Semi-Batch Reactor Selectivity Optimization Simulation Dataset

#Reinforcement learning policy training #Scientific reasoning #Reaction outcome prediction #Selectivity optimization #Semi-batch reactor simulation #Reaction process optimization #Product quality analysis #Laboratory process equipment

4805
0.3GB
JSON
CATL
MOBIUSI INC

Updated:2026-11-03

AI Analysis & Value Prop

This dataset records action parameters from semi-batch reactor simulations, including feed rate, feed composition, temperature, and reaction time, alongside time-varying trajectories for feeds, reactants, target products, and byproducts. It also provides yield, selectivity, side-reaction change, trajectory summary, and product quality metrics for analyzing how material addition strategies and competing reactions affect product distributions. The data supports reaction process modeling, reinforcement learning strategy training, and scientific reasoning evaluation.

Dataset Insights

Sample Examples

{}

Technical Specifications

Field	Type	Description
file_name	string	File name
yield_percent	number	Yield calculated from the final amount of target product relative to the theoretical product amount, expressed as a percentage.
product_quality	object	Final product quality metrics calculated from the composition of target products and byproducts.
action_parameters	object	Action inputs applied during simulation, such as feed rate, feed composition, temperature, and reaction time.
trajectory_summary	object	Derived metrics extracted from the simulation trajectory, such as initial, final, and peak values.
selectivity_percent	number	Proportion of the target product among total products, used to measure the effect of competing reactions on product distribution, expressed as a percentage.
simulation_trajectory	array	Records time-varying states of feeds, temperature, reactants, target products, and byproducts during the reaction.
side_reaction_change_percent	number	Change in byproduct concentration relative to its initial reaction state, expressed as a percentage.

Compliance Statement

Authorization Type	Proprietary - Commercial AI Training License (No Redistribution)
Commercial Use	Requires exclusive subscription or authorization contract (monthly or per-invocation charging)
Privacy and Anonymization	No PII, no real company names, simulated scenarios follow industry standards
Compliance System	Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs

Frequently Asked Questions

What reaction process information does the dataset include?: It includes action parameters such as feed rate, feed composition, temperature, and reaction time, as well as time-varying trajectories for feeds, reactants, target products, and byproducts. Additional fields provide yield, selectivity, side-reaction change, trajectory summaries, and product quality metrics.

Are these data from real experiments or simulations?: The data describes semi-batch reactor simulations and should not be treated as direct measurements from physical experiments. Before using it to make process decisions or design experiments, validate the results against experimental data for the specific reaction system.

Which training and evaluation tasks can this dataset support?: It can support simulation-based reinforcement learning policy training, reaction outcome prediction, analysis of relationships between action parameters and product quality, and evaluation of scientific reasoning and selectivity optimization methods.

How can I obtain the data and verify its license?: Use the download or delivery method provided on the product page, and review the listed license scope, permitted uses, and redistribution restrictions before use. No specific license terms are stated in the available description.

Can't find the data you need?

Post a request and let data providers reach out to you.

Get this Dataset

Verified for Enterprise Use

Cite this Work

@dataset{Mobiusi2026,
  title={Semi-Batch Reactor Selectivity Optimization Simulation Dataset},
  author={MOBIUSI INC},
  year={2026},
  url={https://www.mobiusi.com/datasets/3f1efdaafd9b747b7edb4d683d75f32c?dataset_task_cate_id=8},
  urldate={2026-10-27},
  keywords={semi-batch reactor dataset,reactor simulation data,selectivity optimization,reaction process reinforcement learning,chemical reaction trajectories,yield prediction,side reaction analysis,product quality assessment},
  version={1.0}
}

Using this in research? Please cite us.

placeholder

Scene

Domain

Modality

Task