Contains data from the model validation in the 1D Heat Loss Models to Predict the Aquifer Temperature Profile during Hot/Cold Water Injection Project. The data include two COMSOL models (2D axisymmetric benchmark model and 2D Vinsome model), one python code (1D Vinsome based FEM numerical simulation), one matlab main code (1D Newton analytical solution and all results comparison visualization), and output files generated from the above models.

The BUTTER Empirical Deep Learning Dataset represents an empirical study of the deep learning phenomena on dense fully connected networks, scanning across thirteen datasets, eight network shapes, fourteen depths, twenty-three network sizes (number of trainable parameters), four learning rates, six minibatch sizes, four levels of label noise, and fourteen levels of L1 and L2 regularization each. Multiple repetitions (typically 30, sometimes 10) of each combination of hyperparameters were preformed, and statistics including training and test loss (using a 80% / 20% shuffled train-test split) are recorded at the end of each training epoch. In total, this dataset covers 178 thousand distinct hyperparameter settings ("experiments"), 3.55 million individual training runs (an average of 20 repetitions of each experiments), and a total of 13.3 billion training epochs (three thousand epochs were covered by most runs). Accumulating this dataset consumed 5,448.4 CPU core-years, 17.8 GPU-years, and 111.2 node-years.

This is benchmark model for wastewater treatment using an activated sludge process. The activated sludge process is a means of treating both municipal and industrial wastewater. The activated sludge process is a multi-chamber reactor unit that uses highly concentrated microorganisms to degrade organics and remove nutrients from wastewater, producing quality effluent. This model provides pollutant concentrations, mass balance, electricity requirements, and treatment costs. This model will be continuously updated based on the latest data.

The BuildingsBench datasets consist of: - Buildings-900K: A large-scale dataset of 900K buildings for pretraining models on the task of short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock. - 7 real residential and commercial building datasets for benchmarking two downstream tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. Buildings-900K can be used for pretraining models on day-ahead STLF for residential and commercial buildings. The specific gap it fills is the lack of large-scale and diverse time series datasets of sufficient size for studying pretraining and finetuning with scalable machine learning models. Buildings-900K consists of synthetically generated energy consumption time series. It is derived from the NREL End-Use Load Profiles (EULP) dataset (see link to this database in the links further below). However, the EULP was not originally developed for the purpose of STLF. Rather, it was developed to "...help electric utilities, grid operators, manufacturers, government entities, and research organizations make critical decisions about prioritizing research and development, utility resource and distribution system planning, and state and local energy planning and regulation." Similar to the EULP, Buildings-900K is a collection of Parquet files and it follows nearly the same Parquet dataset organization as the EULP. As it only contains a single energy consumption time series per building, it is much smaller (~110 GB). BuildingsBench also provides an evaluation benchmark that is a collection of various open source residential and commercial real building energy consumption datasets. The evaluation datasets, which are provided alongside Buildings-900K below, are collections of CSV files which contain annual energy consumption. The size of the evaluation datasets altogether is less than 1GB, and they are listed out below: 1. ElectricityLoadDiagrams20112014 2. Building Data Genome Project-2 3. Individual household electric power consumption (Sceaux) 4. Borealis 5. SMART 6. IDEAL 7. Low Carbon London

The database is envisioned to become the main source of carbon estimating and benchmarking for the UK construction sector and a practical instrument to support the decarbonisation of the built environment. The database has been developed to collect and supply product data and entity level data to the industry through its own portal and by interacting with existing databases and software solutions.

This dataset describes corporate greenhouse gas emissions and associated financial intensity metrics as reported to the Carbon Disclosure Project (CDP). The data refers specifically to disclosures made during 2010.

Data on water utilities for 151 national jurisdictions, for a range of years up to and including 2017 (year range varies greatly by country and utility) on service and utility parameters (Benchmark Database) and Tariffs for 211 juristictions (Tariffs database). Information includes cost recovery, connections, population served, financial performance, non-revenue water, residential and total supply, total production. Data can be called up by utility, by group of utility, and by comparison between utilities, including the whole (global) utility database, enabling both country and global level comparison for individual utilities. Data can be downloaded in xls format.

