Scalable earthquake magnitude prediction using spatio-temporal data and model versioning

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Июнь 2, 2025

Earthquake magnitude prediction is critical for natural calamity prevention and mitigation, significantly reducing casualties economic losses through timely warnings. This study introduces a novel approach by using spatio-temporal data from seismic records obtained the Indian government seismology department weather sourced via VisualCrossing to predict earthquake magnitudes. By integrating environmental variables, explores their interrelationships enhance predictive capabilities. The proposed framework incorporates machine learning operations (MLOps)-driven pipeline MLflow automated ingestion, preprocessing, model versioning, tracking, deployment. integration ensures adaptability evolving datasets facilitates dynamic selection optimal performance. Multiple algorithms, including Gradient Boosting, Light Boosting Machine (LightGBM), XGBoost, Random Forest, are evaluated on dataset sizes of 20%, 35%, 65%, 100%, with performance metrics such as Mean Absolute Error, Squared Root R2. results reveal that performs optimally smaller datasets, while LightGBM demonstrates superior accuracy larger showcasing pipeline's flexibility scalability. research presents scalable, robust, resilient solution combining diverse sources operational MLOps framework. outcomes illustrate potential advanced techniques lifecycle management practices applicability in real-world scenarios.

Язык: Английский

---

AI-infused characteristics prediction and multi-objective design of ultra-high performance concrete (UHPC): From pore structures to macro-performance

Journal of Building Engineering, Год журнала: 2024, Номер unknown, С. 111170 - 111170

Опубликована: Окт. 1, 2024

Язык: Английский

---

Use of publicly available data to create a dataset for data-driven urban commercial building energy intensity classification: Model accuracy, interpretation, and implications of an open data framework in Hong Kong

Sustainable Cities and Society, Год журнала: 2023, Номер 100, С. 105063 - 105063

Опубликована: Ноя. 14, 2023

Язык: Английский

---

Converging Human Intelligence with AI Systems to Advance Flood Evacuation Decision Making

Опубликована: Фев. 15, 2024

Abstract. The powers that artificial intelligence (AI) has developed are impressive, with recent success in leveraging human expertise at various stages of model development. AI can attain its full potential only if, as part intelligence, it also actively teams humans to co-create solutions. Combining simulation through data convergence improve decision-making processes and provide a capacity akin "teaming intelligence." This research, for the first time, introduces concepts Human-AI Convergence (HAC) capabilities flood evacuation decision-making. objective this study was develop unique, computationally effective surrogate HAC system integrates distinctive features transportation geospatial data, river hydraulic model, from X (previously Twitter) visualize inundation areas suggest re-routing. is smartly designed forecast stage levels using across US Geological Survey gauging stations combine results Manning's equation integrated into web-based Google Earth visualization architecture. technology been tested Lowcountry South Carolina, where previous flooding disasters caused considerable damage networks increased traffic on routes. state-of-the-art system— product— stands advance frontier human-AI collaborative research context real-time emergency management response.

Язык: Английский

---

Enhancing flood monitoring and prevention using machine learning and IoT integration

Natural Hazards, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 4, 2024

Язык: Английский

---