High-resolution soil temperature and soil moisture patterns in space, depth and time: An interpretable machine learning modelling approach by Maiken Baumberger, Bettina Haas, Sindhu Sivakumar, Marvin Ludwig, Nele Meyer, Hanna Meyer

“…We trained random forest models that were able to predict soil temperature with a mean absolute error of 0.93 °C and soil moisture with a mean absolute error of 4.64 % volumetric water content. …”
Get full text

Characteristics of Flux Footprint over Typical Underlying Surface of Qinghai-Xizang Plateau by Zixin WANG, Lei ZHONG, Yaoming MA, Yunfei FU

“…The heterogeneity of the underlying surface affects the accuracy and representativeness of the land-atmosphere flux observation.The study on the flux footprint distribution of complex underlying surface over Qinghai-Xizang Plateau （QXP） is of great significance to the observation and simulation of land-atmosphere interaction and its influence on weather and climate.Flux footprint analysis plays a pivotal role in investigating the spatial representativeness of flux observation information.The Flux Footprint Prediction （FFP） model represents a proficient methodology for computing the flux footprint.Based on the observation data from multiple research stations， including the Qomolangma Atmospheric and Environmental Observation and Research Station， the Ngari Desert Observation and Research Station， the Nam Co Monitoring and Research Station for Multisphere Interactions， the Muztagh Ata Westerly Observation and Research Station， the Southeast Tibet Observation and Research Station for the Alpine Environment in 2013， the FFP model was utilized to investigate the sensitivity of model parameters concerning flux footprint distribution.Additionally， the spatiotemporal characteristics and specific influencing factors of flux footprint distribution at different stations were discussed， thereby providing valuable insights for the erection of future observing stations.The results reveal that the primary determinants of flux footprint are measurement height， wind speed and wind direction.Characterized by an underlying surface of evergreen coniferous forest， flux footprint at Linzhi station exhibits greater sensitivity to measurement height and planetary boundary layer depth compared to the other stations.In the QXP， the spatial extent of the flux footprint derived from the ultrasonic anemometer measurements ranges from approximately 250 m to 500 m.Among the five stations， Qomo station exhibited the lowest frequency of stable stratification times during daytime， representing 15.69% of the daytime data points， whereas Ali station had the lowest occurrence of unstable stratification times during nighttime， comprising for 13.32% of the nighttime data points.At these five stations on the TP， the nocturnal flux footprints demonstrate greater width and extent compared to their daytime counterparts.In summer， due to the influence of monsoon， the axis of flux footprint tends to be more consistent.Lake-land breeze at Nam Co station is the main factor affecting flux footprint， whereas glacier wind at Qomo station is the dominant factor.Linzhi station possesses the smallest footprint due to the smallest mean wind speed， thus demonstrating the highest level of representativeness among these five stations.Lowering the height of observation instruments at Qomo and Nam Co stations could potentially enhance the representativeness of in situ measurements.…”
Get full text

Investigation on Dimensionality Reduction methods for Tree-Crown Segmentation in Hyperspectral imagery using Segment Anything Model by R. Ravindran, Y. Treitz, D. Iwaszczuk

Get full text

Ecological and temporal drivers of human-gaur conflict in Tamil Nadu, India by Thekke Thumbath Shameer, Priyambada Routray, A. Udhayan, Rangaswamy Kanchana, Senbagapriya Sekar, Sivaranjani Shankar, Dhayanithi Vasanthakumari, Selvakumar Subramaniyam

“…This study offers critical insights into the spatial ecology of HGC and demonstrates the utility of predictive modeling for identifying high-risk areas, informing proactive mitigation strategies for conservation managers.…”
Get full text

Impact of Underground Space Height and BMI on Children’s Fatigue During Ascending Evacuation: An Experimental Study and Intelligent Assistive Implications by Ming Liu, Hu Zhang, Xin Guo, Yongbo Feng, Xiaochen Zhao, Changzheng Xuan, Xiaohu Jia

Get full text

Predictive Mathematical Emergency Information System (EIS) Using GIS, GPS and Digital Photogrammetry (DP) by Abdullah M. Al-Garni

“…Predictive Traffic Response Emergency Information System (PTREIS) was developed based on proven mathematical models. …”
Get full text

Immunophenotype-guided interpretable radiomics model for predicting neoadjuvant anti-PD-1 response in stage III–IV d-MMR/MSI-H colorectal cancer by Xuan Zhang, Zhenhui Li, Yiwen Zhang, Yanli Li, Xi Zhong, Wenjing Jiang, Xiaobo Chen, Zaiyi Liu, Liebin Huang, Caixia Zhang, Lizhu Liu, Ruimin You, Xiaoping Yi

“…This study aimed to develop an interpretable radiomics model guided by immunophenotypes to predict response to preoperative immunotherapy in CRC, with the goal of enabling more precise and personalized treatment strategies.Methods First, we retrospectively collected 108 patients with CRC from the center who underwent preoperative CT and RNA sequencing. …”
Get full text

Machine learning approach for water quality predictions based on multispectral satellite imageries by Vicky Anand, Bakimchandra Oinam, Silke Wieprecht

“…The main objective of this study to retrieve and map the water quality parameters from Sentinel-2 and ResourceSat-2 [Linear Imaging Self-Scanning Sensor (LISS)–IV] multi-spectral satellite data, using Support Vector Machines (SVM), Random Forests (RF), and Multi-Linear regression (MLR) models. This study represents the first attempt to demonstrate the applicability and performance of high-spatial resolution ResourceSat-2 remote sensing satellite's LISS-4 sensor, which operates in three spectral bands in the Visible and Near Infrared Region (VNIR), to predict water quality. …”
Get full text

