Small Target Detection Algorithm for UAV Aerial Images Based on Improved YOLOv7-tiny by ZHANG Guanghua, LI Congfa, LI Gangying, LU Weidang

“…In addition, the ConvMixer layer is integrated into the prediction head; the depthwise and pointwise convolutions in ConvMixer capture the spatial and channel relationships in the feature information, improving the processing capability for small targets. …”
Get full text

Data Biases in Geohazard AI: Investigating Landslide Class Distribution Effects on Active Learning and Self-Optimizing by Jing Miao, Zhihao Wang, Tianshu Ma, Zhichao Wang, Guoming Gao

“…These findings indicate that regardless of the landslide proportion, AL enhances the generalizability of landslide detection models in terms of predictive accuracy and spatial consistency. …”
Get full text

Integrating Street View Images, Deep Learning, and sDNA for Evaluating University Campus Outdoor Public Spaces: A Focus on Restorative Benefits and Accessibility by Tingjin Wu, Deqing Lin, Yi Chen, Jinxiu Wu

“…On this basis, restorative benefit evaluation models were established, including the explanatory and predictive models. …”
Get full text

Analysis of Resolving Efficient Dominating Set and Its Application Scheme in Multi-Step Time Series Forecasting of pH and Soil Moisture in Horizontal Farming by Kamal Dliou, Adinda Putri Aziza, Dafik Dafik, Arika Indah Kristiana, Dwi Agustin Retnowardani

“…Spatial Temporal Graph Neural Network (STGNN) technique proves to be useful in solving the problem of soil moisture and pH by understanding and modeling multi-step time series data. …”
Get full text

The Animal Origin of Major Human Infectious Diseases: What Can Past Epidemics Teach Us About Preventing the Next Pandemic? by Guha Dharmarajan, Ruiyun Li, Emmanuel Chanda, Katharine R. Dean, Rodolfo Dirzo, Kjetill S. Jakobsen, Imroze Khan, Herwig Leirs, Zheng-Li Shi, Nathan D. Wolfe, Ruifu Yang, Nils Chr. Stenseth

“…Here, we provide a systematic review, in conjunction with a meta-analysis and spatial risk modeling, to identify the major characteristics of past epidemics of animal origin and predict areas with high future disease emergence risk. …”
Get full text

STRENGTH SIMULATION AND TOPOLOGY OPTIMIZATION DESIGN OF OFF-ROAD VEHICLES’ HUB MOTOR HOUSING by QI Chang, MA Yuanhang, YANG Lining, YANG Shu, WANG Bolong

“…Secondly, based on the spatial position relation between the housing and interconnected structures, a finite element model of the motor housing and suspension system was constructed for dynamic simulation analysis. …”
Get full text

Spatiotemporal masked pre-training for advancing crop mapping on satellite image time series with limited labels by Xiaolei Qin, Haonan Guo, Xin Su, Zhenghui Zhao, Di Wang, Liangpei Zhang

“…However, the existing SSL methods applied to SITS data typically explore masking solely on temporal dimension, which cannot guarantee strong spatial representation and therefore hinders the accurate prediction of complex crop fields. …”
Get full text

Flood Susceptibility Map Data of Jeju Island Using Probabilistic Methods by Saro Lee

“…These data were used to train and validate the FR model. The model’s predictive performance was evaluated using the receiver operating characteristic-area under curve (ROC-AUC), achieving an accuracy 82.33%, indicating high accuracy. …”
Get full text

Comparison of Machine-Learning Algorithms for Near-Surface Air-Temperature Estimation from FY-4A AGRI Data by Ke Zhou, Hailei Liu, Xiaobo Deng, Hao Wang, Shenglan Zhang

“…The performance of each model and the temporal and spatial distribution of the estimated Tair errors were analyzed. …”
Get full text

Integrable deformations of dimensionally reduced gravity by Mattia Cesàro, David Osten

“…The resulting system typically features a coset σ-model coupled to a dilaton and a scale factor of the dimensional reduction. …”
Get full text

Crop Statistic to Annual Map: Tracking spatiotemporal dynamics of crop-specific areas through machine learning and statistics disaggregating by Xiyu Li, Le Yu, Zhenrong Du, Xiaoxuan Liu

“…In our framework, we collected related spatial indicator used in previous studies and trained random forest regression models to predict spatiotemporal dynamics of crop-specific areas based on them. …”
Get full text

