Search NASA⌕ Search

SEARCH · Search NASA

Results for “natural”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Meta-analysis of biogas upgrading to renewable natural gas through biological CO 2 conversion

Biogas upgrading through CO 2 conversion by hydrogenotrophic methanogenesis is receiving an increasing attention worldwide because of the demand for renewable natural gas. Herein, a holistic and statistical study of the operation conditions, driving forces, performances, and potential implementation of biogas upgrading via biological CO 2 conversion was conducted. Based on a systematic review and meta-analysis of 46 existing publications that were selected from 1475 papers, we have compiled a global dataset of CO 2 bioconversion biogas upgrading, encompassing 308 study cases. Subsequently, we employed a rigorous analytical framework incorporating data processing and mixed effects linear regression analysis to examine the dataset. This analysis revealed a significant positive relationship between the H 2 :CO 2 ratio and the methane percentage in the upgraded biogas when using the study as a random effect. Furthermore, we performed meta-analysis on observations taken when the ratio was close to 4:1 and found that ex situ reactors (91.93% [88.11%, 95.75%]) can perform better than in situ reactors (84.74% [80.69%, 88.80%]). No evidence of differential performance was found based on the present dataset between different temperature regimes or operation modes. Furthermore, those findings establish a database that will contribute to a deeper understanding of the biogas upgrading via biological CO 2 conversion.

Biogas upgrading↗
DOE OSTI2023

Review of the adsorbents/catalysts for the removal of sulfur compounds from natural gas

Here this paper aims to provide a compilation of studies on adsorptive removal of H2S and organic sulfur compounds from natural gas at relatively low temperatures and pressures. The manuscript compares sulfur uptakes among different materials, including zeolites, activated carbons, metallic organic frameworks (MOFs), and metal oxides, and the impact of modifications to these materials. Best sulfur uptakes were achieved by adding metallic or nitrogen species to the adsorbent surfaces. This contribution to the peer-reviewed literature could provide a better understanding of the improvements necessary to achieve greater sulfur capacities and the mechanisms of sulfur interactions with adsorbents' surfaces.

03 NATURAL GAS↗
DOE OSTI2022

Variation in natural attenuation rates of polychlorinated biphenyls (PCBs) in fish from streams and reservoirs in East Tennessee observed over a 35-year period

Environmental contamination due to human activities is a major concern, particularly for persistent chemicals. Within catchments, persistent chemicals linked to negative health outcomes such as polychlorinated biphenyls (PCBs) have great potential to be transported, through adsorption or biological uptake, with downstream locations acting as sinks for accumulation. Here we present long-term trends in PCB bioaccumulation in fish found in lower-order tributaries on the Oak Ridge Reservation, an impacted US Department of Energy property in East Tennessee, USA, and a large reservoir system adjacent to it composed of parts of the Clinch and Tennessee Rivers. Given that the reservoir system has experienced no direct PCB mitigation activities, this record offers an opportunity to explore potential natural attenuation of PCBs within a large lotic ecosystem. Additionally, attenuation rates ranged from 0% to 8% yr -1 in minnows and sunfish at stream sites and 5.4–11.3% yr -1 in catfish at reservoir sites. These rates are comparable to findings from similar studies in other regions, suggesting a consistency in responses since the banning of PCB production in 1979. Further, results suggest that PCB sources from discharge outfalls are important locally but are not primarily responsible for sustaining PCB contamination in downstream reservoirs.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Relative effect of anthropogenic warming and natural climate variability to changes in Compound drought and heatwaves

