Evaluating and implementing temporal, spatial, and spatio-temporal methods for outbreak detection in a local syndromic surveillance system. by Robert W Mathes, Ramona Lall, Alison Levin-Rector, Jessica Sell, Marc Paladini, Kevin J Konty, Don Olson, Don Weiss

“…Of the spatial/spatio-temporal methods we tested, a spatial scan statistic detected 3% of all injects, a Bayes regression found 2%, and a generalized linear mixed model and a space-time permutation scan statistic detected none at a specificity of 95%. …”
Get full text

Predicting sport event outcomes using deep learning by Jianxiong Gao, Yi Cheng, Jianwei Gao

“…In this study, we present a deep learning framework that combines a one-dimensional convolutional neural network (1D CNN) with a Transformer architecture to improve prediction accuracy. The 1D CNN effectively captures local spatial patterns in structured match data, while the Transformer leverages self-attention mechanisms to model long-range dependencies. …”
Get full text

Predicting Forest Evapotranspiration using Remote Sensing and Machine Learning by B. Yadav, L. K. Sharma, B. Bijarniya

Get full text

Study on Key Influencing Factors of Carbon Emissions from Farmland Resource Utilization in Northeast China Under the Background of Energy Conservation and Emission Reduction by Mulin Sun, Yuhao Fu, Mingyao Sun, Run Huang, Yun Teng

“…A gray prediction model is constructed to predict the carbon emissions from the utilization of farmland resources in the next 10 years, and the logarithmic mean Divisia index model is used to analyze the effects of the various influencing factors on the carbon emissions from farmland utilization. …”
Get full text

Breaks in the Arctic ice cover: from observations to predictions by A. A. Ershova, L. N. Dyment, T. A. Alekseeva

Get full text

Deep Learning for Predicting Biomolecular Binding Sites of Proteins by Minjie Mou, Zhichao Zhang, Ziqi Pan, Feng Zhu

“…Emerging trends in hybrid models that combine multimodal data, such as integrating sequence and structural information, along with innovations in geometric deep learning, present promising directions for improving prediction accuracy. …”
Get full text

Application of Machine Learning Methods for Gravity Anomaly Prediction by Katima Zhanakulova, Bakhberde Adebiyet, Elmira Orynbassarova, Ainur Yerzhankyzy, Khaini-Kamal Kassymkanova, Roza Abdykalykova, Maksat Zakariya

“…Results indicated that the Exponential GPR model demonstrated the highest predictive accuracy, outperforming other ML methods, with 72.9% of predictions having errors below 1 mGal. …”
Get full text

Unsupervised Action Anticipation Through Action Cluster Prediction by Jiuxu Chen, Nupur Thakur, Sachin Chhabra, Baoxin Li

“…These pseudo-labels are then input into a temporal sequence modeling module that learns to predict future actions in terms of pseudo-labels. …”
Get full text

BiDGCNLLM: A Graph–Language Model for Drone State Forecasting and Separation in Urban Air Mobility Using Digital Twin-Augmented Remote ID Data by Zhang Wen, Junjie Zhao, An Zhang, Wenhao Bi, Boyu Kuang, Yu Su, Ruixin Wang

“…Using Remote ID data, we propose BiDGCNLLM, a hybrid prediction framework that integrates a Bidirectional Graph Convolutional Network (BiGCN) with Dynamic Edge Weighting and a reprogrammed Large Language Model (LLM, Qwen2.5–0.5B) to capture spatial dependencies and temporal patterns in drone speed trajectories. …”
Get full text

Spatial Ecology of a Resident Avian Predator During the Non-Breeding Period in Managed Habitats of Southeastern Europe by Draženko Z. Rajković, Daliborka Stanković, Jelena Šeat, Dejan S. Stevanović, Miona V. Andrejević Stošović, Stefan Skorić

“…However, scores of model performance metrics showed moderate predictive accuracy, implying that other unmeasured variables may dictate species presence. …”
Get full text

Machine-learning-based spatial analysis of the spring states in the southernmost Eurasian permafrost, Hangai Mountains, central Mongolia by Mamoru Ishikawa, Azumi Okazaki, Avirmed Dashtseren, Khurelbaatar Temuujin, Tetsuya Hiyama

“…An ensemble of the three models predicted that 22.5% of springs in the Hangai Mountains have already been depleted. …”
Get full text

Soil Quality Assessment in the Mashhad Plain, Northeast Iran (A Minimum Data Set and Spatial Analysis Approach) by Amin Mousavi, Alireza Karimi, Seyed Kazem Alavipanah, Ashraf Malekian, Tayebeh Safari

“…IQIwL_MDS yielded the highest SQI, while IQIwNL_MDS produced the lowest. The nonlinear model (R² = 0.89) showed a stronger correlation between MDS and TDS than the linear model (R² = 0.76), underscoring the nonlinear model’s predictive accuracy. …”
Get full text

