Accurate prediction of ship roll motion is essential for safe and autonomous navigation. This study presents a deep learning framework that estimates both roll motion and epistemic uncertainty using Monte Carlo (MC) Dropout. Two architectures, a Long Short-Term Memory (LSTM) network and a Transformer encoder, were trained on HydroD–Wasim simulations covering various sea states, speeds, and damage conditions, and validated with...

Rice cultivation is a significant source of agricultural methane (CH₄), yet routine quantification still relies heavily on gas chromatography (GC), which limits throughput and field deployment. Here, we evaluated a portable tunable-diode-laser absorption spectroscopy (TDLAS) detector (PMD) as an alternative to GC for measuring CH₄ released from pot-grown rice plants under field conditions. Weekly closed-chamber samples from fi...

The mineralization of organic matter at the sediment plays a crucial role in ecosystem functioning by facilitating the biogeochemical cycling of carbon and nutrients. This process not only supports nutrient availability for primary production but also regulates the long-term storage of carbon within sediments. To understand the biogeochemical processes associated with organic matter mineralization and nutrient regeneration, we...

A fire in a marine energy storage system (ESS) has a high risk because of the special situation of the sea compared with land systems. To mitigate serious damage in the event of a fire in marine ESSs, initial suppression of the fire is extremely important. In this study, a unit module-based fire extinguishing system was constructed for the initial suppression of an ESS fire, and a unit module fire suppression test was conducte...