Abstract: A method can include rendering a graphical user interface to a display; receiving data; responsive to determining boundary locations for formations in the subsurface environment using the data, automatically rendering the boundary locations in the graphical user interface; responsive to determining extended boundary locations in the subsurface environment for a region beyond an end of the borehole using the boundary locations, automatically rendering the extended boundary locations in the graphical user interface; responsive to determining a target location in the region using the extended boundary locations, automatically rendering the target location in the graphical user interface; and, responsive to generation of a trajectory from an end of the borehole location to the target location, automatically rendering the trajectory in the graphical user interface.

Abstract: A Channel State Information (CSI) transmission method and apparatus, a terminal, and a network-side device, are provided. The method includes sending at least one CSI report. The at least one CSI report includes a first CSI report including at least two pieces of CSI. A mapping order of the at least two pieces of CSI is determined based on first information. The first information includes at least one of the following: second information associated with each of the at least two pieces of CSI, reported content of each of the at least two pieces of CSI, or an order of at least two spatial adaptation patterns or an order of at least two sub-configurations configured or indicated by a network-side device. The at least two spatial adaptation patterns or the at least two sub-configurations are in a one-to-one correspondence with the at least two pieces of CSI.

Abstract: A method can include acquiring resistivity measurements using a downhole tool of a drillstring disposed in a borehole in a subsurface environment; performing a resistivity measurement-based inversion to generate a structural representation of a portion of the subsurface environment that includes an end of the borehole; generating a control instruction using an artificial intelligence framework and the structural representation, where the control instruction is for lengthening the borehole along a current borehole trajectory or a different borehole trajectory; and controlling the drillstring to lengthen the borehole based on the control instruction.

Abstract: A method and system for finding and efficiently evaluating and selecting a wellbore path that accounts for placement rules and the presence of existing wells. A topological representation of the connected paths is created and managed. The topological representation may be generated as a pre-computed database of space information that represents the locations of existing wells and accounts for restrictions such as anti-collision and the parameters, including geological and drilling equipment parameters. Using such a representation, the design of a wellbore path may be completed quickly and more efficiently. The topology may represent all connected space for a section of the subsurface. This topological representation may be used to evaluate all possible paths from the starting point (surface location, tie-in point for a sidetrack, tie-in point for replanning, etc.) to the target and enable selecting the path that meets the conditions and is optimized for the existing constraints.

Abstract: Systems and methods for training and using a prompt token generator to generate a set of prompt tokens which, when fed into a pretrained generative image transformer (e.g., an autoregressive transformer, continuous diffusion model, non-autoregressive transformer, or discrete diffusion model), may bias the generative image transformer's output towards a particular domain (e.g., towards a particular class of images, towards a particular training instance, etc.). In some examples, the prompt token generator may be used to generate a set of different prompt token sequences, which may then be fed sequentially to a pretrained non-autoregressive generative image transformer as it iteratively generates each image in each time-step in order to introduce more diversity into the transformer's final output.

Abstract: A method can include generating candidate trajectories for drilling a borehole in a subsurface environment; contextualizing each of the candidate trajectories using data from offset wells in the subsurface environment to assign contexts to portions of each of the candidate trajectories; assigning weights to the contexts; ranking the candidate trajectories utilizing the weights; based on the ranking, selecting one of the candidate trajectories; and issuing control instructions to equipment for drilling at least a portion of the borehole using the selected one of the candidate trajectories.

Abstract: Provided are a channel state information processing unit CPU occupancy determining method, a terminal and a readable storage medium. The method includes: determining, by a terminal based on at least two first report sub-configurations in a target CSI report configuration, CPU occupancy required for a target CSI report, the target CSI report including: at least two first CSI reports and/or a second CSI report, where each first CSI report is a CSI report performed by the terminal based on one of the first report sub-configurations, and each first CSI report corresponds to one spatial adaptation pattern; the second CSI report is a CSI report performed by the terminal based on the at least two first report sub-configurations, and the second CSI report corresponds to at least two spatial adaptation patterns; and the CPU occupancy includes a time period of the CPU occupancy and/or a quantity of occupied CPUs.

Abstract: A method for reporting a CSI report is provided. The method includes: determining, by a terminal according to target information, a target sub-configuration corresponding to CSI to be reported at a target CSI report occasion, where the target sub-configuration is one or more sub-configurations in a set of valid sub-configurations in a CSI report configuration, the set of valid sub-configurations includes at least one of: all sub-configurations in the CSI report configuration, one or more default sub-configurations in the CSI report configuration, or one or more activated sub-configurations in the CSI report configuration, and the target information includes at least one of: a target rule or target indication information; and reporting, by the terminal, a target CSI report at the target CSI report occasion, where the target CSI report includes CSI corresponding to the target sub-configuration.