Compound drought and heatwave (CDHW) events can be influenced by large scale teleconnections and anthropogenic warming, leading to severe socio-economic impacts across various climate regions. Here, the relative influence of six different teleconnection patterns and anthropogenic global warming on the global CDHW occurrences is quantified systematically using the instrumental data period, 1982–2016. The results from the study suggest a substantial increase in the CDHW events (1–5 events per year) across various parts of the globe at the beginning of 21st century (2000–2016). A Bayesian approach is implemented to identify the most vulnerable climate regions based on the degree of susceptibility of heatwaves (DSHW) towards drought. As such, top ten most vulnerable regions are selected based on the DSHW magnitude, and a partial correlation analysis is performed to select the natural and anthropogenic drivers of CDHW in those regions, separately. A logistic regression model is then used to determine significant changes in the odds of CDHW due to changes in the selected drivers that suggest a significantly positive, and multiplicative effect of anthropogenic global warming in the top ten most vulnerable climate regions. Finally, the same logistic regression model, integrated with an analytical framework, is applied to determine the relative influence of anthropogenic global warming on the changes in odds of CDHW for the future, 1.5 °C and 2 °C warming limits. Finally, the results suggest that relative to the 2 °C global warming, constraining to the 1.5 °C global warming limit may conduce about 17-fold reduction in the odds of CDHW in the most vulnerable climate region, East Asia, 5–8-fold reduction in Western North America, Northern Australia, Central North America, Central Europe, South Asia, and the Mediterranean region, and 3–4-fold reduction in Northeastern Brazil, Eastern North America, and West Asia.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Natural fiber-derived gas diffusion layers for high performance, lower cost PEM fuel cells

The gas diffusion layer (GDL) is a critical component of proton exchange membrane fuel cells. GDL manufacture is dominated by the use of polyacrylonitrile (PAN) fibers, resulting in high production costs. Those costs contribute to the high cost of fuel cell stacks. Thus, reducing GDL manufacturing costs without sacrificing performance, should help reduce the overall cost of the fuel cell stack. Using inexpensive, natural fiber-based papers and fabric as substrates, here we examine the inherent performance these materials as GDLs, and the improvements enabled by the addition of a microporous layer, gas-phase hydrophobic treatment, and densification. The resulting GDLs achieve equivalent performance the commercial baseline GDL and demonstrate the potential of lower cost GDLs.

25 ENERGY STORAGE↗
DOE OSTI2022

Direct, efficient and selective capture of low concentration of CO 2 from natural gas flue gas using a high temperature tubular carbon capture membrane

Natural gas (NG) fired power plants emit low concentration (4–5%) of CO 2 , which presents additional technical and economic challenges to the current benchmark amine absorption technology. The newly emerged high-temperature multiphase membranes operated on molten carbonate (MC) chemistry for CO 2 capture/separation/conversion have been demonstrated with great potential to meet this challenge. In this study, we report on the CO 2 capture performance of such a membrane in tubular geometry from a mockup NG flue gas. The membrane is comprised of a mixture of Gd 0.20 Ce 0.80 O 1.95 (GDC) and MC, in which GDC forms a porous skeleton to contain MC. Here, we show that the membrane with a dimension of 6.1 mm in outer diameter, 5.1 mm in inner diameter and 5 cm in effective length (resulting in 4cm 2 effective surface area) can achieve a CO 2 flux density of 0.46–0.55 mL/min·cm 2 at 650°C, capturing 97% pure CO 2 at a rate of 37–42% from 5%CO 2 –N 2 using moistened Ar as the sweep gas. The level of performance demonstrated by this study suites the membrane well for stationary CO 2 capture from NG power plants.

03 NATURAL GAS↗
DOE OSTI2021

Conversion of the LLNL/CAMS 1 MV biomedical AMS system to a semi-automated natural abundance 14C spectrometer: system optimization and performance evaluation

The Lawrence Livermore National Laboratory – Center for Accelerator Mass Spectrometry compact 1 MV biomedical accelerator mass spectrometer was repurposed and optimized for the semi-automated radiocarbon measurement of natural abundance environmental samples. Here we present results from 15 months of routine system operation and evaluate the system performance based on 30 sample wheels measured with consistent operating conditions over 7 months from August 2019 to March 2020. Additionally, the average measurement precision was 2.7 ± 0.7‰. System accuracy was assessed with measurements of 14 C-free materials, standard materials with 14 C-content spanning 0.5 to 1.5 F 14 C, and by comparison to split samples measured with the 10 MV AMS system. Overall, this system can routinely measure samples as small as 300 µgC and less than 33000 years without the need for size-specific correction protocols.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Hydraulic performance and wave transmission through nature-inspired perforated hollow-base piles breakwater

