What Helps to Detect What? Explainable AI and Multisensor Fusion for Semantic Segmentation of Simultaneous Crop and Land Cover Land Use Delineation by Saman Ebrahimi, Saurav Kumar

“…Interclass-Grad-CAM provides insights into interactions between land cover classes, revealing complex spatial arrangements, while Spectral-Grad-CAM quantifies the contributions of individual spectral bands to model predictions, optimizing spectral data use. …”
Get full text

Ultradense Dark Matter Halos with Poisson Noise from Stellar-mass Primordial Black Holes by Saeed Fakhry, Javad T. Firouzjaee

“…Conversely, at higher values of n , the predicted UDMH distributions align more closely with single-component models dominated by stellar-mass PBHs. …”
Get full text

Range dynamics of Anopheles mosquitoes in Africa suggest a significant increase in the malaria transmission risk by Peixiao Nie, Chunyan He, Jianmeng Feng

“…Through a unified scheme, we developed 21 species distribution models to predict the range dynamics of 21 major An. species in Africa under future scenarios and also examined their overall range dynamic patterns mainly through suitability overlap index and range overlap index. …”
Get full text

Advanced Deep Learning Algorithms for Energy Optimization of Smart Cities by Izabela Rojek, Dariusz Mikołajewski, Krzysztof Galas, Adrianna Piszcz

“…Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) facilitate detailed analysis of spatial and temporal data to better predict energy usage. …”
Get full text

Airborne sound insulation performance of lightweight double leaf walls with different stud types by Hequn Min, Bo Wang, Ting Qu

“…To support performance-based design workflows, this paper presents an analytical model based on sound transmission path decoupling, enabling architects to quickly predict the STL of commonly used lightweight double leaf wall types, including wooden, steel, and acoustical stud constructions. …”
Get full text

Advancing resilient power systems through hierarchical restoration with renewable resources by Mohannad Alhazmi, Peijin Li

“…At the upper level, Graph Neural Networks (GNNs) are used to predict fault locations and optimize network topology by analyzing the spatial and topological features of the grid. …”
Get full text

Numerical Solution of Binary Liquid-Phase Adsorption onto Porocel Clay Using Linear, Freundlich and Langmuir Isotherms by Olaosebikan A. Olafadehan, Alfred A. Susu

“…A computational scheme for the solution of the model equations is presented. The scheme is based on orthogonal collocation for spatial discretization of the resulting set of coupled hyperbolic and parabolic partial differential equations for the macro-and micro-system, respectively. …”
Get full text

Improving imperfect data from health management information systems in Africa using space-time geostatistics. by Peter W Gething, Abdisalan M Noor, Priscilla W Gikandi, Esther A A Ogara, Simon I Hay, Mark S Nixon, Robert W Snow, Peter M Atkinson

“…<h4>Methods and findings</h4>This study has taken the example of presumed malaria in outpatients within the largely incomplete Kenyan HMIS database and has defined a geostatistical modelling framework that can predict values for all data that are missing through space and time. …”
Get full text

PKA regulation of neuronal function requires the dissociation of catalytic subunits from regulatory subunits by Weihong Xiong, Maozhen Qin, Haining Zhong

“…However, the spatiotemporal dynamics of endogenous PKA upon activation remain debated. The classical model predicts that PKA catalytic subunits dissociate from regulatory subunits in the presence of cAMP, whereas a second model proposes that catalytic subunits remain associated with regulatory subunits following physiological activation. …”
Get full text

GAN-based solar radiation forecast optimization for satellite communication networks by Chao Chen, Xin Liu, Shizhong Zhao, Muhammad Bilal

“…In such scenarios, predictions often exhibit spatial texture degradation and distortions in radiation intensity. …”
Get full text

The potential spatiotemporal distribution patterns of Avena nuda and Avena sativa from global perspective provide new insights for the cultivation of commonly cultivated oats by Huanhuan Lu, Yuying Zheng, Ting Zhao, Liuban Tang, Fan Zhang, Wengang Xie

