A prediction device that predicts an objective variable desired to be predicted in a predetermined environment by using two or more prediction models, the prediction device including: a first prediction model configured to output a characteristic representing a relationship with an event related to the objective variable from a change in a factor of the environment; and a second prediction model configured to output information regarding an amount of change of the objective variable from the characteristic and an explanatory variable characterizing the environment.

An occluded hydrogen content estimation method implemented by an occluded hydrogen content estimation device performs an occluded hydrogen content estimation step in which, based on an occluded hydrogen unit content which is a content of hydrogen occluded in a metal due to a change in humidity from a wet state to a dry state, a period after the metal is placed, and meteorological data corresponding to the period for an area where the metal is located, a content of occluded hydrogen that is absorbed in the metal for the period after the metal is placed is estimated. In the occluded hydrogen content estimation step, the occluded hydrogen content is estimated by multiplying the number of rainfalls in the meteorological data by the occluded hydrogen unit content.

An electronic apparatus includes a wiring board. The wiring board also includes a first wiring pattern that is provided on the wiring board and includes a first wiring portion extending in a first direction. The wiring board further includes a second wiring pattern that includes a second wiring portion extending in the first direction. The wiring also includes a first via provided on the first wiring portion, and a second via provided on the second wiring portion. A power supply circuit applies a first voltage to the first wiring portion at periodic time intervals. A detection circuit outputs an alert signal when a current flows through the second wiring pattern.

The invention provides novel methods to place a complete package system filled with a sample into a light exposure chamber as a complete unit with periodic monitoring of the contents of the packaging system. Through this approach, it can be determined how the components of a complete package system perform collectively to influence its photoprotective performance enabling a first ever method to quantitate these impacts. In turn this will allow for package designs to be optimized for the photoprotection performances, for the impacts of packaging production defects to be explored, and for the influence of packaging form (e.g., surface area to volume ratio) to be determined. Such capabilities allow a first ever means to optimize package systems for photoprotective performance.

A corrosion rate estimation device for estimating a corrosion rate of a metal disposed in a predetermined environment includes an input unit that inputs water component information including information such as water content (time), temperature, conductivity, soil type, and the like, a corrosion rate estimation model configured to receive the water component information related to a water component contained in the predetermined environment as an input, and estimate the corrosion rate of the metal disposed in the predetermined environment from the water component information, and an output unit that outputs the estimated corrosion rate of the metal to the outside. The corrosion rate estimation model is generated using, for example, a machine learning algorithm such as a random forest, a neural network, or RNN (LSTM).

A corrosion rate estimation device for estimating a corrosion rate of a metal disposed in a predetermined environment includes an input unit that inputs water component information including information such as water content (time), temperature, conductivity, soil type, and the like, a corrosion rate estimation model configured to receive the water component information related to a water component contained in the predetermined environment as an input, and estimate the corrosion rate of the metal disposed in the predetermined environment from the water component information, and an output unit that outputs the estimated corrosion rate of the metal to the outside. The corrosion rate estimation model is generated using, for example, a machine learning algorithm such as a random forest, a neural network, or RNN (LSTM).

Here is described an apparatus for measuring and/or monitoring a strength of a magnetic field inside a sample including: a fixing unit made of a non-magnetic material; a magnetic field strength measuring device having a sensor; and a first elongated member and a second elongated member. The elongated members are made of a material having a high relative magnetic permeability, and each of the elongated members has a first end portion and a second end portion. The fixing unit is configured to support the elongated members in a fixed posture such that the first end portion of the first elongated member and the first end portion of the second elongated member are positioned opposite to each other to form a gap, and the fixing unit is configured to support the sensor of the measuring device inside the gap or substantially inside the gap.

A metal material corrosion loss mapping method includes creating a corrosion loss prediction map by using corrosion loss data including a use period of a metal material, a plurality of environmental parameters, position coordinates of the environmental parameters on a map, topographical data of the map, and a corrosion loss of the metal material. The metal material corrosion loss mapping method includes: an environment map creation step of creating an environment map at certain mesh intervals based on the environmental parameters, the topographical data of the map, and the position coordinates of the environmental parameters; a prediction request point input step; a similarity degree calculation step; a corrosion loss prediction step; and a corrosion loss prediction map creation step of creating a corrosion loss prediction map by coloring a prediction result of the corrosion loss at the prediction request point in the mesh.

A metal material corrosion loss mapping method includes creating a corrosion loss prediction map by using corrosion loss data including a use period of a metal material, a plurality of environmental parameters, position coordinates of the environmental parameters on a map, topographical data of the map, and a corrosion loss of the metal material. The metal material corrosion loss mapping method includes: an environment map creation step of creating an environment map at certain mesh intervals based on the environmental parameters, the topographical data of the map, and the position coordinates of the environmental parameters; a prediction request point input step; a similarity degree calculation step; a corrosion loss prediction step; and a corrosion loss prediction map creation step of creating a corrosion loss prediction map by coloring a prediction result of the corrosion loss at the prediction request point in the mesh.

A corrosion amount estimation apparatus that estimates the corrosion amount of a metal material buried in the ground, the apparatus including: a soil adjustment unit that dries the target soil; a water permeability measurement unit that measures the water permeability of the soil after supplying water to the dried soil; and a corrosion estimation unit that estimates the corrosion amount of the metal material when buried in the soil using the water permeability.