Nature-based Solutions (NbS) are critical to achieving long-term sustainable coastlines in deltaic coastlines, particularly susceptible to severe impacts under climate change. In recent years, coastal erosion has accelerated in the Vietnam Mekong Delta (VMD), particularly in the West Sea (from Ca Mau to Kien Giang). Due to the characteristics of muddy coastlines and eroded mangrove forests in this region, only a few engineering solutions have effectively reduced waves and promoted sediment accumulation to facilitate beach accretion. However, these solutions require significant investment and cannot be relocated or reused. Therefore, this study introduces a coastal mangrove-inspired perforated hollow-base piles breakwater (PHBPB), which uses the principle of biomimicry by studying the ability of mangrove groups to protect the coastline, stimulate sediment deposition, and over time, restore mangrove forests in the VMD. The hydraulic parameters of PHBPB were tested in 260 scenarios using a physical model, which included varying parameters such as crest width (B), pile row numbers (n c ), crest freeboard (R c ), and wave parameters (H s , T p ) in determining the capabilities of wave transmission, reflection, and wave dissipation. The results showed that the process of wave energy dissipation through perforated hollow-base breakwaters without piles (PHBBWP) is governed by three main parameters, including the relative water depth of the crest (R c /H m0,i ), the relative width of the crest (B/H m0,i ), and the wave slope at the structure location (s m = H m0,i /L m ). In contrast, for PHBPB, the primary influencing factors are the relative submergence depth or the length of the submerged pile portion (R c /H m0,i ) and the relative width of the pile system (X b /L m ). Finally, the hollow structure is suitable for the soft, weak mud geology in this region with poor load-bearing capacity, allows for rapid installation, is reasonably cost-effective, and can be relocated and reused once regeneration has been completed in each stretch of coastline.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Investigation of the end-gas autoignition process in natural gas engines and evaluation of the methane number index

Engine knock and misfire are barriers to pathways leading to high-efficiency Spark-Ignited (SI) Natural Gas (NG) engines. The general tendency to knock is highly dependent on engine operating conditions and the fuel reactivity. The problem is further complicated by the wide range of chemical reactivity in pipeline quality NG, represented by the Methane Number (MN) (65< MN<95). Understanding the underlying phenomena responsible for engine knock can support the development of predictive tools capable of identifying knock onset/intensity as well as a fuel’s propensity to knock, allowing engine manufacturers to expand the knock envelope and design more efficient/robust SI NG engines. Additionally, there is an opportunity for increased efficiency by controlling levels of end-gas autoignition if this can be predicted and controlled. This work focuses on the development of a novel methodology to understand/predict a fuel’s propensity to knock. This methodology is based on the charge fraction undergoing autoignition, namely fractional end-gas autoignition (F-EGAI), and was developed based on first order laminar flame speeds and ignition delay analysis combined with a 0-D homogeneous batch reactor model. This methodology proved to be suitable to predict a fuel’s propensity to knock, even under conditions when light knock was observed. The simple modeling approach was used to explain the results from a series of MN tests with multiple NG compositions exhibiting a wide range of reactivity compositions and providing insight on why fuels of very different chemical compositions can have the same MN. Finally, a CFD model was developed was used to confirm the methodology capability and provide further insights in the physical and chemical phenomena behind end gas autoignition.

42 ENGINEERING↗
DOE OSTI2022

Influence of NOx chemistry on the prediction of natural gas end-gas autoignition in CFD engine simulations

Natural gas (NG) represents a promising low-cost/low-emission alternative to diesel fuel when used in high-efficiency internal combustion engines. Advanced combustion strategies utilizing high EGR rates and controlled end-gas autoignition can be implemented with NG to achieve diesel-like efficiencies; however, to support the design of these next-generation NG ICEs, computational tools, including single- and multi-dimensional simulation packages will need to account for the complex chemistry that can occur between the reactive species found in EGR (including NOx) and the fuel. Research has shown that NOx plays an important role in the promotion/inhibition of large hydrocarbon autoignition and when accounted for in CFD engine simulations, can significantly improve the prediction of end-gas autoignition for these fuels. However, reduced NOx-enabled NG mechanisms for use in CFD engine simulations are lacking, and as a result, the influence of NOx chemistry on NG engine operation remains unknown. Here, we analyze the effects of NOx chemistry on the prediction of NG/oxidizer/EGR autoignition and generate a reduced mechanism of a suitable size to be used in engine simulations. Results indicate that NG ignition is sensitive to NOx chemistry, where it was observed that the addition of EGR, which included NOx, promoted NG autoignition. The modified mechanism captured well all trends and closely matched experimentally measured ignition delay times for a wide range of EGR rates and NG compositions. Here, the importance of C2-C3 chemistry is noted, especially for wet NG compositions containing high fractions of ethane and propane. Finally, when utilized in CFD simulations of a Cooperative Fuels Research (CFR) engine, the new reduced mechanism was able to predict the knock onset crank angle (KOCA) to within one crank angle degree of experimental data, a significant improvement compared to previous simulations without NOx chemistry.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2020

