Predicting the impact of climate change on the distribution of rhododendron on the qinghai-xizang plateau using maxent model by Sen-Xin Chai, Li-Ping Ma, Zhong-Wu Ma, Yu-Tian Lei, Ya-Qiong Ye, Bo Wang, Yuan-Ming Xiao, Ying Yang, Guo-Ying Zhou

“…To investigate the possible spatial distribution of Rhododendron on the Qinghai-Xizang Plateau in light of future global warming scenarios, we employed the Maximum entropy model (MaxEnt model) to map its suitable habitat using geographic distribution data and environmental factors projected for 2050s and 2070s, considering three representative concentration pathway (RCP) scenarios, while identifying the key factors influencing their distribution. …”
Get full text

Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model by Guanfeng Chen, Wenxi Liu, Yingmin Lin, Jie Zhang, Risheng Huang, Deqiu Ye, Jing Huang, Jieyun Chen

“…Results: The ViT model demonstrated superior predictive performance, achieving an AUC of 0.918 on the test set, significantly outperforming all traditional radiomics-based models. …”
Get full text

Prediction of litchi flower induction in South China region based on the CMIP6 climate model by HOU Wei, ZHANG Liuhong, ZHANG Lei, LUAN Lan, ZHANG Mingjie, WANG Xiuzhen, ZHANG Hui

“…Additionally, we selected the average ensemble of four climate models (CanESM5, FGOALS-g3, GFDL-CM4, and IPSL-CM6A-LR) from CMIP6 to assess the spatial and temporal evolution characteristics of the commercial cultivation limits and flower formation induction of litchi under two climate scenarios, comparing the base period with future projections in the South China region. …”
Get full text

Short-term rainfall prediction based on radar echo using an efficient spatio-temporal recurrent unit by Dali Wu, Shunli Zhang, Guohong Zhao, Yongchao Feng, Yuan Ma, Yue Zhang

“…In this paper, we propose an Efficient Spatio-Temporal Recurrent Unit (ESTRU) for short-term precipitation prediction based on radar echoes. The ability of the model to process spatio-temporal information is enhanced by fusing two ConvGRU units while controlling the complexity. …”
Get full text

Predicting determinants of unimproved water supply in Ethiopia using machine learning analysis of EDHS-2019 data by Jember Azanaw, Mihret Melese, Eshetu Abera Worede

“…This study aimed to provide more accurate predictions and data-driven insights that can inform policy-making, resource allocation, and interventions to address Ethiopia’s water crisis. …”
Get full text

MSLKSTNet: Multi-Scale Large Kernel Spatiotemporal Prediction Neural Network for Air Temperature Prediction by Feng Gao, Jiaen Fei, Yuankang Ye, Chang Liu

“…However, statistical analysis reveals that temperature evolution varies across temporal and spatial scales due to factors like terrain, leading to a lack of existing temperature prediction models that can simultaneously learn both large-scale global features and small to medium-scale local features over time. …”
Get full text

Analysis of Drought Evolution Characteristics in Haihe River Basin Based on Sub-Period Prediction Model by HAN Dongmei, JIANG Shanshan

“…In order to reduce the prediction uncertainty of future extreme climate events,a sub-period prediction model was constructed based on the daily observed precipitation data of 0.5°×0.5° provided by the China Meteorological Data Service Center and the simulated data of five global climate models (GCMs) from CMIP5.Meanwhile,the spatio-temporal evolution of drought in the Haihe River Basin (HRB) during 2020—2050 was predicted.Results show that both single GCM and multi-model ensemble average can better reproduce changes in annual average precipitation in HRB,but a large error in extreme precipitation simulation exists.The sub-period prediction model was constructed by the regression relationship at the monthly scale between the five GCMs and actually observed precipitation,and the test results show that the model has significantly improved the simulation ability of extreme precipitation in HRB.In the future,HRB tends to be humid,with moderate drought mainly appearing.Spatially,the frequency and degree of drought increase from west to east.This study aims to provide a reference for improving the ability of GCMs in simulating extreme climate events and offer ideas for decision-making for future droughts in HRB.…”
Get full text

Predicting potential biomass production by geospatial modelling: The case study of citrus in a Mediterranean area by G.A. Catalano, P.R. D'Urso, C. Arcidiacono

“…The methodology combines Geographic Information System (GIS) tools, for data interpolation and map overlays, with Software for Assisted Habitat Modelling (SAHM) for local level simulations.The results of the different models showed accurate and spatially coherent predictions, with AUC values ranging from 0.85 to 0.90, and highest potentialities in the northern and eastern regions of the study area. …”
Get full text

Selecting Appropriate Model Complexity: An Example of Tracer Inversion for Thermal Prediction in Enhanced Geothermal Systems by Hui Wu, Zhijun Jin, Su Jiang, Hewei Tang, Joseph P. Morris, Jinjiang Zhang, Bo Zhang

“…Abstract A major challenge in the inversion of subsurface parameters is the ill‐posedness issue caused by the inherent subsurface complexities and the generally spatially sparse data. Appropriate simplifications of inversion models are thus necessary to make the inversion process tractable and meanwhile preserve the predictive ability of the inversion results. …”
Get full text