The Water Data Portal (WDP), following ""one-stop shop"" approach, provides access to a large amount of data related to water and agriculture. WDP contains meteorological, hydrological, socio-economic, spatial data layer, satellite images as well as hydrological model setups. The data in the WDP, both spatial & non-spatial, are supported by the standardized metadata and are available for download by user including academia, scientists, researchers and decision makers. However, access is provided in compliance with copyrights, intellectual property rights and data agreements with our partners. Data products include Global Environmental Flow Information System, Global Drought Patterns, Global Irrigated Area Mapping, Flow Management Classes, and regional data on Irrigated Area (Asia and Africa), Glacier and Snow (Asia), Flood Risk Mapping (East Asia) (South East Asia), Flood Risk Mapping (Nigeria), Water Resources Management (Eastern Ganges), Climate Change vulnerability (Nepal), Water Quality Mapping (Sri Lanka), Kabul River Basin Geodatabase, Tana River Basin Information System. The Portal also links to the IWMI Irrigation Benchmarking Service, providing data on irrigation system performance (service delivery, financial, agricultural, environmental, gender) based on voluntary submissions from irrigation schemes across the world.

These datasets can be used to evaluate and benchmark the performance accuracy of Fault Detection and Diagnostics (FDD) algorithms or tools. It contains operational data from simulation, laboratory experiments, and field measurements from real buildings for seven HVAC systems/equipment (rooftop unit, single-duct air handler unit, dual-duct air handler unit, variable air volume box, fan coil unit, chiller plant, and boiler plant). Each dataset includes a .pdf file to document key information necessary to understand the content and scope, multiple csv files containing all the time-series data for faults at different severity levels and one fault-free case, and a ttl file to visualize the data according to BRICK schema. The dataset was created by LBNL, PNNL, NREL, ORNL and Drexel University.

The Real Estate Environmental Benchmark (REEB) is a publicly available operational benchmark of environmental performance for commercial property in the UK. It is one of the only benchmarks based on buildings ‘in-use’ performance. It is increasingly becoming the ‘industry standard’ used by investors, fund managers, and property owners to compare the performance of their assets with other similar assets from portfolios across the UK.

Wind turbine condition monitoring (CM) can potentially help the wind industry reduce turbine downtime and operation and maintenance (O&M) cost. NREL CM research has investigated various condition-monitoring techniques such as acoustic emission (AE specifically stress wave), vibration, electrical signature, lubricant and debris monitoring based on the Gearbox Reliability Collaborative dynamometer and field tests, and other test turbines and resources accessible by NREL. During the past several years, NREL CM research has shown that there are very few validation and verification efforts on commercial wind turbine CM systems. One of the reasons might be limited benchmarking datasets accessible by stakeholders. To fill this gap, NREL executed a data collection effort. The targeted users of these datasets include those investigating vibration-based wind turbine CM research, evaluating commercially available vibration-based CM systems, or testing prototyped vibration-based CM systems. NREL collected data from a healthy and a damaged gearbox of the same design tested by the GRC. Vibration data were collected by accelerometers along with high-speed shaft RPM signals during the dynamometer testing. The healthy gearbox was only tested in the dynamometer. The damaged gearbox was first tested in the dynamometer and later sent to a wind farm close to NREL for field testing. In the field test, it experienced two loss-of-oil events that damaged its internal bearings and gear elements. The gearbox was brought back to NREL and it was retested in the dynamometer with CM systems deployed under controlled loading conditions that would not cause catastrophic failure of the gearbox. The objective of releasing these datasets to the public along with information about the real damage that occurred to the damaged gearbox is to provide the wind industry with some benchmarking datasets. These datasets will benefit research, development, validation, verification, and advancement of vibration-based wind condition-monitoring techniques. By accessing this data you acknowledge the terms outlined in the "License Information" document. Please contract Shawn Sheng (NREL) if you have any questions on the data or would like to collaborate on publications based on the datasets.