Abstract: The present disclosure provides for crop yield estimation by identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data.

Abstract: This disclosure provides a data-driven and scalable method to discover cause-and-effect relationships in data from natural systems that include sparse data sets. This technique can learn a causal graph from heterogenous data sources by combining embeddings from real data and embeddings from simulated data generated by process-based models. The causal graph is used for what-if analysis in out-of-distribution settings. One application is understanding the factors that affect soil carbon. A causal model created by these techniques can be used to discover cause-and-effect relationships that affect soil carbon. This model has applications such as forecasting soil carbon for a future time point to help inform farm practices. Farm practices, like tilling, may be modified in response to predictions provided by the model.

Abstract: One or more processors may detect that an extreme event that occurred in a first region. One or more processors may determine that the extreme event creates a drift in a probability distribution that is an output of a model associated with the first region. One or more processors may retrain the model associated with the first region using data associated with the extreme event. One or more processors may identify a second region similar to the first region according to a defined correlation threshold. One or more processors may generate data representing potential extreme scenarios for the second region based on the detected extreme event in the first region. One or more processors may retrain a model associated with the second region based on the generated data representing potential extreme scenarios.

Abstract: Constructive layout in a container, to provide clean areas for medical and hospital care, such as fractionation of solid and liquid oral drugs (ISO8) and handling of sterile drugs (ISO7), as well as the configuration of the containers for the infusion, diagnosis, surgery, ICU and hemodialysis areas.

Abstract: A microservice and the recipe for that microservice are automatically created by modifying a local environment in an integrated development environment executing on a computing system to construct a desired microservice, recording commands entered while modifying the local environment, computing a list of changes from the recorded commands that change the local environment and compiling the list of changes into a recipe comprising commands and dependencies sufficient to assemble an operating system and software files that are sufficient to instantiate the desired microservice.

Abstract: A method includes confirming when a vehicle accesses a region of interest, obtaining data associated within the region of interest, and determining, based on analytics performed on the data obtained of the region of interest, whether one or more anomalies are present at the region of interest. Obtaining data includes at least one of collecting, with an imaging sensor associated with the vehicle, image data of a given point of interest within the region of interest or collecting, with a motion sensor associated with the vehicle, motion data of the vehicle in a given fragment of interest within the region of interest. The confirming, obtaining and determining steps are performed by at least one processing device comprising a processor operatively coupled to a memory.

Abstract: The present disclosure provides for crop yield estimation by identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data.

Abstract: Resource usage is monitored for a hybrid cloud computing environment having on-premises computing resources and off-premises computing resources, for at least a first time period. For the time period, the amount of the on-premises computing resources and off-premises computing resources are related to the demand for computing services from the environment. Future demand for computing services from the environment is dynamically predicted based on the relating step and a learned function of the demand and/or a projection of future business growth for a business utilizing the on-premises and off-premises computing resources. Based on the predicted future demand, the amount of the on-premises computing resources is dynamically optimized for a future time period, so as to minimize costs for the future time period; and new amounts of on-premises computing resources and off-premises computing resources are provisioned for the future time period, in accordance with the optimizing step.

Abstract: A method includes confirming when a vehicle accesses a region of interest, obtaining data associated within the region of interest, and determining, based on analytics performed on the data obtained of the region of interest, whether one or more anomalies are present at the region of interest. Obtaining data includes at least one of collecting, with an imaging sensor associated with the vehicle, image data of a given point of interest within the region of interest or collecting, with a motion sensor associated with the vehicle, motion data of the vehicle in a given fragment of interest within the region of interest. The confirming, obtaining and determining steps are performed by at least one processing device comprising a processor operatively coupled to a memory.

Abstract: A method for automatically generating scheduling algorithms, including determining a scheduling policy for a plurality of jobs to be executed on a computer system, where the scheduling policy specifies an execution order of a plurality of jobs; using the scheduling policy in a production environment for a period of time, and collecting data indicative of a business impact of each job executed during the period of time; generating a list of all pairwise comparisons of business impact between the plurality of jobs, together with outcomes of the comparisons; marking each pair for which the comparison outcome is inconsistent with the relative execution order of the pair of jobs according to a predefined criteria to create a reinforcement learning batch; and using the reinforcement learning batch to adjust a decision criteria used to determine the scheduling policy.

Abstract: A microservice and the recipe for that microservice are automatically created by modifying a local environment in an integrated development environment executing on a computing system to construct a desired microservice, recording commands entered while modifying the local environment, computing a list of changes from the recorded commands that change the local environment and compiling the list of changes into a recipe comprising commands and dependencies sufficient to assemble an operating system and software files that are sufficient to instantiate the desired microservice.