Abstract: This disclosure relates to a predictive lookahead system that generates simulated or predicted wellbore trajectory plans in a drilling environment and determines when a simulated wellbore trajectory plan is at risk based on various lookahead metrics, such as torque and drag (T&D) metrics and hydraulic pressure metrics. For instance, the predictive lookahead system uses a predictive framework with various steps to determine if drilling metrics for a predictive wellbore trajectory plan, such as T&D metrics and/or hydraulic pressure metrics corresponding to subsurface formations, may exceed one or more risk threshold limits and cause damage to the drill bit, drill string, casing, and/or surface rig. The predictive lookahead system determines whether a predictive wellbore trajectory, which aims to converge with a previously planned wellbore trajectory, can proceed safely along the projected trajectory without exceeding T&D, pressure window, or other lookahead metric limits in the wellbore.

Abstract: A method can include rendering a graphical user interface to a display; receiving data; responsive to determining boundary locations for formations in the subsurface environment using the data, automatically rendering the boundary locations in the graphical user interface; responsive to determining extended boundary locations in the subsurface environment for a region beyond an end of the borehole using the boundary locations, automatically rendering the extended boundary locations in the graphical user interface; responsive to determining a target location in the region using the extended boundary locations, automatically rendering the target location in the graphical user interface; and, responsive to generation of a trajectory from an end of the borehole location to the target location, automatically rendering the trajectory in the graphical user interface.

Abstract: A method can include receiving data acquired via a drillstring in a borehole in a subsurface environment; determining boundary locations for formations in the subsurface environment using at least a portion of the data, where an end of the borehole is disposed in one of the formations; determining extended boundary locations in the subsurface environment for a region beyond the end of the borehole using the boundary locations; determining a target location in the region; generating a trajectory from an end of the borehole location to the target location; and executing a directional drilling system to control directional drilling of the drillstring that extends the borehole beyond the end of the borehole towards the target location.

Abstract: A method can include acquiring resistivity measurements using a downhole tool of a drillstring disposed in a borehole in a subsurface environment; performing a resistivity measurement-based inversion to generate a structural representation of a portion of the subsurface environment that includes an end of the borehole; generating a control instruction using an artificial intelligence framework and the structural representation, where the control instruction is for lengthening the borehole along a current borehole trajectory or a different borehole trajectory; and controlling the drillstring to lengthen the borehole based on the control instruction.

Abstract: A channel state information (CSI) sending method, which includes sending, by user equipment (UE), a plurality of pieces of first CSI to a network side device according to a first form, where the plurality of pieces of first CSI are CSI for different measurement assumptions. The first form includes feeding back one CSI report, where the CSI report includes the plurality of pieces of first CSI.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a video output using an autoregressive token generation neural network model In one aspect, a system comprises obtaining a model input, processing the model input to generate an input sequence of embeddings that represents the model input, autoregressively generating a plurality of output sequences of tokens, wherein each output sequence of tokens corresponds to a respective output modality of tokens from a set of a plurality of modalities that includes a video modality and one or more other modalities, and generating a model output that includes a video output of the video modality by decoding the sequence of tokens.

Abstract: A channel state information reporting and processing method and apparatus are disclosed. The method includes: receiving, by a terminal, indication information sent by a network side device, the indication information indicating a change related to channel state information (CSI) reporting configuration; and performing, by the terminal, CSI reporting based on the indication information.

Abstract: A system and method that include receiving a well plan and determining a plurality of sections of the well plan and receiving data from surface and downhole to determine a current location of a drill bit. The system and method also include analyzing the well plan to automatically derive trajectory constraints that are associated with each of the plurality of sections of the well plan. The system and method additionally include determining a plurality of trajectory candidates that pertain to respective paths from the current location of a drill bit to respective targets included within each of the plurality of sections of the well plan based on a consideration of the trajectory constraints. The system and method further include determining a working plan that includes an optimal path from the current location of the drill bit to reach a final target based on the plurality of trajectory candidates.

Abstract: Provided are techniques for training a denoising diffusion model on multi-modal data which leverage a timestep vector with a mixture of timestep values.

Abstract: Techniques for determining trajectories for a plurality of wells while avoiding collision between wells are presented. The techniques can include determining a zone of uncertainty for individual wells of the plurality of wells, determining a minimum separation factor for individual wells of the plurality of wells, determining a gradient of a separation factor for at least one pair of wells of the plurality of pairs of wells, updating a nudge position for at least one well, and providing nudge positions for the individual wells of the plurality of wells.

Abstract: A method can include receiving data for a bottom hole assembly of a drillstring and a drill plan; generating candidate trajectories using at least a portion of the data; generating drill command schedules for the candidate trajectories; ranking the candidate trajectories based at least in part on the drill command schedules; and outputting at least a top ranked candidate trajectory and its corresponding drill command schedule.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controllable video generation. One of the methods includes receiving a text prompt that specifies an object; receiving a control input that comprises an image that depicts a particular instance of the object; generating a video that comprises a respective video frame at each of a plurality of time steps in the video and that depicts the particular instance of the object. Generating the video includes, at each of the plurality of time steps: obtaining a text prompt embedding; obtaining a control input embedding; and generating the respective video frame at the time step using a video generation neural network while the video generation neural network is conditioned on the text prompt embedding and on the control input embedding.