Abstract
Researchers detail new data in artific ial intelligence. According to news originating from Iowa State University by Ne wsRx correspondents, research stated, "Large earthquakes (EQs) occur at surprisi ng loci and timing, and their descriptions remain a long-standing enigma." Financial supporters for this research include National Science Foundation. Our news correspondents obtained a quote from the research from Iowa State Unive rsity: "Finding answers by traditional approaches or recently emerging machine l earning (ML)-driven approaches is formidably difficult due to data scarcity, int erwoven multiple physics, and absent first principles. This paper develops a nov el artificial intelligence (AI) framework that can transform raw observational E Q data into ML-friendly new features via basic physics and mathematics and that can self-evolve in a direction to better reproduce short-term large EQs. An adva nced reinforcement learning (RL) architecture is placed at the highest level to achieve self-evolution. It incorporates transparent ML models to reproduce magni tude and spatial location of large EQs ( $$M_ w \ge $$ 6.5) weeks before of the failure. Verifications with 40-year EQs in the western U.S. and compariso ns against a popular EQ forecasting method are promising. This work will add a n ew dimension of AI technologies to large EQ research."
NETL
NSTL