20 docs tagged with "Smart-Foodsheds"

The Angular UI is structured around two primary sections: Domestic Flow and Foreign Flow, both accessible from the left-hand navigation menu. Each section is designed to support efficient exploration and analysis of freight data.

- PDF-to-Text Extraction

Graph Neural Networks for Food Trade Flow Prediction

Project Structure

LinkML is an emerging standard and toolset for describing data schemas with an orientation towards building linked data applications. LinkML data schemas are written in YAML and the framework provides tools to convert these schemas into a number of other formats, including JSON-Schema, OWL, SQL DDL, SHACL, ShEx, and Python classes. The framework also provides tools for validating and converting data between different formats including RDF, CSV, JSON, YAML, and SQLite databases. As such LinkML is intended as a lingua franca for interoperability between data schemas and datasets.

TapisUI provides a research oriented frontend to interact with Tapis and tenant components. In this case, the ICICLE extension extends TapisUI with custom branding

API access to the US Bureau of Transportation Statistics' Freight Analysis Framework dataset

This is intended as a helpful front end to a REST API to the US Bureau of Transportation Statistics (BTS) Feight Analysis Framework (FAF) dataset. It has been developed by the Data To Insight Center (D2I) at Indiana University as part of the NSF ICICLE AI Institute and in collaboration with the US Bureau of Transportation Statistics. See FAF-API-ICICLE. This project was generated with Angular CLI version 18.2.12.

Overview

1. Install Dependencies

For a complete overview of how to use the API, please refer to the APIREADME.md file located in the same directory. This file provides a detailed explanation of each endpoint, including:

🌐 Accessing the Frontend

How to Implement a Hurdle Model for Trade Prediction

Repository Clone

View the main TapisUI wiki to learn how to deploy and test TapisUI extensions locally.

A project leveraging Graph Neural Networks (GNNs) to predict food flows between counties and FAF zones for economic planning, infrastructure development, and policy-making.

This repository contains code for training and evaluating models that classify organizations into Standard Industrial Classification (SIC) codes based on different types of descriptive text. This model is designed for researchers and data scientists who need to categorize unknown or newly listed organizations by business type. It can be applied to tasks such as food systems research, analyzing supply chains, and regional economic mapping, particularly in scenarios where structured corpora are unavailable. Given only an organization’s name and its description, the model predicts a high-level SIC category.

This repository contains a LinkML schema for a version of the PPOD (Persons-Projects-Organizations-Datasets) data pattern that describes resources being cataloged by the UC Davis Food Systems Lab. These are resources pertinent to California foodsheds and conservation activities, and include lists of organizations, people, programs, projects, tools, datasets, and guidelines and mandates. These resources are currently maintained in a Google Sheets document which is converted into a RDF Turtle file using a Python script that is posted in the PPODtottl repository.

This tapis ui extension enables additional icicle specific branding and tabs on tapisui.

Getting Started with Food Flow Prediction