Solvent Screening for Separation Processes Using Machine Learning and High-Throughput Technologies

Aug 5, 2026

As the chemical industry shifts toward sustainable practices, solvent development increasingly aims to replace fossil-derived solvents with environmentally friendlier options such as ionic liquids (ILs) and deep eutectic solvents (DESs). Artificial intelligence supports discovery and design by enabling physicochemical property prediction and separation process design. This review surveys advances in AI-assisted solvent screening, emphasizing machine learning models and automated high-throughput platforms, and evaluates challenges and future prospects for ML-driven high-throughput strategies in green solvent optimization.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Solvent extraction and separation process role

Conventional solvents and sustainability drivers

Emerging green alternatives: ILs and DESs

Need for faster screening and ML/HT integration

Lawrence Berkeley National Laboratory LBL Publications Title Solvent Screening for Separation Processes Using Machine Learning and High-Throughput Technologies Permalink [https://escholarship.org/uc/item/5v72z23f](https://escholarship.org/uc/item/5v72z23f) Journal Chem & Bio Engineering, 2(4) ISSN 2836-967X Authors Edaugal, Justin P Zhang, Difan Liu, Dupenget al. Publication Date 2025-04-24 DOI 10.1021/cbe.4c00170 Copyright Information This work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/) Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California ACS Partner Journal This article is licensed under CC-BY-NC-ND 4.0 [pubs.acs.org/ChemBioEng](pubs.acs.org/ChemBioEng) Review Solvent Screening for Separation Processes Using Machine Learning and High-Throughput Technologies Justin P. Edaugal, Difan Zhang, * Dupeng Liu, * Vassiliki-Alexandra Glezakou, and Ning Sun* Cite This: Chem Bio Eng. 2025, 2, 210−228 Read Online | | | | | | --- | --- | --- | --- | | ACCESS | Metrics & More | | Article Recommendations | ABSTRACT: As the chemical industry shifts toward sustainable practices, there is a growing initiative to replace conventional fossil-derived solvents with environmentally friendly alternatives such as ionic liquids (ILs) and deep eutectic solvents (DESs). Artificial intelligence (AI) plays a key role in the discovery and design of novel solvents and the development of green processes. This review explores the latest advancements in AI-assisted solvent screening with a specific focus on machine learning (ML) models for physicochemical property prediction and separation process design. Additionally, this paper highlights recent progress in the development of automated high-throughput (HT) platforms for solvent screening. Finally, this paper discusses the challenges and prospects of ML-driven HT strategies for green solvent design and optimization. To this end, this review provides key insights to advance solvent screening strategies for future chemical and separation processes. KEYWORDS: Ionic liquids, Deep eutectic solvents, Artificial intelligence, Machine learning, Solvent extraction, High-throughput screening 1. INTRODUCTION Separation processes play an integral role in the production of a diverse range of products across the oil and gas, food, pharmaceutical, and chemical industries. Traditionally, these processes utilize large-scale physical and thermal treatments, such as centrifugation, filtration, and distillation, for the removal of various impurities and byproducts. However, such processes are energetically approximately 10−15% intensive and costly, accounting for of global energy consumption. 1 Solvent extraction, otherwise known as liquid−liquid extraction (LLE), is a well-established operation for the effective separation of a wide range of synthetic and bio-based compounds from liquid mixtures. By leveraging the differential affinity of target compounds across immiscible liquid phases, solvent extraction can achieve separation with a high extraction efficiency and selectivity. Additionally, solvent extraction offers a simpler process setup and reduced energy costs, positioning it as an attractive strategy for industrial-scale application. Despite these advantages, the efficiency of an extraction process significantly hinges on the selection of the appropriate solvent. The optimal extractant solvent should exhibit a high distribution coefficient, low mutual solubility, low toxicity, high chemical stability, and low cost.2 Most industrial extraction processes rely on conventional organic solvents, owing to their aqueous immiscibility and relatively low bulk costs. However, the environmental concerns regarding their nonrenewable, fossil-fuel

FAQs

Why is solvent screening important for separation processes?

Separation performance depends strongly on selecting an appropriate solvent, including distribution coefficient, mutual solubility, toxicity, stability, and cost.

What green solvent alternatives are highlighted in the review?

The review focuses on ionic liquids (ILs) and deep eutectic solvents (DESs), described as tunable and potentially lower-volatility or lower-toxicity alternatives.

How do machine learning and high-throughput technologies work together in this context?

Machine learning models support physicochemical property prediction and separation process design, while automated high-throughput platforms enable efficient solvent screening at scale.

Aug 5, 2026

Upload by River Wang