International Business Machines Corporation

Utopus Insights, Inc.

Aanchal Goyal

Younghun Kim

Tarun Kumar

Aleksandr Y Aravkin

Ranjini Bangalore Guruprasad

Mark Alan Lavin

Fook-Luen Heng

Jagabondhu Hazra

Sachin Gupta

Kevin Wilson Warren

Srivats Shukla

Wander S Wadman

Kamal Das

Methods, systems, and computer program products for dynamic determination of irrigation-related data using machine learning techniques are provided herein. A computer-implemented method includes obtaining irrigation-related data pertaining to a region of interest; determining temporal values corresponding to irrigation activity at the region of interest by performing spatiotemporal analysis of the irrigation-related data; determining amounts of water utilized in connection with the irrigation activity corresponding to the temporal values by applying machine learning techniques to the irrigation-related data; determining types of irrigation activity attributed to the irrigation activity by applying machine learning techniques to the irrigation-related data and determined amounts of water; determining irrigation-related variables pertaining to the region of interest by executing a physical model using, as inputs, the determined temporal values, amounts of water, and types of irrigation activity, wherein the irrigation-related variables include an extent of irrigation activity; and outputting the determined irrigation-related variables to a user.

Dynamic determination of irrigation-related data using machine learning techniques

A virtual satellite system may receive, re-project to a spatial resolution and interpolate to a desired temporal resolution, georeferenced data representing an image of a geographic region from a plurality of different satellites. Bias in the georeferenced data between the plurality of satellites is determined and based on which satellite's image data contains an identified minimum spatial resolution, vegetation index data may be set to one of the satellite's data, which may or may not be adjusted. A target image may be generated based on the set vegetation index data.

Enhancing temporal and spatial resolution and correcting data anomalies of remote sensed data for estimating high spatio-temporal resolution vegetation indices

Embodiments herein relate to improving a stochastic forecast for uncertain power generations and demands to quantify an effect on an electrical power grid. To improve the stochastic forecast, a method includes fitting marginal distributions to data of the uncertain power generation and demand by power generation and demand nodes of the electrical power grid. The power generation and demand nodes provide corresponding uncertain power generation and demand based on a renewable energy source. The method also includes determining a correlation structure between the power generation and demand nodes by transforming the data from marginal distributions to a second distribution and by fitting a multivariate time series on transformed data. The method also includes simulating multivariate stochastic forecast with an improved correlation structure.

Quantifying a combined effect of interdependent uncertain resources in an electrical power grid

Disclosed herein are systems, methods, and computer-readable media for utilizing sensor data captured by one or more sensors as well as ground-truth physically sampled data to generate a predictive model that can be used to estimate a measurable parameter without having to obtain additional physically sampled data for the parameter.

Predictive modeling to estimate data values between sampling events

A system and method to produce an electric network from estimated line impedance and physical line length among smart meter devices is provided using communication between the smart meters. The smart meters: (1) synchronize time using GPS pps signals, which provide an accurate time stamp; (2) send/receive an identifiable signal through the same phase of electric networks; (3) identify other smart meters on the same phase lines by listening to the information signal on the same phase lines; and (4) calculate time-of-arrival of an identifiable signal from other smart meters. The time of arrival information is used to calculate the line length, which is then used to calculate impedance of a line and topology of the electric network. The system then constructs an electric network by combining geo-spatial information and tree-like usual connection information.

Method and apparatus to determine electric power network anomalies using a coordinated information exchange among smart meters

Growing community of inventors

White Plains, NY, United States of America

Aanchal Goyal