Abstract: This disclosure introduces a novel method and system for using a large language model (LLM) to create a convenient interface for a complex database. The system includes a custom prompt generator that creates custom prompts from natural language queries. The custom prompts are used to control how the LLM interacts with a database look-up tool. The database look-up tool provides queries to the database in a format understandable by the database and receives responses from the database. This system is useful for obtaining information that is not in a natural language, and thus, is poorly suited for being processed as an embedding by the LLM. Information obtained from the database is included in an answer produced by the LLM.

Abstract: A computing system for interactive prompting for a supply chain includes processing circuitry that constructs a knowledge graph based ontologies from a plurality of data sources, the ontologies being related to a product. In a turn-based dialog session, the processing circuitry receives a prompt for the product, identifies at least one ontology-level node in a first layer of the knowledge graph, and generates one or more sub-questions. The processing circuitry outputs the sub-questions via a large language model, receives responses to the sub-questions, identifies one or more second-level nodes in a second, middle layer of the knowledge graph based on the responses, and performs a multi-hop query to identify one or more instance-level nodes in the third layer of the knowledge graph. The processing circuitry outputs, via the large language model, text data corresponding to the instance-level nodes as an answer to the prompt.

Abstract: The techniques disclosed herein enable an autonomous agent to interpret an input dataset and orchestrate a suite of software modules to perform a computational task on a representation of a chemical material. The input dataset includes a prompt defining a computational task to be performed on a chemical material. Moreover, the input dataset includes data defining a chemical included in the chemical material, molecular descriptors describing the chemical and/or the chemical material, and an external variable. The agent analyzes the benefits and drawbacks of each model within the context of the computational task to determine a technique for performing the computational task. Accordingly, the agent formulates a chain of calls invoking the functionality of data processing tools and models to perform the computational task responsive to the prompt.

Abstract: Techniques for optically detecting a subject chemical species within an atmospheric environment are disclosed. Image data is obtained representing multispectral imagery of a geographic region captured through the atmospheric environment. The image data includes an array of band-specific intensity values for each of a plurality of spectral bands, including a sample spectral band having increased sensitivity to the subject chemical species as compared to a plurality of reference spectral bands. A background reflectance map is generated that includes an array of inter-band intensity values in which each inter-band intensity value represents a filtered combination of band-specific intensity values of albedo-normalized arrays for a grouped subset of the plurality of reference spectral bands. The albedo-normalized array of band-specific intensity values for the sample spectral band is compared to the background reflectance map to obtain an index array of intensity variance values for the subject chemical species.

Abstract: This disclosure provides a machine learning technique to predict a protein characteristic. A first training set is created that includes, for multiple proteins, a target feature, protein sequences, and other information about the proteins. A first machine learning model is trained and then used to identify which of the features are relevant as determined by feature importance or causal relationships to the target feature. A second training set is created with only the relevant features. Embeddings generated from the protein sequences are also added to the second training set. The second training set is used to train a second machine learning model. The first and second machine learning models may be any type of regressors. Once trained, the second machine learning model is used to predict a value for the target feature for an uncharacterized protein. The model of this disclosure provides 91% accuracy in predicting an ideal digestibility score.

Abstract: A deep learning system is used to predict crop characteristics from inputs that include crop variety features, environmental features, and field management features. The deep learning system includes domain-specific modules for each category of features. Some of the domain-specific modules are implemented as convolutional neural networks (CNN) while others are implemented as fully-connected neural networks. Interactions between different domains are captured with cross attention between respective embeddings. Embeddings from the multiple domain-specific modules are concatenated to create a deep neural network (DNN). The prediction generated by the DNN is a characteristic of the crop such as yield, height, or disease resistance. The DNN can be used to select a crop variety for planting in a field. For a crop that is planted, the DNN may be used to select a field management technique.

Abstract: Techniques for optically detecting a subject chemical species within an atmospheric environment are disclosed. Image data is obtained representing multispectral imagery of a geographic region captured through the atmospheric environment. The image data includes an array of band-specific intensity values for each of a plurality of spectral bands, including a sample spectral band having increased sensitivity to the subject chemical species as compared to a plurality of reference spectral bands. A background reflectance map is generated that includes an array of inter-band intensity values in which each inter-band intensity value represents a filtered combination of band-specific intensity values of albedo-normalized arrays for a grouped subset of the plurality of reference spectral bands. The albedo-normalized array of band-specific intensity values for the sample spectral band is compared to the background reflectance map to obtain an index array of intensity variance values for the subject chemical species.

Abstract: A method for source attribution comprises receiving measurements of a chemical species at a spatially distributed sensor array for a given set of spatially positioned emission sources in a physical environment using a dispersion model. Based on the received measurements, a concentration field is mapped from the emission sources to the sensor array using a forward operator. For each emission source, a likelihood data set is evaluated at least by fitting an emission rate of the chemical species using a regression model based on the mapped concentration field and real-world, runtime measurements from the sensor array. A posterior data set is evaluated based at least on the evaluated likelihood data set and historical data for the physical environment. For each sensor of the sensor array, estimated emission rates and contribution rankings for emission sources are determined and output based on the evaluation of the posterior data set.

Abstract: A method for pollutant sensor placement for pollutants from point sources is described. Data about environmental characteristics for a geographic region are received from a plurality of environmental sensors. The geographic region includes pollutant sources that emit a pollutant. The received data from one or more of the plurality of environmental sensors are transformed into common data having a common spatial and temporal discretization across the geographic region. Predicted emission plumes are generated for the pollutant sources within the geographic region that identify pollutant detection regions for the pollutant when the pollutant is emitted by the pollutant sources using the common data. Sensor locations for a plurality of pollutant sensors are greedily selected across the common spatial and temporal discretization according to a number of predicted emission plumes that are detectable by the plurality of pollutant sensors.