“…This study comprehensively collected the geographic distribution and environmental data of A. nuda and A. sativa from global regions, the ensembled niche and Marxan model were used to predict the potential spatiotemporal distribution and planting pattern of commonly cultivated oats, and further explore the environmental factors that affected the spatial distribution and genetic diversity pattern. …”
Get full text

Application of a GA-BP Neural Network in Accurately Characterizing the Diffusion Range of Groundwater Pollutants by Jiayun JI, Xiao XIAO, Pinlu YANG, Yang LIU, Yahong ZHOU

“…To overcome this, two neural network models—GA-BP and standard BP—were applied to predict Mn2+ concentrations at unsampled locations. …”
Get full text

Voronoi tessellation captures very early clustering of single primary cells as induced by interactions in nascent biofilms. by Iris Hödl, Josef Hödl, Anders Wörman, Gabriel Singer, Katharina Besemer, Tom J Battin

“…Model predictions match empirical observations reasonably well, highlighting the role of biotic interactions even already during very early biofilm formation despite few and distant cells. …”
Get full text

Translational control by the DEAD Box RNA helicase belle regulates ecdysone-triggered transcriptional cascades. by Robert J Ihry, Anne L Sapiro, Arash Bashirullah

“…The accumulation of E74A mRNA in belle mutant salivary glands is a result of auto-regulation, fulfilling a prediction made by Ashburner nearly 40 years ago. In this model, Ashburner postulates that, in addition to regulating secondary response genes, protein products of primary response genes like E74A also inhibit their own ecdysone-induced transcription. …”
Get full text

Re-identification assistance and multi-stage association for pedestrian multi-object tracking by Ye Li, Li Zhan, Lei Wu, Hongkun Liu, Jianli Min, Xinzhong Wang

“…Currently, most methods mainly use the Kalman filter to model the motion and predict the position of the pedestrian in the next frame. …”
Get full text

The Value of Learning about Natural History in Biodiversity Markets. by Douglas J Bruggeman

“…I use an individually-based, spatially-explicit population model for the Red-cockaded Woodpecker (Picoides borealis) to predict spatial- and temporal- influences of landscape change on species occurrence and genetic diversity. …”
Get full text

Vortex Avalanches and Collective Motion in Neutron Stars by I-Kang Liu, Andrew W. Baggaley, Carlo F. Barenghi, Toby S. Wood

“…We simulate the dynamics of about 600 quantum vortices in a spinning-down cylindrical container using a Gross–Pitaevskii model. For the first time, we find convincing spatial-temporal evidence of avalanching behavior resulting from vortex depinning and collective motion. …”
Get full text

AI-driven fusion of multimodal data for Alzheimer’s disease biomarker assessment by Varuna H. Jasodanand, Sahana S. Kowshik, Shreyas Puducheri, Michael F. Romano, Lingyi Xu, Rhoda Au, Vijaya B. Kolachalama

“…Our approach achieved an AUROC of 0.79 and 0.84 in classifying Aβ and τ status, respectively. Predicted PET status was consistent with various biomarker profiles and postmortem pathology, and model-identified regional brain volumes aligned with known spatial patterns of tau deposition. …”
Get full text

Gene circuit analysis of the terminal gap gene huckebein. by Maksat Ashyraliyev, Ken Siggens, Hilde Janssens, Joke Blom, Michael Akam, Johannes Jaeger

“…This is achieved by fitting the model to gap gene expression patterns, in order to obtain estimates for regulatory parameters which predict a specific network topology. …”
Get full text

Identifying Priority Areas for the Indian Leopard (Panthera pardus fusca) Within a Shared Landscape by Aparna Kolekar, Kimberley Hockings, Kristian Metcalfe, Sanjay Gubbi

“…Environment variables were chosen to reflect land use, climatic, topographic, and human disturbances that could affect habitat selection at a resolution of 0.1 km2. The mean ensemble model was projected to the state of Karnataka. Habitat selection predicted by the ensemble model was driven by proximity to forest cover and rocky outcrops, higher precipitation, and negatively by distance to cropland and roads. …”
Get full text