to understand how snow affects streamflow. …”
Get full text