Combining point observations with raster data for machine learning
AssigneesInternational Business Machines Corporation, IHI Corporation
InventorsJohannes W. Schmude, Siyuan Lu, Hendrik F. Hamann, Akihisa Sakurai, Taku Izumiyama, Masao Hasegawa
Life of this patent
Estimating the term…
Abstract
A computer produces predictions throughout a raster field in response to point data, by obtaining a partially empty matrix of point data, filling a matrix of extrapolated raster data by dilating the point data in a first convolutional neural network, and generating a matrix of aggregate raster data by combining the extrapolated raster data with organic raster data in a second convolutional neural network.
Claims20
A method for operating a computer to produce predictions throughout a raster field in response to point data, the method comprising:
- obtaining a partially empty matrix of point data <X0>;
- filling a matrix of extrapolated raster data <Xn> by dilating the point data in a first convolutional neural network;
- and
- generating a matrix of aggregate raster data <Xa> by combining the extrapolated raster data <Xn> with organic raster data <Xr> in a second convolutional neural network.
A non-transitory computer readable medium embodying computer executable instructions which when executed by a computer cause the computer to facilitate a method of:
- obtaining a partially empty matrix of point data <X0>;
- filling a matrix of extrapolated raster data <Xn> by dilating the point data in a first convolutional neural network;
- and
- generating a matrix of aggregate raster data <Xa> by combining the extrapolated raster data <Xn> with organic raster data <Xr> in a second convolutional neural network.
An apparatus comprising:
- a memory embodying computer executable instructions;
- and
- at least one processor, coupled to the memory, and operative by the computer executable instructions to facilitate a method of:
- obtaining a partially empty matrix of point data <X0>;
- filling a matrix of extrapolated raster data <Xn> by dilating the point data in a first convolutional neural network;
- and
- generating a matrix of aggregate raster data <Xa> by combining the extrapolated raster data <Xn> with organic raster data <Xr> in a second convolutional neural network.
Dependencies are inferred from the claim text.