Separation characteristics of cations and natural organic matter in electrodialysis

Natural organic matter (NOM) in water can cause the formation of disinfection byproducts (DBPs) when NOM reacts with a disinfectant such as chlorine. Nanofiltration (NF) and reverse osmosis (RO) are effective treatment methods to remove NOM. However, the simultaneous presence of both NOM and divalent cations such as Ca 2+ can enhance fouling in NF and RO. Therefore, an appropriate pretreatment to remove such cations before NF or RO would delay fouling and perhaps improve water recovery and NOM removal efficiency. Electrodialysis (ED) is potentially an excellent pretreatment method because it separates inorganic ions well using ion exchange membranes (IEMs) but does not separate NOM well because of its size and consequent low diffusivity. This research focused on ion and NOM separation with ED using three different types of commercially available IEM pairs, two different commercially available NOM sources, and six different influents at 500 mg/L total dissolved solids in the presence or absence of both hardness (Ca 2+ and Mg 2+ ) and NOM. The target waters of interest in this research were drinking water supplies that require little or no desalination but substantial removal of NOM; after NOM separation in NF or RO, some or all of the ED concentrate can be added to the NF/RO permeate to create the finished water prior to disinfection. The results indicate that ED can effectively separate alkaline earth metal ions without separation of NOM. Cation exchange membranes with high exchange capacity, high selectivity for divalent cations are desirable, and both anion and cation exchange membranes should have low affinity for organic adsorption. As a result, the process would work particularly well for NOM with relatively low hydrophobicity, since NOM adsorption to most surfaces increases with hydrophobicity.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Structure and composition of natural ferrihydrite nano-colloids in anoxic groundwater

Fe-rich mobile colloids play vital yet poorly understood roles in the biogeochemical cycling of Fe in groundwater by influencing organic matter (OM) preservation and fluxes of Fe, OM, and other essential (micro-)nutrients. Yet, few studies have provided molecular detail on the structures and compositions of Fe-rich mobile colloids and factors controlling their persistence in natural groundwater. Here, we provide comprehensive new information on the sizes, molecular structures, and compositions of Fe-rich mobile colloids that accounted for up to 72% of aqueous Fe in anoxic groundwater from a redox-active floodplain. The mobile colloids are multi-phase assemblages consisting of Si-coated ferrihydrite nanoparticles and Fe(II)-OM complexes. Ferrihydrite nanoparticles persisted under both oxic and anoxic/sulfidic conditions, which we attribute to passivation by Si and OM. These findings suggest that mobile Fe-rich colloids generated in floodplains can persist during transport through redox-variable soils and could be discharged to surface waters. These results shed new light on their potential to transport Fe, OM, and nutrients across terrestrial-aquatic interfaces.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Effect of Natural Organic Matter on the Fate of Cadmium During Microbial Ferrihydrite Reduction

Natural organic matter (NOM) is known to affect the microbial reduction and transformation of ferrihydrite, but its implication toward cadmium (Cd) associated with ferrihydrite is not well-known. In this work, we investigated how Cd is redistributed when ferrihydrite undergoes microbial reduction in the presence of NOM. Incubation with Geobacter sulfurreducens showed that both the rate and the extent of reduction of Cd-loaded ferrihydrite were enhanced by increasing concentrations of NOM (i.e., C/Fe ratio). Furthermore, without NOM, only 3–4% of Fe(III) was reduced, but around 61% of preadsorbed Cd was released into solution due to ferrihydrite transformation to lepidocrocite. At high C/Fe ratio (1.6), more than 35% of Fe(III) was reduced, as NOM can facilitate bioreduction by working as an electron shuttle and decreased aggregate size, but only a negligible amount of Cd was released into solution, thus decreasing Cd toxicity and prolonging microbial Fe(III) reduction. No ferrihydrite transformation was observed at high C/Fe ratios using Mössbauer spectroscopy and X-ray diffraction, and X-ray absorption spectroscopy indicated the proportion of Cd-OM bond increased after microbial reduction. This study shows that the presence of NOM leads to less mobilization of Cd under reducing condition possibly by inhibiting ferrihydrite transformation and recapturing Cd through Cd-OM bond.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Composition, Emissions, and Air Quality Impacts of Hazardous Air Pollutants in Unburned Natural Gas from Residential Stoves in California

