Optimization of hydrothermal liquefaction process through machine learning approach: process conditions and oil yield

Gopirajan, P. V.; Gopinath, Kannappan Panchamoorthy; Sivaranjani, G.; Arun, Jayaseelan

doi:10.1007/s13399-020-01233-8

Cited by 30 publications

(11 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of treatment part of organic waste, in the advanced study, the hydrogen gas extracted from the HTL "Hydrothermal liquefaction" was 21% which could be a helpful technology for university campuses [24]. Another valuable strategy is The Decision Support System (DSS) through a Machine Learningbased Artificial Intelligence platform that optimises the hydrothermal liquefaction process of various biomass resources in a decentralised system [25]. The SLCC-Social Life Cycle Costs; IC-Investment costs; OC-Operational costs; EC-Environmental costs.…”

Section: Attempt To Make Zero Waste Automated Campusmentioning

confidence: 99%

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Kumar

Agrawal

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Solid Waste Management (SWM) is a challenging issue to be addressed in most of the urban centres in India. Heavy population densities and exponential growth of the cities’ boundaries, due to migration, create kiosks to the cities’ resources such as land and other amenities. In such cities, the unsegregated waste gets generated in huge quantities while the rest are dumped in landfill sites without any specific treatment. Centralised and holistic approaches are missing, as most of the waste-to-energy & waste treatment plants are either getting closed or not working to its fullest efficiency. The strategies for a decentralised collection system, segregation and treatment of waste are not usually standard practices. In spite of the global impacts being pretty visible due to global warming, a massive amount of plastic gets dumped into ocean, which reaches the human beings via food chain and results in the most number of incurable diseases like cancer. Further, it also results in rapid extinction of the indigenous species. Campuses are known as mini-city or autonomous urban centres for knowledge sharing and the development of innovations. The time is here to make the Indian campuses smatter in collecting and treating the waste on their premises. Hence, the pneumatic collection process of the garbage can play an essential role in making the campus, an advanced and a sustainable one. Thus, there is an urgent need to develop a compact and a decentralised strategy to manage the waste in various urban centres. Also, a formalised informal sector of waste could be contributing to further recycling and processing of the garbage on the campus. The aim of the current research investigation is to identify various possibilities for making the campus, a smart one, in terms of waste management. Furthermore, the study also intends to find out how the compact, decentralised waste collection methods in urban can manage their solid waste in the limited available space. Making zero-waste campuses is a herculean task and a massive challenge must be dealt with immediately to help the cities achieve long-term sustainability.

show abstract

Section: Attempt To Make Zero Waste Automated Campusmentioning

confidence: 99%

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Kumar

Agrawal

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Nowadays, data-driven approaches, especially machine learning (ML) algorithms, have been proven to be powerful to assist the design and understanding of waste-to-energy systems. − Additionally, a few studies have been reported on the ML applications in the AD process. , For example, Xu et al found that the extreme gradient boosting (XGBoost) model was the best for predicting CH 4 production, and total solid, soluble chemical oxygen demand (SCOD), and dosages of zero-valent iron (ZVI) are key factors affecting the CH 4 yield from ZVI-based AD . Long et al’s study showed that the ML model obtained a prediction accuracy of 0.82 by considering both operational parameters and genomic data based on 50 samples .…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Based In-Depth Interpretation and Inverse Design of Anaerobic Digestion for CH₄-Rich Biogas Production

Zhang

et al. 2022

ACS EST Eng.

View full text Add to dashboard Cite

Anaerobic digestion (AD) is one of the most widely used bioconversion technologies for renewable energy production from wet biowaste. However, such an AD system is so complicated that it is challenging to fully comprehend this process and design the operational conditions for a specific biowaste to achieve CH4-rich biogas. In this context, ensemble machine learning (ML) algorithms were employed to develop multitask models for jointly predicting the CH4 yield and content in biogas and understanding this complicated process. Based on the best ensemble model with the R 2 values of 0.82 and 0.86 for the multitask prediction of CH4 yield and content, the top three critical factors for CH4 yield/contents were identified and their interactions with process acid generation and microbial community in the AD process were comprehensively interpreted to unveil their importance on CH4 generation. Moreover, the well-developed ensemble model was integrated with an optimization algorithm to inversely design the AD process for a real-world food waste, in which the CH4 yield was as high as 468.7 mL/gVS and the calculation results were experimentally validated with relative errors of 9–16%. This work provides a creative approach to gain insights and inverse design for AD reactors, which is helpful to waste-to-energy technologists and practitioners.

show abstract

“…In the case of HTP, ML algorithms are being used to predict materials properties, production yields, and reaction mechanisms, as well as to identify optimal process parameters, and suitability of feedstock to produce biocrude oils. 16 , 17 The advances enabled by AI and ML are especially relevant for finding optimal processing conditions and for eventually scaled-up HTP processes (see Figure 7 ). However, the complex reactions that take place in HTP and the different partitioning of chemical species between solid and liquid phases during the process make mechanistic modeling extremely challenging, and challenges remain ahead.…”

Section: The Role Of Multiscale Modeling Ai and ML On Biomass Valoriz...mentioning

confidence: 99%

“…Research, development, and investment is needed to achieve deeper understanding of composition-process-structure-property relationships in biomass carbon mining, and more importantly to scale up biorefinery processes that allow us to efficiently utilize renewable resources 15 for the production of fit-for-purpose biobased materials. To assist with this composition-process-structure-property relationships, ML algorithms are being used to identify optimal hydrothermal processing (HTP) conditions, 16 , 17 although the complexity of HTP reactions and the different partitioning of chemical species between solid and liquid phases during the process make mechanistic modeling extremely challenging. 18 Despite the challenges ahead, the advantages of incorporating computational modeling into biomass-for-HTP or biobased-from-HTP materials, as well as the new opportunities arising from the integration of AI/ML into the material design and the biomass data analysis, are out of question.…”

Section: Introductionmentioning

confidence: 99%

Biomass carbon mining to develop nature-inspired materials for a circular economy

Bachs-Herrera¹,

York²,

Stephens-Jones³

et al. 2023

iScience

View full text Add to dashboard Cite

Optimization of hydrothermal liquefaction process through machine learning approach: process conditions and oil yield

Cited by 30 publications

References 68 publications

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Data-Driven Based In-Depth Interpretation and Inverse Design of Anaerobic Digestion for CH₄-Rich Biogas Production

Biomass carbon mining to develop nature-inspired materials for a circular economy

Contact Info

Product

Resources

About

Optimization of hydrothermal liquefaction process through machine learning approach: process conditions and oil yield

Cited by 30 publications

References 68 publications

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Pneumatic waste collection system - A proposed innovation for Indian Institute of Technology, Roorkee Campus, India

Data-Driven Based In-Depth Interpretation and Inverse Design of Anaerobic Digestion for CH4-Rich Biogas Production

Biomass carbon mining to develop nature-inspired materials for a circular economy

Contact Info

Product

Resources

About

Data-Driven Based In-Depth Interpretation and Inverse Design of Anaerobic Digestion for CH₄-Rich Biogas Production