This paper builds on exploring the applications of biomediated pathways to solve geotechnical challenges.First,the state of the art of biological remediation strategies including microbial remediation and phytoremedia...This paper builds on exploring the applications of biomediated pathways to solve geotechnical challenges.First,the state of the art of biological remediation strategies including microbial remediation and phytoremediation have been introduced and critically reviewed in the context of decontaminating the soils.Next,biopolymerisation,biomineralisation and bioneutralisation processes have been depicted with a special emphasis on the applications including but not limited to soil stabilisation,soil erosion prevention,anti-desertification and pH neutralisation.Each of these methods have their own limitations and bottlenecks while scaling up,and these challenges have been summarised and some possible paths to overcome the challenges have also been discussed.The state of the art of electromagnetic(EM)monitoring methods to capture the effects of biomediation on spatio-temporal soil properties are then highlighted as a non-invasive and rapid pathway to track the progress of biomediated soil processes.Finally,each of the technologies discussed have been evaluated for their maturity level using the principles of technology readiness level(TRL).A majority of the technologies amounting to around 77%are still in the TRL 4e7,i.e.in the valley of death.It is thus evident that development of these technologies needs to be supported with appropriate funding for improving their maturity to a level of industrial deployment.展开更多
Traffic forecasting is crucial for intelligent transportation systems.It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data.However,recent deep-l...Traffic forecasting is crucial for intelligent transportation systems.It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data.However,recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results.Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models.To tackle these challenges,we propose a traffic flow prediction model based on large language models(LLMs)to generate explainable traffic predictions,named xTP-LLM.By transferring multi-modal traffic data into natural language descriptions,xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data.The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data.Empirically,xTP-LLM shows competitive accuracy compared with deep learning baselines,while providing an intuitive and reliable explanation for predictions.This study contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation.展开更多
文摘This paper builds on exploring the applications of biomediated pathways to solve geotechnical challenges.First,the state of the art of biological remediation strategies including microbial remediation and phytoremediation have been introduced and critically reviewed in the context of decontaminating the soils.Next,biopolymerisation,biomineralisation and bioneutralisation processes have been depicted with a special emphasis on the applications including but not limited to soil stabilisation,soil erosion prevention,anti-desertification and pH neutralisation.Each of these methods have their own limitations and bottlenecks while scaling up,and these challenges have been summarised and some possible paths to overcome the challenges have also been discussed.The state of the art of electromagnetic(EM)monitoring methods to capture the effects of biomediation on spatio-temporal soil properties are then highlighted as a non-invasive and rapid pathway to track the progress of biomediated soil processes.Finally,each of the technologies discussed have been evaluated for their maturity level using the principles of technology readiness level(TRL).A majority of the technologies amounting to around 77%are still in the TRL 4e7,i.e.in the valley of death.It is thus evident that development of these technologies needs to be supported with appropriate funding for improving their maturity to a level of industrial deployment.
基金National Natural Science Foundation of China(No.52302379)Guangdong Provincial Natural Science Foundation-General Project(No.2024A1515011790)+3 种基金Guangzhou Basic and Applied Basic Research Projects(Nos.2023A03J0106 and 2024A04J4290)Guangdong Province General Universities Youth Innovative Talents Project(No.2023KQNCX100)Guangzhou Municipal Science and Technology Project(No.2023A03J0011)Nansha District Key R&D Project(No.2023ZD006).
文摘Traffic forecasting is crucial for intelligent transportation systems.It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data.However,recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results.Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models.To tackle these challenges,we propose a traffic flow prediction model based on large language models(LLMs)to generate explainable traffic predictions,named xTP-LLM.By transferring multi-modal traffic data into natural language descriptions,xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data.The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data.Empirically,xTP-LLM shows competitive accuracy compared with deep learning baselines,while providing an intuitive and reliable explanation for predictions.This study contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation.
