A method and system perform quantum-assisted finite elements-based, design optimization of an object to minimize a shape-specific quantity by manipulating the shape of the object using a processing unit, for example, a Quantum Processing Unit (QPU). As a result, a shape-specific quantity, such as an approximation of sound pressure at a specific position around an object, can be minimized by manipulating the object shape using the QPU.

A method and system for building a thermal model of a power lithium-ion battery based on an electrochemical mechanism. The method includes: discretizing a second order partial differential heat conduction equation of a power lithium-ion battery according to a finite differential method, thereby building a thermal model of the power lithium-ion battery; carrying out a dynamic working condition test by using a cylindrical power lithium-ion battery selected as an object, thereby acquiring experimental data such as a temperature, a current, a voltage, and a temperature of a surface of the battery; identifying an electrochemical parameter of the power lithium-ion battery according to an optimal parameter algorithm by using test data acquired in a dynamic working condition, thereby building a thermal model of the power lithium-ion battery; and verifying accuracy of the thermal model of the power lithium-ion battery by using test data acquired in another dynamic working condition.

A method for a whole-process numerical simulation and hazard forecast of a mountain disaster is provided. The method includes: S1, a high space-time rainfall forecast of a mountain area; S2, a hydrodynamic process and numerical simulation: establishing a hydrodynamic process model and solving the hydrodynamic process model; S3, a motion model and numerical simulation of a mountain torrent and debris flow disaster; and S4, a risk analysis and hazard forecast of a small watershed disaster. The present invention predicts disaster hazard and dynamically and quantitatively evaluates risk loss according to a whole-process scenario simulation of the disaster driven by a climate forecast result, improves current disaster level forecasts to hazard forecasts, and serves for accurate disaster preventions and accurate rescues.

A method, a computer system, and a computer program product for regionalized climate models is provided. Embodiments of the present invention may include selecting a class of a reduced order model. Embodiments of the present invention may include building a neural network in a reduced order space. Embodiments of the present invention may include recovering full state dynamics. Embodiments of the present invention may include training a model. Embodiments of the present invention may include providing an output.

A method, a computer system, and a computer program product for regionalized climate models is provided. Embodiments of the present invention may include selecting a class of a reduced order model. Embodiments of the present invention may include building a neural network in a reduced order space. Embodiments of the present invention may include recovering full state dynamics. Embodiments of the present invention may include training a model. Embodiments of the present invention may include providing an output.

Techniques for incorporating a black-box function into a neural network are described. For example, an image editing function may be the black-box function and may be wrapped into a layer of the neural network. A set of parameters and a source image are provided to the black-box function, and the output image that represents the source image with the set of parameters applied to the source image is output from the black-box function. To address the issue that the black-box function may not be differentiable, a loss optimization may calculate the gradients of the function using, for example, a finite differences calculation, and the gradients are used to train the neural network to ensure the output image is representative of an expected ground truth image.

Techniques for incorporating a black-box function into a neural network are described. For example, an image editing function may be the black-box function and may be wrapped into a layer of the neural network. A set of parameters and a source image are provided to the black-box function, and the output image that represents the source image with the set of parameters applied to the source image is output from the black-box function. To address the issue that the black-box function may not be differentiable, a loss optimization may calculate the gradients of the function using, for example, a finite differences calculation, and the gradients are used to train the neural network to ensure the output image is representative of an expected ground truth image.

Systems and methods for managing post-harvest crop quality and pests. A post-harvest monitoring system receives sensor device measurements from sensors deployed within a commodity storage facility. The system analyzes the sensor measurements and, optionally, other data, and provides a user with a representation of the storage facility that includes air flow, temperature, and/or moisture content readouts, along with stored commodity quality and/or stored commodity business metrics predictions concerning infestation level, visible mold, dry matter loss, germination capacity, gas concentration, and estimates of commodity value and profit margin under a variety of post-harvest monitoring system-recommended or user-specified scenarios. Use of the system thus enhances stored commodity quality, marketability and food safety by providing solutions that combat spoilage manifestations and guide end users to efficient pest management.

Systems and methods for managing post-harvest crop quality and pests. A post-harvest monitoring system receives sensor device measurements from sensors deployed within a commodity storage facility. The system analyzes the sensor measurements and, optionally, other data, and provides a user with a representation of the storage facility that includes air flow, temperature, and/or moisture content readouts, along with stored commodity quality and/or stored commodity business metrics predictions concerning infestation level, visible mold, dry matter loss, germination capacity, gas concentration, and estimates of commodity value and profit margin under a variety of post-harvest monitoring system-recommended or user-specified scenarios. Use of the system thus enhances stored commodity quality, marketability and food safety by providing solutions that combat spoilage manifestations and guide end users to efficient pest management.

A method for performing a modified two point flux approximation scheme is disclosed. The method includes: obtaining a first pressure value for a first neighbor cell and a second pressure value for a second neighbor cell, where the first neighbor cell has a first value of a reservoir property and the second neighbor cell as a second value of the reservoir property; determining a first weight using the first pressure value and a second weight using the second pressure value; calculating a third value of the reservoir property as a weighted average of the first value and the second value; and applying the third value to the first neighbor cell.