The presence of hazardous air pollutants (HAPs) entrained in end-use natural gas (NG) is an understudied source of human health risks. We performed trace gas analyses on 185 unburned NG samples collected from 159 unique residential NG stoves across seven geographic regions in California. Our analyses commonly detected 12 HAPs with significant variability across region and gas utility. Mean regional benzene, toluene, ethylbenzene, and total xylenes (BTEX) concentrations in end-use NG ranged from 1.6–25 ppmv–benzene alone was detected in 99% of samples, and mean concentrations ranged from 0.7–12 ppmv (max: 66 ppmv). By applying previously reported NG and methane emission rates throughout California’s transmission, storage, and distribution systems, we estimated statewide benzene emissions of 4,200 (95% CI: 1,800–9,700) kg yr –1 that are currently not included in any statewide inventories–equal to the annual benzene emissions from nearly 60,000 light-duty gasoline vehicles. Additionally, we found that NG leakage from stoves and ovens while not in use can result in indoor benzene concentrations that can exceed the California Office of Environmental Health Hazard Assessment 8-h Reference Exposure Level of 0.94 ppbv–benzene concentrations comparable to environmental tobacco smoke. This study supports the need to further improve our understanding of leaked downstream NG as a source of health risk.

42 ENGINEERING↗
DOE OSTI2019

Beyond-the-Meter: Unaccounted Sources of Methane Emissions in the Natural Gas Distribution Sector

The United States Environmental Protection Agency maintains an inventory of greenhouse gas emissions in accordance with the Intergovernmental Panel on Climate Change. Methane (CH 4 ), a potent gas with a global warming potential 86–125× that of carbon dioxide (CO 2 ) over a twenty-year period, is the main component of natural gas (NG). As NG becomes an increasingly larger percentage of the energy resources used in the United States, it is ever more important to evaluate the CH 4 emissions inventory. However, the inventory also does not account for all possible sources of CH 4 leaks, contributing to uncertainty in the national CH 4 inventory. Discrepancies between top-down and bottom-up inventories of CH 4 emissions imply that there are significant unaccounted-for sources of CH 4 leaks, especially over cities. Diffuse CH 4 plumes above cities that are not attributable to distribution pipelines or other NG infrastructure suggest many small beyond-the-meter leaks together contribute to large emissions. Here, we evaluate the distribution sector of the CH 4 emissions inventory and make suggestions to improve the inventory by analyzing end-user emissions. Preliminary research into beyond-the-meter emissions suggests that while individually small, the appliances and buildings that make up the residential sector could contribute significantly to national scale emissions. Furnaces are the most leak-prone of appliances, contributing to 0.14% of total CH 4 emissions from the NG sector in the United States. Combining measurements from whole house emissions and steady-state operation of appliances, we estimate that residential homes and appliances could release 9.1 Gg CH 4 yearly in the United States, totaling over 2% of the CH 4 released from the NG sector. Here, while factors such as appliance age and usage, climate, and residential setting could influence the emissions profile of individual appliances, these preliminary estimates justify further exploration of beyond-the-meter emissions.

03 NATURAL GAS↗
DOE OSTI2024

Protein–Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools

The study of protein-protein interactions (PPIs) provides insight into various biological mechanisms, including the binding of antibodies to antigens, enzymes to inhibitors or promoters, and receptors to ligands. Recent studies of PPIs have led to significant biological breakthroughs. For example, the study of PPIs involved in the human:SARS-CoV-2 viral infection mechanism aided in the development of the SARS-CoV-2 vaccines. Though several databases exist for the manual curation of PPI networks, text mining methods have been routinely demonstrated as useful alternatives for newly studied or understudied species where databases are incomplete. Here, the relationship extraction (RE) performance of several open-source classical text processing, machine learning (ML)-based natural language processing (NLP), and large language model (LLM)-based NLP tools were compared. Overall, our results indicated that networks derived from classical methods tend to have high true positive rates at the expense of having overconnected-networks, ML-based NLP methods have lower true positive rates but networks with the closest structures to the target network, and LLM-based NLP methods tend to exist in-between the two other approaches, with variable performances. Finally, the selection of a specific NLP approach should be tied to the needs of a study and text availability, as models varied in performance due to the amount of text provided.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Structure and Sulfur: Tuning the Viscoelastic and Surface Properties of Natural Keratin Fibers