Abstract: A computer-implemented method, a computer program product, and a computer system for infrastructure resource provisioning using trace-based workload temporal analysis. An infrastructure provider receives, from an on-premises infrastructure, scheduler traces of the on-premises infrastructure, one or more scenarios, one or more goals, and one or more constraints of resource deployment on the on-premises infrastructure. The infrastructure provider performs trace-based workload temporal analysis, based on the scheduler traces, the one or more scenarios, the one or more goals, and the one or more constraints. The infrastructure provider generates one or more options of provisioning infrastructure resources, based on the trace-based workload temporal analysis.

Abstract: Constructive layout in a container, to provide clean areas for medical and hospital care, such as fractionation of solid and liquid oral drugs (ISO8) and handling of sterile drugs (ISO7), as well as the configuration of the containers for the infusion, diagnosis, surgery, ICU and hemodialysis areas.

Abstract: A method for automatically generating scheduling algorithms, including determining a scheduling policy for a plurality of jobs to be executed on a computer system, where the scheduling policy specifies an execution order of a plurality of jobs; using the scheduling policy in a production environment for a period of time, and collecting data indicative of a business impact of each job executed during the period of time; generating a list of all pairwise comparisons of business impact between the plurality of jobs, together with outcomes of the comparisons; marking each pair for which the comparison outcome is inconsistent with the relative execution order of the pair of jobs according to a predefined criteria to create a reinforcement learning batch; and using the reinforcement learning batch to adjust a decision criteria used to determine the scheduling policy.

Abstract: A system, method and program product for managing hydrocarbon energy production. A hydrocarbon field modeler models physical characteristics of a hydrocarbon energy field. A load predictor predicts processing workload in modeling the hydrocarbon energy field, and identifying a balanced modeling unit distribution across multiple processors simulating field production. A load distribution unit distributes the modeling units across the processors for a balanced modeling unit distribution. The load predictor and load distribution unit proactively shifts loads to maintain workload balanced throughout the simulation.

Abstract: A method for automatically generating scheduling algorithms, including determining a scheduling policy for a plurality of jobs to be executed on a computer system, where the scheduling policy specifies an execution order of a plurality of jobs; using the scheduling policy in a production environment for a period of time, and collecting data indicative of a business impact of each job executed during the period of time; generating a list of all pairwise comparisons of business impact between the plurality of jobs, together with outcomes of the comparisons; marking each pair for which the comparison outcome is inconsistent with the relative execution order of the pair of jobs according to a predefined criteria to create a reinforcement learning batch; and using the reinforcement learning batch to adjust a decision criteria used to determine the scheduling policy.

Abstract: A method and computer program product for managing hydrocarbon field production, e.g., petro-chemical reservoir production. The hydrocarbon field is modeled using the finite volume method (FVM) model and the finite element method (FEM). Centroids are located in each FVM cell and each FEM element and overlapping cells are identified. After determining the distance between centroids for overlapping cells, fluid characteristics are mapped to the FEM element centroids, weighted inversely for distance between the respective centroids. A permeability/conductivity weighted average is determined for pore pressure and temperature of sub-volumes clustered around each FEM element node. Field production may be adjusted in response to FEM element node characteristics.

Abstract: A method for automatically generating scheduling algorithms, including determining a scheduling policy for a plurality of jobs to be executed on a computer system, where the scheduling policy specifies an execution order of a plurality of jobs; using the scheduling policy in a production environment for a period of time, and collecting data indicative of a business impact of each job executed during the period of time; generating a list of all pairwise comparisons of business impact between the plurality of jobs, together with outcomes of the comparisons; marking each pair for which the comparison outcome is inconsistent with the relative execution order of the pair of jobs according to a predefined criteria to create a reinforcement learning batch; and using the reinforcement learning batch to adjust a decision criteria used to determine the scheduling policy.

Abstract: Resource usage is monitored for a hybrid cloud computing environment having on-premises computing resources and off-premises computing resources, for at least a first time period. For the time period, the amount of the on-premises computing resources and off-premises computing resources are related to the demand for computing services from the environment. Future demand for computing services from the environment is dynamically predicted based on the relating step and a learned function of the demand and/or a projection of future business growth for a business utilizing the on-premises and off-premises computing resources. Based on the predicted future demand, the amount of the on-premises computing resources is dynamically optimized for a future time period, so as to minimize costs for the future time period; and new amounts of on-premises computing resources and off-premises computing resources are provisioned for the future time period, in accordance with the optimizing step.

Abstract: A system, method and program product for managing hydrocarbon energy production. A hydrocarbon field modeler models physical characteristics of a hydrocarbon energy field. A load predictor predicts processing workload in modeling the hydrocarbon energy field, and identifying a balanced modeling unit distribution across multiple processors simulating field production. A load distribution unit distributes the modeling units across the processors for a balanced modeling unit distribution. The load predictor and load distribution unit proactively shifts loads to maintain workload balanced throughout the simulation.