MaxEnt Modeling of Future Habitat Shifts of <i>Itea yunnanensis</i> in China Under Climate Change Scenarios by Jinxin Zhang, Xiaoju Li, Suhang Li, Qiong Yang, Yuan Li, Yangzhou Xiang, Bin Yao

“…The optimized model (RM = 3.0, FC = QHPT) significantly reduced overfitting risk (ΔAICc = 0) and achieved high prediction accuracy (AUC = 0.968). …”
Get full text

Temporal–Spatial Partial Differential Equation Modeling of Land Cover Dynamics via Satellite Image Time Series and Sparse Regression by Ming Kang, Zheng Zhang, Zhitao Zhao, Keli Shi, Junfang Zhao, Ping Tang

“…Land cover dynamics play a critical role in understanding environmental changes, but accurately modeling these dynamics remains a challenge due to the complex interactions between temporal and spatial factors. …”
Get full text

Pedestrian Trajectory Prediction Based on Transformer and Multi-relation Graph Convolutional Networks by LIU Guihong, ZHOU Zongrun, MENG Xiangfu

“…To address this, a pedestrian trajectory prediction model combining Transformer and multi-relation graph convolutional network (GCN) is proposed. …”
Get full text

Spatial Analysis of Rural Architecture Structure in Passive Defense by VIKOR Modeling; Case study: Yaseh Chai Village by Kourosh Momeni, Mostafa Mohebian, Elias Mavedat

“…Based on the results obtained from the VIKOR modeling, the spatial analysis of the architectural and urban structure of Yaseh Chai village is based on non-operational defense criteria, such as "hiding the village's appearance with local materials" and "predicting the stair-shaped form of houses to reduce damage caused by the destruction of houses" as well as "suitable village location based on suitable and fertile soil for agriculture, horticulture and farming to provide for the economic needs of the inhabitants." …”
Get full text

Short term prediction of photovoltaic power with time embedding temporal convolutional networks by Jingxin Wang, Guohan Li, Jin Gu, Zhengyi Xu, Xinrong Chen, Jianming Wei

“…Abstract The incorporation of both spatial and temporal characteristics is vital for improving the predictive accuracy of photovoltaic (PV) power generation forecasting. …”
Get full text

Predicting traffic flow with federated learning and graph neural with asynchronous computations network by Muhammad Yaqub, Shahzad Ahmad, Malik Abdul Manan, Muhammad Salman Pathan, Lan He

“…The experimental results obtained from conducting tests on two distinct traffic datasets demonstrate that the utilization of FLAGCN leads to the optimization of both training and inference durations while maintaining a high level of prediction accuracy. FLAGCN outperforms existing models with significant improvements by achieving up to approximately 6.85 % reduction in RMSE, 20.45 % reduction in MAPE, compared to the best-performing existing models.…”
Get full text

Scenario-based validation and prediction of land use changes in Birjand watershed in 1404 by Elham Yusefiroobiat, Fatemeh Jahanishakib

“…Then, using the CA-Markov Model, land use changes in 2014 were predicted and modeled. …”
Get full text

Dynamic Graph-Based Clustering for Non-Stationary Spatio-Temporal Event Prediction by Vasavi M., Murugan A., Sharma K. Venkatesh

“…Representation of Graph gives us the crime data analysis with location wise and helps us to predict the next occurrence instance. An alternate way of modeling the objects in data sets is to represent those using graphs. …”
Get full text

GMTP: Enhanced Travel Time Prediction with Graph Attention Network and BERT Integration by Ting Liu, Yuan Liu

“…(1) Background: Existing Vehicle travel time prediction applications face challenges in modeling complex road network and handling irregular spatiotemporal traffic state propagation. (2) Methods: To address these issues, we propose a Graph Attention-based Multi-Spatiotemporal Features for Travel Time Prediction (GMTP) model, which integrates an enhanced graph attention network (GATv2) and Bidirectional Encoder Representations from Transformers (BERT) to analyze dynamic correlations across spatial and temporal dimensions. …”
Get full text

3D long time spatiotemporal convolution for complex transfer sequence prediction by Qiu Yunan, Cui Yingjie, Tang Haibo, Chen Zhongfeng, Lu Zhenyu, Xue Feng

“…However, two challenges still exist in the existing methods: 1) Most of the existing spatio-temporal prediction tasks focus on extracting temporal information using recurrent neural networks and using convolution networks to extract spatial information, but ignore the fact that the forgetting of historical information still exists as the input sequence length increases. 2) Spatio-temporal sequence data have complex non-smoothness in both temporal and spatial, such transient changes are difficult to be captured by existing models, while such changes are often particularly important for the detail reconstruction in the image prediction task. …”
Get full text

Overview of Applications and Research Directions of Deep Learning Methods for Wind Power Prediction by LIU Tan, LIU Na, LIU Guiping, LIU Kunjie, LIU Min, ZHUANG Xufei, ZHANG Zhonghao

“…The application of deep learning technology in wind power prediction is reviewed, and on the basis of making a careful division of deep learning technology, it focuses on analyzing the overcome problems and performance by spatial structure-based deep learning models and time-based deep learning models and their related variants, and summarizes the limitations of the proposed modeling methods and the corresponding solutions. …”
Get full text

Forest Loss and Susceptible Area Prediction at Sefwi Wiawso District (SWD), Ghana by William Osei-Wusu, Jonathan Quaye-Ballard, Terah Antwi, Naa Lamkai Quaye-Ballard, Alfred Awotwi

“…The impacts of selected spatial variables on forest losses were examined using retrospective and predictive approaches. …”
Get full text