Technology mediates the interaction between us and our natural environment, so technological innovation is essential in the transition to sustainable developmentSustainable development. This paper overviews (1) current and potential applications of Artificial Intelligence (AIArtificial Intelligence (AI)) in the development and deployment of environmentalEnvironmental biosensorsBiosensors, also touching on related applications like healthcare, food processing and manufacturing, and (2) the resulting “big picture.” This is done through the lenses provided by a previously developed model of holistic management of data, informationInformation and knowledge for cost-effective development of solutions/generation of eco-innovationEco-innovation in a “state space” defined by a scale of solution readiness levels (SRL) and a logic set of systemic sustainabilitySustainability filters (SFs). In brief, the main AIArtificial Intelligence (AI) applications are related to machine learningMachine learning (ML) for pattern detection in the biorecognition component of biosensorsBiosensors, and in the specificity-and-sensitivity dynamics. These open new possibilities for the monitoringMonitoring of pollutants and pathogens. Then, computer-based handling of high-throughput analytical techniques positions ML/AIArtificial Intelligence (AI) as a strong enabler, but this is conditional upon in-depth understanding of biological processes. This means that useful AIArtificial Intelligence (AI) applications in the multi-disciplinary field of biosensorBiosensors development begin with fundamental research and continue all along the classic Technology Readiness LevelsTechnology readiness levels (TRLs) scale, from TRL1 to TRL9. Then, the paper also shows that and how the operational requirements derived from the integrated systemic perspective on sustainabilitySustainability bring biosensorsBiosensors closer to sustainabilitySustainability in a semantic similarity network (SSNSemantic Similarity Network (SSN)). In practice, those requirements imply some key restrictions (and addressing practical questions like “What is actually the environmentalEnvironmental footprint of a biosensorBiosensors lifecycle?” and “How can a given biosensorBiosensors contribute concretely to advancing sustainabilitySustainability?”). But those same restrictions also have a ‘catalyzer’ effect because they help channel efforts into faster and more cost-effective development of eco-innovative solutions, and this effect in fact expands the range of objective possibilities for sustainable developmentSustainable development.

Uses and Perspectives of Artificial Intelligence in Environmental Biosensors

章节
发表日期：

2026年

查看全文

Ioan M. Ciumasu

摘要

Technology mediates the interaction between us and our natural environment, so technological innovation is essential in the transition to sustainable developmentSustainable development. This paper overviews (1) current and potential applications of Artificial Intelligence (AIArtificial Intelligence (AI)) in the development and deployment of environmentalEnvironmental biosensorsBiosensors, also touching on related applications like healthcare, food processing and manufacturing, and (2) the resulting “big picture.” This is done through the lenses provided by a previously developed model of holistic management of data, informationInformation and knowledge for cost-effective development of solutions/generation of eco-innovationEco-innovation in a “state space” defined by a scale of solution readiness levels (SRL) and a logic set of systemic sustainabilitySustainability filters (SFs). In brief, the main AIArtificial Intelligence (AI) applications are related to machine learningMachine learning (ML) for pattern detection in the biorecognition component of biosensorsBiosensors, and in the specificity-and-sensitivity dynamics. These open new possibilities for the monitoringMonitoring of pollutants and pathogens. Then, computer-based handling of high-throughput analytical techniques positions ML/AIArtificial Intelligence (AI) as a strong enabler, but this is conditional upon in-depth understanding of biological processes. This means that useful AIArtificial Intelligence (AI) applications in the multi-disciplinary field of biosensorBiosensors development begin with fundamental research and continue all along the classic Technology Readiness LevelsTechnology readiness levels (TRLs) scale, from TRL1 to TRL9. Then, the paper also shows that and how the operational requirements derived from the integrated systemic perspective on sustainabilitySustainability bring biosensorsBiosensors closer to sustainabilitySustainability in a semantic similarity network (SSNSemantic Similarity Network (SSN)). In practice, those requirements imply some key restrictions (and addressing practical questions like “What is actually the environmentalEnvironmental footprint of a biosensorBiosensors lifecycle?” and “How can a given biosensorBiosensors contribute concretely to advancing sustainabilitySustainability?”). But those same restrictions also have a ‘catalyzer’ effect because they help channel efforts into faster and more cost-effective development of eco-innovative solutions, and this effect in fact expands the range of objective possibilities for sustainable developmentSustainable development.