Mechanical prediction method of strata movement and surface subsidence in backfill-strip mining by Xiaojun Zhu, Feng Zha, Guangli Guo, Qingliang Chang, Hui Liu, Xiaoyu Yang

Get full text

Evaluation of Statistical Models of NDVI and Agronomic Variables in a Protected Agriculture System by Edgar Vladimir Gutiérrez-Castorena, Joseph Alejandro Silva-Núñez, Francia Deyanira Gaytán-Martínez, Vicente Vidal Encinia-Uribe, Gustavo Andrés Ramírez-Gómez, Emilio Olivares-Sáenz

“…This has created a database to generate predictive models of development and yield as a function of nutrient status. …”
Get full text

A framework for continual learning in real-time traffic forecasting utilizing spatial–temporal graph convolutional recurrent networks by Mariam Labib Francies, Abeer Twakol Khalil, Hanan M. Amer, Mohamed Maher Ata

“…To address these challenges, this research presents an innovative framework known as the Continual Learning-based Spatial–Temporal Graph Convolutional Recurrent Neural Network (STGNN-CL) for persistent and accurate long-term traffic flow prediction. …”
Get full text

Radiogenomics of intrahepatic cholangiocarcinoma predicts immunochemotherapy response and identifies therapeutic target by Gu-Wei Ji, Zheng-Gang Xu, Shuo-Chen Liu, Shu-Ya Cao, Chen-Yu Jiao, Ming Lu, Biao Zhang, Yue Yang, Qing Xu, Xiao-Feng Wu, Ke Wang, Yong-Xiang Xia, Xiang-Cheng Li, Xue-Hao Wang

“…We aimed to unveil a novel radiotranscriptomic signature that can facilitate treatment response prediction by multi-omics integration and multiscale modelling. …”
Get full text

Data quality and uncertainty issues in flood prediction: a systematic review by Jinhui Yu, Yichen Li, Xiao Huang, Xinyue Ye

“…These datasets often suffer from issues such as incompleteness, inconsistency, and accuracy deficits, further complicated by uncertainties arising from complex spatial features and environmental changes. The literature proposes a range of solutions, including the development of innovative methodologies, model construction, and comparative analysis, to address these challenges. …”
Get full text

On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction by Yanwen Wang, Mahdi Khodadadzadeh, Raúl Zurita-Milla

“…Recent geospatial machine learning studies have shown that the results of model evaluation via cross-validation (CV) are strongly affected by the dissimilarity between the sample data and the prediction locations. …”
Get full text

Suitability prediction of potential arable land in southeast coastal area of China by Yan Zheng, Xiaohuang Liu, Jianwei Shi, Ping Zhu, Run Liu, Liyuan Xing, Hongyu Li, Chao Wang

“…To ensure food security in the southeast coastal region, it is necessary to focus on the cultivated land degradation caused by climate change. This study predicted the potential suitable areas for cultivated land in the southeast coastal region using 32 environmental variables by the R-optimized MaxEnt model. …”
Get full text

STFGCN: Spatio-Temporal Fusion Graph Convolutional Networks for Subway Traffic Prediction by Xiaoxi Zhang, Zhanwei Tian, Yan Shi, Qingwen Guan, Yan Lu, Yujie Pan

“…Experimental results on the Hangzhou Metro’s inbound and outbound passenger flow datasets demonstrate that the STFGCN model exhibits significant superiority over baseline models and shows excellent performance in metro passenger flow prediction. …”
Get full text

Unveiling Hidden Dynamics in Air Traffic Networks: An Additional-Symmetry-Inspired Framework for Flight Delay Prediction by Chao Yin, Xinke Du, Jianyu Duan, Qiang Tang, Li Shen

“…To address this challenge, this study proposes a novel hybrid predictive framework named DenseNet-LSTM-FBLS. The framework first employs a DenseNet-LSTM module for deep spatio-temporal feature extraction, where DenseNet captures the intricate spatial correlations between airports, and LSTM models the temporal evolution of delays and meteorological conditions. …”
Get full text

User Trajectory Prediction in Cellular Networks Using Multi-Step LSTM Approaches: Case Study and Performance Evaluation by Iskandar, Hajiar Yuliana, Hendrawan, Adriel Timoteo, Fabian Rafinanda Benyamin, Naufal Bhanu Anargyarahman

“…While LSTM excels in capturing sequential temporal patterns, Transformer introduces multi-head attention mechanisms to model complex spatial and temporal dependencies, filling a significant research gap in trajectory prediction. …”
Get full text

Reconstructed hyperspectral imaging for in-situ nutrient prediction in pine needles by Yuanhang Li, Yuanhang Li, Jun Du, Jun Du, Chuangjie Zeng, Chuangjie Zeng, Yongshan Wu, Yongshan Wu, Junxian Chen, Junxian Chen, Teng Long, Teng Long, Yongbing Long, Yongbing Long, Yubin Lan, Yubin Lan, Xiaoliang Che, Tianyi Liu, Jing Zhao, Jing Zhao

“…However, its high cost and complexity hinder practical field applications.MethodsTo overcome these limitations, we propose a deep-learning-based method to reconstruct hyperspectral images from RGB inputs for in situ needle nutrient prediction. The model reconstructs hyperspectral images with a spectral range of 400–1000 nm (3.4 nm resolution) and spatial resolution of 768×768. …”
Get full text