Nitrogen Accumulation in Forests. Exposure Monitoring by Mosses by Roland Pesch, Winfried Schröder, Gunther Schmidt

“…Statistical analyses performed at the different spatial scales revealed that the areas showing greater agricultural and livestock spatial densities favor N bioaccumulation in mosses. …”
Get full text

Downscaling of ERA5 reanalysis land surface temperature based on attention mechanism and Google Earth Engine by Shiyu Li, Hong Wan, Qun Yu, Xinyuan Wang

“…In addition, the Bayesian global optimization algorithm is used to select the optimal hyperparameters of the network in order to enhance the predictive performance of the model. Finally, the downscaling accuracy of the network was evaluated through simulated data experiments and real data experiments and compared with the Random Forest (RF) method. …”
Get full text

Evaluation of ground based spectral imaging for real time maize biomass monitoring by Andrea Szabó, Andrea Szabó, Nxumalo Gift Siphiwe, Nxumalo Gift Siphiwe, Erika Buday-Bódi, Erika Buday-Bódi, Blessing Ademola, János Tamás, János Tamás, Attila Nagy, Attila Nagy

“…Conversely, the chlorophyll prediction model showed improved accuracy, achieving an R² of 0.64, an MBE of 0.04 µg/g, and an NRMSE of 15.92%. …”
Get full text

Multi-dimensional water quality indicators forecasting from IoT sensors: A tensor decomposition and multi-head self-attention mechanism. by Li Bo, Lv Junrui, Luo Xuegang

“…Accurate prediction of multi-dimensional water quality indicators is critical for sustainable water resource management, yet existing methods often fail to address the high-dimensional, nonlinear, and spatially correlated nature of data from heterogeneous IoT sensors. …”
Get full text

A three-dimensional reconstruction method of coal mine tunnel fused with LiDAR and IMU by Qinghua MAO, Jianquan CHAI, Yanzhang CHEN, Xusheng XUE, Chuanwei WANG

“…In this method, the residual function of the lidar observation model and the prior state deviation of the IMU prediction model are tightly coupled through iterative kalman filter, and a more accurate posteriori state is obtained through state update, which provides reliable pose estimation for the degraded environment. …”
Get full text

Emerging role of generative AI in renewable energy forecasting and system optimization by Erdiwansyah, Rizalman Mamat, Syafrizal, Mohd Fairusham Ghazali, Firdaus Basrawi, S.M. Rosdi

“…Results indicate that GAN-based models reduce root mean square error (RMSE) by 15–20 % in solar irradiance forecasting and significantly enhance spatial-temporal wind simulations. …”
Get full text

Evaluation of the Monitoring Capabilities of Remote Sensing Satellites for Maritime Moving Targets by Weiming Li, Zhiqiang Du, Li Wang, Tiancheng Zhou

“…Firstly, a target motion prediction model for calculating the transfer probability and a satellite observation information calculation model for obtaining observation strips and time windows are established. …”
Get full text

Panoramic video coding based on spherical distortion with spatio-temporal dependency by Xu YANG, Ce ZHU, Hongwei GUO, Lei LUO

“…The planar coding distortion, which affects objective quality, and spherical distortion, which affects subjective quality, as well as existing independent rate-distortion optimization techniques that fail to consider the temporal propagation of spherical distortion and its impact on coding performance, result in coding performance degradation.To address these issues, a spatio-temporal dependent spherical distortion model was proposed for optimizing panoramic video coding.Firstly, a spatial mapping model was proposed to map spherical distortions to coding distortions, aiming to align subjective and objective quality assessments.Secondly, a temporal propagation model for spherical distortions was introduced to enhance the overall coding performance of all coding units in the propagation chain.Finally, the coding parameters were adjusted by computing the weights for spatial mapping and temporal propagation of spherical distortions.Experimental results demonstrate that, under low-delay encoding configurations, compared to the VTM14.0, a state-of-the-art video coding benchmark, the proposed algorithm achieves an average bitrate savings of 7.4% (up to 22.1%) and reduction in coding time of 9%.…”
Get full text

Plausible Vehicle Trajectory Augmentation With Hybrid Machine Learning by Junyeop Park, Hyeonsoo Jang, Byeongju Kang, Yunhyoung Hwang

“…Validation on the inD dataset confirms that our approach excels in expanding training datasets, yielding substantial improvements in trajectory prediction accuracy for autonomous vehicles when applied to a vanilla long short-term memory model. …”
Get full text