Spatial heterogeneity patterns along the human footprint gradient and their ecological implications: A case study in South Korea by Kyoung-Ho Kim, Minkyu Park, Taeho Park, Donghae Baek, Gyobeom Kim, Namjoo Heo, Dong Jun Chun

“…While forest fragmentation increased with HF intensity, mammal species richness showed local increases in transitional zones despite declining protected area coverage, supporting the heterogeneity-diversity relationship. Machine learning models incorporating multiple heterogeneity metrics significantly improved predictive performance compared to HF intensity alone, with Random Forest achieving the highest accuracy. …”
Get full text

Simulations of divertor designs that spatially separate power and particle exhaust using mid-leg divertor particle pumping by J.H. Yu, R.S. Wilcox, R. Maurizio, A. Holm, S.L. Allen, W. Choi, M.E. Fenstermacher, M. Groth, A.W. Leonard, A.G. McLean, F. Scotti, M.W. Shafer

“…Predictive design modeling of a Dissipation-Focused Divertor for future operation in DIII-D reveals that increasing the poloidal distance of the pump duct entrance from the target surface along the low-field side divertor baffle increases neutral compression and modifies the spatial distribution of power dissipation. …”
Get full text

Fully convolutional video prediction network for complex scenarios by Rui Han, Shuaiwei Liang, Fan Yang, Yong Yang, Chen Li

“…Traditional predictive models, often used in simpler settings, face issues like high latency and computational demands, especially in complex real-world environments. …”
Get full text

Research on the influencing factors of PM2.5 in China at different spatial scales based on machine learning algorithm by Meiru Chen, Jun Liu, Biwu Chu, Di Zhao, Ruiyu Li, Tianzeng Chen, Qingxin Ma, Yonghong Wang, Peng Zhang, Hao Li, Hong He

“…Further, after increasing the spatial resolution and applying a grid-level model, R2 further improves to 0.96 ∼ 0.99. …”
Get full text

Spatial patterns and key driving factors of wheat harvest index under irrigation and rainfed conditions in arid regions by Yongyu Chen, Yongyu Chen, Hengbati Wutanbieke, Dongdong Zhong, Dongdong Zhong, Jian Chen, Jian Chen, Zhen Huo, Zhen Huo, Hegan Dong, Hegan Dong

“…By integrating multidimensional factors such as geographical and climatic conditions, agronomic management practices, and soil nutrient status, methods including correlation analysis, random forest models, structural equation modeling, and linear regression analysis were employed to systematically investigate the spatial distribution characteristics and driving mechanisms of wheat HI under different irrigation regimes in arid regions.ResultsThe results revealed that: (1) Wheat HI in arid regions exhibited significant spatial heterogeneity (0.43–0.67), with an overall distribution pattern of "central high, peripheral low" and "northern high, southern low." (2) The importance rankings of influencing factors differed between irrigation regimes. …”
Get full text

Prediction of drought-flood prone zones in inland mountainous regions under climate change with assessment and enhancement strategies for disaster resilience in high-standard farml... by Yongheng Shen, Qingxia Guo, Zhenghao Liu, Yanli Shen, Yikun Jia, Yuehan Wei

“…The overall findings indicate that: (1) Precipitation (Pr) and the Standardized Precipitation-Evapotranspiration Index (SPEI) have increased in recent years, with Pr expected to continue rising until 2035. (2) The integration of historical data with the predictions from the PSO-LSTM-GAT model reveals significant spatial overlap between historical and future disaster-prone areas and intensive cropland, especially in the central region. (3) Compared to single models, the PSO-LSTM-GAT model demonstrates significantly improved performance and precision in predicting drought- and flood-prone areas. (4) Through the FDRA integrated adjustment mechanism, 6.6668 km² of unsuitable land was identified, and 6.7349 km² of high-quality land was selected as the proposed site for the next round of HSF projects. …”
Get full text

An approach for predicting landslide susceptibility and evaluating predisposing factors by Wanxin Guo, Jian Ye, Chengbing Liu, Yijie Lv, Qiuyu Zeng, Xin Huang

“…Effectively leveraging landslide spatial location information is crucial for improving the accuracy of deep learning in predicting landslide susceptibility and exploring the impacts of predisposing factors. …”
Get full text

Spatiotemporal Land Use and Land Cover Changes and Their Impact on Landscape Patterns in the Colombian Coffee Cultural Landscape (2014–2034) by Anyela Piedad Rojas Celis, Jie Shen, Jose David Martinez Otalora

“…Landscape metric analysis revealed increased fragmentation and spatial heterogeneity. The integration of multisensor remote sensing, hybrid predictive models, and landscape metrics within the CCLC provides a quantitative methodological framework to evaluate the transformation of cultural landscapes under anthropogenic pressures.…”
Get full text