Natural keratin fibers, such as wool, possess a complex hierarchical structure that governs their mechanical properties and surface energy. However, the extent to which these characteristics are influenced by combined contributions of structural variations (e.g., fiber diameter, intermediate filament (IF) packing) and chemical composition (e.g., disulfide bond density) remains poorly understood. In this study, we investigate wool fibers from five sheep breeds (Merino, Polwarth, Cheviot, Eider, and Devon) to elucidate how these factors influence viscoelasticity and surface interactions. Using a multimodal approach integrating interfacial and bulk characterization methods, including inverse gas chromatography (IGC), atomic force microscopy-infrared spectroscopy (AFM-IR), X-ray photoelectron spectroscopy (XPS), uniaxial tensile testing, and synchrotron small-angle X-ray scattering (SAXS), we show that the nanometer-thick 18-methyleicosanoic acid (18-MEA) layer is consistently present across all wool types and plays a key role in governing hydrophobicity and surface heterogeneity. A controlled isothermal treatment at 200 °C, designed to cleave disulfide bonds, results in a nearly 40% reduction in specific surface area across all fiber types, accompanied by a significant decrease in tensile strength and 80% reduction in elongation at break for Merino and Devon wool, but limited influence on the mechanical properties of Eider fibers. Furthermore, rate-dependent tensile testing within the elastic regime reveals distinct viscoelastic responses among the fiber types, suggesting that the sulfur-rich protein matrix surrounding IFs and its structure contribute actively to stress partitioning. Altogether, when combined with conclusions from SAXS measurements of IF spacing, our work offers compelling insights into the role of the keratin-associated protein (KAP) matrix in shaping wool fiber mechanics. Differences in mechanical behavior among wool types, despite similar IF spacing or sulfur content, highlight the importance of matrix composition and cross-linking density, suggesting that the molecular architecture of the KAP network may be a dominant factor in determining fiber performance.

X-ray scattering↗
DOE OSTI2025

Leveraging Natural Language Processing and Generative Models in Molecular Chemistry: Property Prediction and Novel Compound Generation

The accurate prediction of molecular properties is important for the rational design and the advancement of green chemistry and sustainable materials research. However, the predictive power of traditional computational chemistry methods is limited due to computational restrictions. Here, in this study, we examine an alternative approach to the accurate prediction of properties of organic compounds: natural language processing (NLP)-based molecular embedding. Using viscosity, partition coefficient (log P), and enthalpy of vaporization as test properties through a survey of comprehensive datasets comprising 5695 data points for viscosity, 25 870 data points for log P, and 2296 data points for enthalpy of vaporization. These are important properties for the design of greener, safer, and sustainable chemical processes. Models were trained using NLP methods such as Mol2vec and fine-tuned ChemBERTa, and results were compared with traditional input featurization techniques such as Morgan fingerprints and quantum chemistry derived sigma profiles and DFT features. Among the various machine learning models, Mol2vec demonstrated superior predictive capabilities, achieving the highest correlation coefficient (R 2 = 0.945) and lowest RMSE (0.106 mPa s) for viscosity, as well as high accuracy for log P and enthalpy of vaporization predictions. These findings establish the Mol2vec featurization technique, graph-convolutional neural networks (GCNN), and fine-tuned ChemBERTa model as powerful tools for predictive modeling of organic compounds properties, offering a significant improvement over previously used featurization techniques and opening up strategies for very-high-throughput computational screening. Finally, we integrated ML models with hybrid language-model-based generative adversarial networks (LM-GAN) to generate novel molecular sequences with desirable properties for different research applications. The ability to computationally design solvents with lower viscosity, lower log P, and lower enthalpy of vaporization offers a data-driven route to accelerating the discovery of sustainable alternatives to traditionally toxic solvents.

ChemBERTa↗